7.0.1.0

* ntf server: shard push workers per notification token

* ntf server: inline push worker shard calculation

.github/workflows/build.yml

@@ -24,6 +24,8 @@ jobs:
       - name: Clone project
         if: startsWith(github.ref, 'refs/tags/v')
         uses: actions/checkout@v3
+        with:
+          submodules: recursive
 
       - name: Build changelog
         id: build_changelog
@@ -114,6 +116,8 @@ jobs:
       - name: Clone project
         if: matrix.should_run == true
         uses: actions/checkout@v3
+        with:
+          submodules: recursive
 
       - name: Set up Docker Buildx
         if: matrix.should_run == true
@@ -173,7 +177,7 @@ jobs:
             -v ${{ github.workspace }}:/project \
             build/${{ matrix.os }}:latest
 
-      - name: Build smp-server (postgresql) and tests
+      - name: Build smp-server, xftp-server (postgresql) and tests
         if: matrix.should_run == true
         shell: docker exec -t builder sh -eu {0}
         run: |
@@ -182,12 +186,12 @@ jobs:
           cabal update
           cabal build --jobs=$(nproc) --enable-tests -fserver_postgres
           mkdir -p /out
-          for i in smp-server simplexmq-test; do
+          for i in smp-server xftp-server simplexmq-test; do
             bin=$(find /project/dist-newstyle -name "$i" -type f -executable)
             chmod +x "$bin"
             mv "$bin" /out/
           done
-          strip /out/smp-server
+          strip /out/smp-server /out/xftp-server
 
       - name: Copy simplexmq-test from container
         if: matrix.should_run == true
@@ -195,19 +199,29 @@ jobs:
         run: |
           docker cp builder:/out/simplexmq-test .
 
-      - name: Copy smp-server (postgresql) from container and prepare it
+      - name: Copy smp-server, xftp-server (postgresql) from container and prepare it
         if: startsWith(github.ref, 'refs/tags/v') && matrix.should_run == true
         id: prepare-postgres
         shell: bash
         run: |
-          name="smp-server-postgres-ubuntu-${{ matrix.os_underscore }}-${{ matrix.arch }}"
-          docker cp builder:/out/smp-server $name
+          printf 'bins<<EOF\n' > bins.output
+          printf 'hashes<<EOF\n' > hashes.output
 
-          path="${{ github.workspace }}/$name"
-          echo "bin=$path" >> $GITHUB_OUTPUT
+          for i in smp-server xftp-server; do
+            name="${i}-postgres-ubuntu-${{ matrix.os_underscore }}-${{ matrix.arch }}"
+            docker cp builder:/out/$i $name
 
-          hash="SHA2-256($name)= $(openssl sha256 $path | cut -d' ' -f 2)"
-          printf 'hash=%s' "$hash" >> $GITHUB_OUTPUT
+            path="${{ github.workspace }}/$name"
+            hash="SHA2-256($name)= $(openssl sha256 $path | cut -d' ' -f 2)"
+
+            printf '%s\n' "$path" >> bins.output
+            printf '%s\n\n' "$hash" >> hashes.output
+          done
+          printf 'EOF\n' >> bins.output
+          printf 'EOF\n' >> hashes.output
+
+          cat bins.output >> "$GITHUB_OUTPUT"
+          cat hashes.output >> "$GITHUB_OUTPUT"
 
       - name: Build everything else (standard)
         if: matrix.should_run == true
@@ -257,10 +271,10 @@ jobs:
           fail_on_unmatched_files: true
           body: |
             ${{ steps.prepare-regular.outputs.hashes }}
-            ${{ steps.prepare-postgres.outputs.hash }}
+            ${{ steps.prepare-postgres.outputs.hashes }}
           files: |
             ${{ steps.prepare-regular.outputs.bins }}
-            ${{ steps.prepare-postgres.outputs.bin }}
+            ${{ steps.prepare-postgres.outputs.bins }}
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/docker-image.yml

@@ -20,6 +20,8 @@ jobs:
     steps:
       - name: Clone project
         uses: actions/checkout@v4
+        with:
+          submodules: recursive
 
       - name: Log in to Docker Hub
         uses: simplex-chat/docker-login-action@v3

.github/workflows/reproduce-schedule.yml

@@ -11,6 +11,8 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v3
+        with:
+          submodules: recursive
 
       - name: Get latest release
         shell: bash

.gitmodules

@@ -0,0 +1,6 @@
+[submodule "cbits/libbbs"]
+	path = cbits/libbbs
+	url = https://github.com/simplex-chat/libbbs.git
+[submodule "cbits/blst"]
+	path = cbits/blst
+	url = https://github.com/supranational/blst.git

CHANGELOG.md

@@ -1,3 +1,39 @@
+# 6.5.1
+
+Version 6.5.1.0
+
+XFTP client:
+- backwards compatible file header decoding.
+
+# 6.5.0
+
+Version 6.5.0.17
+
+SMP agent:
+- improve subscriptions
+  - reduce memory usage and retries during initial subscription (#1758)
+  - fix race resulting in pending subscriptions never subscribed (#1756)
+  - batch processing of subscription results and errors (#1652)
+  - reduce memory usage of active subscriptions.
+- drop message after N reception attempts (#1762)
+- fix possible deadlocks of queue overloading when processing messages (#1713)
+- improved APIs for short link management and creation.
+- support multiple link owners in link data (#1701)
+
+SMP server:
+- store messages in PostgreSQL (#1622).
+- reduce memory usage with PostgreSQL database - do not use queue cache (#1637)
+- fix in-memory server not restoring queue/service associations after 2+ restarts (#1618)
+
+XFTP server:
+- support PostgreSQL database.
+- add server page.
+- support uploads from web clients.
+
+Servers:
+- better socket leak prevention during TLS handshake, NetworkError type to bette diagnose connection errors (#1619)
+- use "=" as default INI key-value separator (#1767)
+
 # 6.4.4
 
 Servers:

README.md

@@ -33,7 +33,7 @@ To initialize the server use `smp-server init -n <fqdn>` (or `smp-server init --
 
 SMP server uses in-memory persistence with an optional append-only log of created queues that allows to re-start the server without losing the connections. This log is compacted on every server restart, permanently removing suspended and removed queues.
 
-To enable store log, initialize server using `smp-server -l` command, or modify `smp-server.ini` created during initialization (uncomment `enable: on` option in the store log section). Use `smp-server --help` for other usage tips.
+To enable store log, initialize server using `smp-server -l` command, or modify `smp-server.ini` created during initialization (uncomment `enable = on` option in the store log section). Use `smp-server --help` for other usage tips.
 
 Starting from version 2.3.0, when store log is enabled, the server would also enable saving undelivered messages on exit and restoring them on start. This can be disabled via a separate setting `restore_messages` in `smp-server.ini` file. Saving messages would only work if the server is stopped with SIGINT signal (keyboard interrupt), if it is stopped with SIGTERM signal the messages would not be saved.
 

apps/common/Web/static/index.html

@@ -105,13 +105,13 @@
                     class="text-[16px] leading-[26px] tracking-[0.01em] nav-link-text text-black dark:text-white before:bg-black dark:before:bg-white">Server
                     information</span></a>
               </li>
-              <x-xftpConfig>
+              <!-- <x-xftpConfig>
               <li class="nav-link relative"><a href="/file"
                   class="flex items-center justify-between gap-2 lg:py-5 whitespace-nowrap"><span
                     class="text-[16px] leading-[26px] tracking-[0.01em] nav-link-text text-black dark:text-white before:bg-black dark:before:bg-white">File
                     transfer</span></a>
               </li>
-              </x-xftpConfig>
+              </x-xftpConfig> -->
             </ul><a target="_blank" href="https://github.com/simplex-chat/simplex-chat#help-us-with-donations"
               class="whitespace-nowrap flex items-center gap-1 self-center text-white dark:text-black text-[16px] font-medium tracking-[0.02em] rounded-[34px] bg-primary-light dark:bg-primary-dark py-3 lg:py-2 px-20 lg:px-5 mb-16 lg:mb-0">Donate</a>
           </div>

apps/xftp-server/XFTPWeb.hs

@@ -34,7 +34,7 @@ xftpMediaContent = $(embedDir "apps/xftp-server/static/media/")
 xftpFilePageHtml :: ByteString
 xftpFilePageHtml = $(embedFile "apps/xftp-server/static/file.html")
 
-xftpGenerateSite :: XFTPServerConfig -> Maybe ServerPublicInfo -> Maybe TransportHost -> FilePath -> IO ()
+xftpGenerateSite :: XFTPServerConfig s -> Maybe ServerPublicInfo -> Maybe TransportHost -> FilePath -> IO ()
 xftpGenerateSite cfg info onionHost path = do
   let substs = xftpSubsts cfg info onionHost
   Web.generateSite embeddedContent (render (Web.indexHtml embeddedContent) substs) [] path
@@ -50,10 +50,10 @@ xftpGenerateSite cfg info onionHost path = do
       createDirectoryIfMissing True dir
       forM_ content_ $ \(fp, content) -> B.writeFile (dir </> fp) content
 
-xftpServerInformation :: XFTPServerConfig -> Maybe ServerPublicInfo -> Maybe TransportHost -> ByteString
+xftpServerInformation :: XFTPServerConfig s -> Maybe ServerPublicInfo -> Maybe TransportHost -> ByteString
 xftpServerInformation cfg info onionHost = render (Web.indexHtml embeddedContent) (xftpSubsts cfg info onionHost)
 
-xftpSubsts :: XFTPServerConfig -> Maybe ServerPublicInfo -> Maybe TransportHost -> [(ByteString, Maybe ByteString)]
+xftpSubsts :: XFTPServerConfig s -> Maybe ServerPublicInfo -> Maybe TransportHost -> [(ByteString, Maybe ByteString)]
 xftpSubsts XFTPServerConfig {fileExpiration, logStatsInterval, allowNewFiles, newFileBasicAuth} information onionHost =
   [("smpConfig", Nothing), ("xftpConfig", Just "y")] <> substConfig <> serverInfoSubsts simplexmqSource information <> [("onionHost", strEncode <$> onionHost), ("iniFileName", Just "file-server.ini")]
   where

apps/xftp-server/static/xftp-web-bundle/crypto.worker.js

@@ -619,7 +619,6 @@ async function handleEncrypt(id, data, fileName) {
   const digest = sha512Streaming([encData], (done) => {
     self.postMessage({ id, type: "progress", done: source.length + done, total });
   }, encDataLen);
-  console.log(`[WORKER-DBG] encrypt: encData.len=${encData.length} digest=${_whex(digest, 64)} chunkSizes=[${chunkSizes.join(",")}]`);
   const dir = await getSessionDir();
   const fileHandle = await dir.getFileHandle("upload.bin", { create: true });
   const writeHandle = await fileHandle.createSyncAccessHandle();
@@ -643,9 +642,7 @@ function handleReadChunk(id, offset, size) {
 }
 async function handleDecryptAndStore(id, dhSecret, nonce, body, chunkDigest, chunkNo) {
   const bodyArr = new Uint8Array(body);
-  console.log(`[WORKER-DBG] store chunk=${chunkNo} body.len=${bodyArr.length} nonce=${_whex(nonce, 24)} dhSecret=${_whex(dhSecret)} digest=${_whex(chunkDigest, 32)} body[0..8]=${_whex(bodyArr)} body[-8..]=${_whex(bodyArr.slice(-8))}`);
   const decrypted = decryptReceivedChunk(dhSecret, nonce, bodyArr, chunkDigest);
-  console.log(`[WORKER-DBG] decrypted chunk=${chunkNo} len=${decrypted.length} [0..8]=${_whex(decrypted)} [-8..]=${_whex(decrypted.slice(-8))}`);
   if (useMemory) {
     memoryChunks.set(chunkNo, decrypted);
     self.postMessage({ id, type: "stored" });
@@ -660,7 +657,6 @@ async function handleDecryptAndStore(id, dhSecret, nonce, body, chunkDigest, chu
   currentDownloadOffset += decrypted.length;
   chunkMeta.set(chunkNo, { offset, size: decrypted.length });
   const written = downloadWriteHandle.write(decrypted, { at: offset });
-  console.log(`[WORKER-DBG] OPFS write chunk=${chunkNo} offset=${offset} size=${decrypted.length} written=${written}`);
   if (written !== decrypted.length) {
     console.warn(`[WORKER] OPFS write failed chunk=${chunkNo}: ${written}/${decrypted.length}, falling back to in-memory storage`);
     for (const [cn, meta] of chunkMeta.entries()) {
@@ -684,23 +680,16 @@ async function handleDecryptAndStore(id, dhSecret, nonce, body, chunkDigest, chu
     return;
   }
   downloadWriteHandle.flush();
-  const verifyBuf = new Uint8Array(Math.min(8, decrypted.length));
-  downloadWriteHandle.read(verifyBuf, { at: offset });
-  const verifyEnd = new Uint8Array(Math.min(8, decrypted.length));
-  downloadWriteHandle.read(verifyEnd, { at: offset + decrypted.length - verifyEnd.length });
-  console.log(`[WORKER-DBG] OPFS verify chunk=${chunkNo} readBack[0..8]=${_whex(verifyBuf)} readBack[-8..]=${_whex(verifyEnd)} expected[0..8]=${_whex(decrypted)} expected[-8..]=${_whex(decrypted.slice(-8))}`);
   self.postMessage({ id, type: "stored" });
 }
 async function handleVerifyAndDecrypt(id, size, digest, key, nonce) {
-  console.log(`[WORKER-DBG] verify: expectedSize=${size} expectedDigest=${_whex(digest, 64)} useMemory=${useMemory} chunkMeta.size=${chunkMeta.size} memoryChunks.size=${memoryChunks.size}`);
   const chunks = [];
   let totalSize = 0;
   const total = size * 3;
   let done = 0;
   if (useMemory) {
     const sorted = [...memoryChunks.entries()].sort((a, b) => a[0] - b[0]);
-    for (const [chunkNo, data] of sorted) {
-      console.log(`[WORKER-DBG] verify memory chunk=${chunkNo} size=${data.length}`);
+    for (const [, data] of sorted) {
       chunks.push(data);
       totalSize += data.length;
       done += data.length;
@@ -715,12 +704,10 @@ async function handleVerifyAndDecrypt(id, size, digest, key, nonce) {
     const dir = await getSessionDir();
     const fileHandle = await dir.getFileHandle("download.bin");
     const readHandle = await fileHandle.createSyncAccessHandle();
-    console.log(`[WORKER-DBG] verify: OPFS file size=${readHandle.getSize()}`);
     const sortedEntries = [...chunkMeta.entries()].sort((a, b) => a[0] - b[0]);
-    for (const [chunkNo, meta] of sortedEntries) {
+    for (const [, meta] of sortedEntries) {
       const buf = new Uint8Array(meta.size);
-      const bytesRead = readHandle.read(buf, { at: meta.offset });
-      console.log(`[WORKER-DBG] verify read chunk=${chunkNo} offset=${meta.offset} size=${meta.size} bytesRead=${bytesRead} [0..8]=${_whex(buf)} [-8..]=${_whex(buf.slice(-8))}`);
+      readHandle.read(buf, { at: meta.offset });
       chunks.push(buf);
       totalSize += meta.size;
       done += meta.size;
@@ -745,20 +732,9 @@ async function handleVerifyAndDecrypt(id, size, digest, key, nonce) {
   }
   const actualDigest = r.crypto_hash_sha512_final(state);
   if (!digestEqual(actualDigest, digest)) {
-    console.error(`[WORKER-DBG] DIGEST MISMATCH: expected=${_whex(digest, 64)} actual=${_whex(actualDigest, 64)} chunks=${chunks.length} totalSize=${totalSize}`);
-    const state2 = r.crypto_hash_sha512_init();
-    for (let i = 0; i < chunks.length; i++) {
-      const chunk = chunks[i];
-      for (let off = 0; off < chunk.length; off += hashSEG) {
-        r.crypto_hash_sha512_update(state2, chunk.subarray(off, Math.min(off + hashSEG, chunk.length)));
-      }
-      const chunkDigest = sha512Streaming([chunk]);
-      console.error(`[WORKER-DBG] chunk[${i}] size=${chunk.length} sha512=${_whex(chunkDigest, 32)}… [0..8]=${_whex(chunk)} [-8..]=${_whex(chunk.slice(-8))}`);
-    }
     self.postMessage({ id, type: "error", message: "File digest mismatch" });
     return;
   }
-  console.log(`[WORKER-DBG] verify: digest OK`);
   const result = decryptChunks(BigInt(size), chunks, key, nonce, (d) => {
     self.postMessage({ id, type: "progress", done: size * 2 + d, total });
   });

apps/xftp-server/static/xftp-web-bundle/index.js

@@ -334,11 +334,6 @@ class WorkerBackend {
     const nonceCopy = new Uint8Array(nonce);
     const digestCopy = new Uint8Array(digest);
     const buf = this.toTransferable(body);
-    const hex = (b, n = 8) => {
-      const u = b instanceof ArrayBuffer ? new Uint8Array(b) : b;
-      return Array.from(u.slice(0, n)).map((x) => x.toString(16).padStart(2, "0")).join("");
-    };
-    console.log(`[BACKEND-DBG] chunk=${chunkNo} body.len=${body.length} body.byteOff=${body.byteOffset} buf.byteLen=${buf.byteLength} nonce=${hex(nonceCopy, 24)} dhSecret=${hex(dhSecretCopy)} digest=${hex(digestCopy, 32)} buf[0..8]=${hex(buf)} body[-8..]=${hex(body.slice(-8))}`);
     await this.send(
       { type: "decryptAndStoreChunk", dhSecret: dhSecretCopy, nonce: nonceCopy, body: buf, chunkDigest: digestCopy, chunkNo },
       [buf]
@@ -10913,14 +10908,12 @@ async function sendXFTPCommandOnce(client, privateKey, entityId, cmdBytes, chunk
   const block = encodeAuthTransmission(client.sessionId, corrId, entityId, cmdBytes, privateKey);
   const reqBody = chunkData ? concatBytes$1(block, chunkData) : block;
   const fullResp = await client.transport.post(reqBody);
-  console.log(`[XFTP-DBG] sendOnce: fullResp.length=${fullResp.length} entityId=${_hex(entityId)} cmdTag=${cmdBytes[0]}`);
   if (fullResp.length < XFTP_BLOCK_SIZE) {
     console.error("[XFTP] Response too short: %d bytes (expected >= %d)", fullResp.length, XFTP_BLOCK_SIZE);
     throw new Error("Server response too short");
   }
   const respBlock = fullResp.subarray(0, XFTP_BLOCK_SIZE);
   const body = fullResp.subarray(XFTP_BLOCK_SIZE);
-  console.log(`[XFTP-DBG] sendOnce: body.length=${body.length} body.byteOffset=${body.byteOffset} body.buffer.byteLength=${body.buffer.byteLength}`);
   const raw = blockUnpad(respBlock);
   if (raw.length < 20) {
     const text = new TextDecoder().decode(raw);
@@ -10939,18 +10932,13 @@ async function sendXFTPCommandOnce(client, privateKey, entityId, cmdBytes, chunk
   }
   return { response, body };
 }
-function _hex(b, n = 8) {
-  return Array.from(b.slice(0, n)).map((x) => x.toString(16).padStart(2, "0")).join("");
-}
 async function sendXFTPCommand(agent, server, privateKey, entityId, cmdBytes, chunkData, maxRetries = 3) {
   let clientP = getXFTPServerClient(agent, server);
   let client = await clientP;
   for (let attempt = 1; attempt <= maxRetries; attempt++) {
     try {
-      if (attempt > 1) console.log(`[XFTP-DBG] sendCmd: retry attempt=${attempt}/${maxRetries}`);
       return await sendXFTPCommandOnce(client, privateKey, entityId, cmdBytes, chunkData);
     } catch (e) {
-      console.log(`[XFTP-DBG] sendCmd: attempt=${attempt} failed: ${e instanceof Error ? e.message : String(e)} retriable=${isRetriable(e)}`);
       if (!isRetriable(e)) {
         throw categorizeError(e);
       }
@@ -10979,7 +10967,6 @@ async function downloadXFTPChunkRaw(agent, server, rpKey, fId) {
   const { response, body } = await sendXFTPCommand(agent, server, rpKey, fId, cmd);
   if (response.type !== "FRFile") throw new Error("unexpected response: " + response.type);
   const dhSecret = dh(response.rcvDhKey, privateKey);
-  console.log(`[XFTP-DBG] dlChunkRaw: body.length=${body.length} nonce=${_hex(response.nonce, 24)} dhSecret=${_hex(dhSecret)} body[0..8]=${_hex(body)} body[-8..]=${_hex(body.slice(-8))}`);
   return { dhSecret, nonce: response.nonce, body };
 }
 async function downloadXFTPChunk(agent, server, rpKey, fId, digest) {
@@ -11012,7 +10999,6 @@ function encryptFileForUpload(source, fileName) {
   const encSize = BigInt(chunkSizes.reduce((a, b) => a + b, 0));
   const encData = encryptFile(source, fileHdr, key, nonce, fileSize, encSize);
   const digest = sha512Streaming([encData]);
-  console.log(`[AGENT-DBG] encrypt: encData.len=${encData.length} digest=${_dbgHex(digest, 64)} chunkSizes=[${chunkSizes.join(",")}]`);
   return { encData, digest, key, nonce, chunkSizes };
 }
 const DEFAULT_REDIRECT_THRESHOLD = 400;
@@ -11169,9 +11155,7 @@ async function downloadFileRaw(agent, fd, onRawChunk, options) {
   if (err) throw new Error("downloadFileRaw: " + err);
   const { onProgress} = options ?? {};
   if (fd.redirect !== null) {
-    console.log(`[AGENT-DBG] resolving redirect: outer size=${fd.size} chunks=${fd.chunks.length}`);
     fd = await resolveRedirect(agent, fd);
-    console.log(`[AGENT-DBG] resolved: size=${fd.size} chunks=${fd.chunks.length} digest=${Array.from(fd.digest.slice(0, 16)).map((x) => x.toString(16).padStart(2, "0")).join("")}…`);
   }
   const resolvedFd = fd;
   let downloaded = 0;
@@ -11189,7 +11173,6 @@ async function downloadFileRaw(agent, fd, onRawChunk, options) {
       const seed = decodePrivKeyEd25519(replica.replicaKey);
       const kp = ed25519KeyPairFromSeed(seed);
       const raw = await downloadXFTPChunkRaw(agent, server, kp.privateKey, replica.replicaId);
-      console.log(`[AGENT-DBG] chunk=${chunk.chunkNo} body.len=${raw.body.length} expectedChunkSize=${chunk.chunkSize} digest=${_dbgHex(chunk.digest, 32)} body.byteOffset=${raw.body.byteOffset} body.buffer.byteLength=${raw.body.buffer.byteLength}`);
       await onRawChunk({
         chunkNo: chunk.chunkNo,
         dhSecret: raw.dhSecret,

bench/ClientSim.hs

@@ -1,133 +0,0 @@
-{-# LANGUAGE DataKinds #-}
-{-# LANGUAGE DuplicateRecordFields #-}
-{-# LANGUAGE GADTs #-}
-{-# LANGUAGE LambdaCase #-}
-{-# LANGUAGE NamedFieldPuns #-}
-{-# LANGUAGE OverloadedStrings #-}
-{-# LANGUAGE PatternSynonyms #-}
-{-# LANGUAGE ScopedTypeVariables #-}
-{-# LANGUAGE TupleSections #-}
-{-# LANGUAGE TypeApplications #-}
-{-# OPTIONS_GHC -fno-warn-ambiguous-fields #-}
-
-module ClientSim
-  ( SimClient (..),
-    connectClient,
-    createQueue,
-    subscribeQueue,
-    sendMessage,
-    receiveAndAck,
-    connectN,
-    benchKeyHash,
-  )
-where
-
-import Control.Concurrent.Async (mapConcurrently)
-import Control.Concurrent.STM
-import Control.Monad (forM_)
-import Control.Monad.Except (runExceptT)
-import Data.ByteString.Char8 (ByteString)
-import Data.List (unfoldr)
-import qualified Data.List.NonEmpty as L
-import Network.Socket (ServiceName)
-import qualified Simplex.Messaging.Crypto as C
-import Simplex.Messaging.Encoding
-import Simplex.Messaging.Protocol
-import Simplex.Messaging.Transport
-import Simplex.Messaging.Transport.Client
-import Simplex.Messaging.Version
-
-data SimClient = SimClient
-  { scHandle :: THandleSMP TLS 'TClient,
-    scRcvKey :: C.APrivateAuthKey,
-    scRcvId :: RecipientId,
-    scSndId :: SenderId,
-    scDhSecret :: C.DhSecret 'C.X25519
-  }
-
-benchKeyHash :: C.KeyHash
-benchKeyHash = "LcJUMfVhwD8yxjAiSaDzzGF3-kLG4Uh0Fl_ZIjrRwjI="
-
-connectClient :: TransportHost -> ServiceName -> IO (THandleSMP TLS 'TClient)
-connectClient host port = do
-  let tcConfig = defaultTransportClientConfig {clientALPN = Just alpnSupportedSMPHandshakes}
-  runTransportClient tcConfig Nothing host port (Just benchKeyHash) $ \h ->
-    runExceptT (smpClientHandshake h Nothing benchKeyHash supportedClientSMPRelayVRange False Nothing) >>= \case
-      Right th -> pure th
-      Left e -> error $ "SMP handshake failed: " <> show e
-
-connectN :: Int -> TransportHost -> ServiceName -> IO [THandleSMP TLS 'TClient]
-connectN n host port = do
-  let batches = chunksOf 100 [1 .. n]
-  concat <$> mapM (\batch -> mapConcurrently (\_ -> connectClient host port) batch) batches
-
-createQueue :: THandleSMP TLS 'TClient -> IO SimClient
-createQueue h = do
-  g <- C.newRandom
-  (rPub, rKey) <- atomically $ C.generateAuthKeyPair C.SEd448 g
-  (sPub, sKey) <- atomically $ C.generateAuthKeyPair C.SEd25519 g
-  (dhPub, dhPriv :: C.PrivateKeyX25519) <- atomically $ C.generateKeyPair g
-  -- NEW command
-  Resp "1" NoEntity (Ids rId sId srvDh) <- signSendRecv h rKey ("1", NoEntity, New rPub dhPub)
-  let dhShared = C.dh' srvDh dhPriv
-  -- KEY command (secure queue)
-  Resp "2" _ OK <- signSendRecv h rKey ("2", rId, KEY sPub)
-  pure SimClient {scHandle = h, scRcvKey = rKey, scRcvId = rId, scSndId = sId, scDhSecret = dhShared}
-
-subscribeQueue :: SimClient -> IO ()
-subscribeQueue SimClient {scHandle = h, scRcvKey = rKey, scRcvId = rId} = do
-  Resp "3" _ (SOK _) <- signSendRecv h rKey ("3", rId, SUB)
-  pure ()
-
-sendMessage :: THandleSMP TLS 'TClient -> C.APrivateAuthKey -> SenderId -> ByteString -> IO ()
-sendMessage h sKey sId body = do
-  Resp "4" _ OK <- signSendRecv h sKey ("4", sId, SEND noMsgFlags body)
-  pure ()
-
-receiveAndAck :: SimClient -> IO ()
-receiveAndAck SimClient {scHandle = h, scRcvKey = rKey, scRcvId = rId} = do
-  (_, _, Right (MSG RcvMessage {msgId = mId})) <- tGet1 h
-  Resp "5" _ OK <- signSendRecv h rKey ("5", rId, ACK mId)
-  pure ()
-
--- Helpers (same patterns as ServerTests.hs)
-
-pattern Resp :: CorrId -> EntityId -> BrokerMsg -> Transmission (Either ErrorType BrokerMsg)
-pattern Resp corrId queueId command <- (corrId, queueId, Right command)
-
-pattern Ids :: RecipientId -> SenderId -> RcvPublicDhKey -> BrokerMsg
-pattern Ids rId sId srvDh <- IDS (QIK rId sId srvDh _ _ Nothing Nothing)
-
-pattern New :: RcvPublicAuthKey -> RcvPublicDhKey -> Command 'Creator
-pattern New rPub dhPub = NEW (NewQueueReq rPub dhPub Nothing SMSubscribe (Just (QRMessaging Nothing)) Nothing)
-
-signSendRecv :: (Transport c, PartyI p) => THandleSMP c 'TClient -> C.APrivateAuthKey -> (ByteString, EntityId, Command p) -> IO (Transmission (Either ErrorType BrokerMsg))
-signSendRecv h pk t = do
-  signSend h pk t
-  (r L.:| _) <- tGetClient h
-  pure r
-
-signSend :: (Transport c, PartyI p) => THandleSMP c 'TClient -> C.APrivateAuthKey -> (ByteString, EntityId, Command p) -> IO ()
-signSend h@THandle {params} (C.APrivateAuthKey a pk) (corrId, qId, cmd) = do
-  let TransmissionForAuth {tForAuth, tToSend} = encodeTransmissionForAuth params (CorrId corrId, qId, cmd)
-      authorize t = (,Nothing) <$> case a of
-        C.SEd25519 -> Just . TASignature . C.ASignature C.SEd25519 $ C.sign' pk t
-        C.SEd448 -> Just . TASignature . C.ASignature C.SEd448 $ C.sign' pk t
-        C.SX25519 -> (\THAuthClient {peerServerPubKey = k} -> TAAuthenticator $ C.cbAuthenticate k pk (C.cbNonce corrId) t) <$> thAuth params
-  Right () <- tPut1 h (authorize tForAuth, tToSend)
-  pure ()
-
-tPut1 :: Transport c => THandle v c 'TClient -> SentRawTransmission -> IO (Either TransportError ())
-tPut1 h t = do
-  rs <- tPut h (Right t L.:| [])
-  case rs of
-    (r : _) -> pure r
-    [] -> error "tPut1: empty result"
-
-tGet1 :: (ProtocolEncoding v err cmd, Transport c) => THandle v c 'TClient -> IO (Transmission (Either err cmd))
-tGet1 h = do
-  (r L.:| _) <- tGetClient h
-  pure r
-
-chunksOf :: Int -> [a] -> [[a]]
-chunksOf n = unfoldr $ \xs -> if null xs then Nothing else Just (splitAt n xs)

bench/Dockerfile

@@ -1,25 +0,0 @@
-FROM haskell:9.6.3 AS build
-
-WORKDIR /src
-
-# Copy cabal file first for dependency caching
-COPY simplexmq.cabal cabal.project* ./
-RUN cabal update && cabal build --only-dependencies -f server_postgres smp-server-bench || true
-
-# Copy full source
-COPY . .
-RUN cabal build -f server_postgres smp-server-bench \
-  && cp $(cabal list-bin -f server_postgres smp-server-bench) /usr/local/bin/smp-server-bench
-
-FROM debian:bookworm-slim
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-      libgmp10 libpq5 libffi8 zlib1g ca-certificates \
-  && rm -rf /var/lib/apt/lists/*
-
-COPY --from=build /usr/local/bin/smp-server-bench /usr/local/bin/smp-server-bench
-COPY tests/fixtures /app/tests/fixtures
-
-WORKDIR /app
-
-ENTRYPOINT ["smp-server-bench"]

bench/Main.hs

@@ -1,243 +0,0 @@
-{-# LANGUAGE CPP #-}
-{-# LANGUAGE DataKinds #-}
-{-# LANGUAGE DuplicateRecordFields #-}
-{-# LANGUAGE GADTs #-}
-{-# LANGUAGE LambdaCase #-}
-{-# LANGUAGE NamedFieldPuns #-}
-{-# LANGUAGE NumericUnderscores #-}
-{-# LANGUAGE OverloadedStrings #-}
-{-# LANGUAGE ScopedTypeVariables #-}
-{-# LANGUAGE TypeApplications #-}
-{-# OPTIONS_GHC -fno-warn-ambiguous-fields #-}
-
-module Main where
-
-import Control.Concurrent (threadDelay)
-import Control.Concurrent.Async (async, cancel, forConcurrently_, mapConcurrently, mapConcurrently_)
-import Control.Concurrent.STM
-import Control.Monad (forever, forM_, void, when)
-import Data.ByteString.Char8 (ByteString)
-import qualified Data.ByteString.Char8 as B
-import Data.IORef
-import Data.List (unfoldr)
-import Data.Time.Clock (getCurrentTime, utctDayTime)
-import Network.Socket (ServiceName)
-import System.Environment (getArgs)
-import System.IO (hFlush, stdout)
-
-import ClientSim
-import Report
-
-import Crypto.Random (ChaChaDRG)
-import qualified Simplex.Messaging.Crypto as C
-import Simplex.Messaging.Server (runSMPServerBlocking)
-import Simplex.Messaging.Server.Env.STM as Env
-import Simplex.Messaging.Server.Expiration (ExpirationConfig (..))
-import Simplex.Messaging.Server.MsgStore.Postgres (PostgresMsgStore)
-import Simplex.Messaging.Server.QueueStore.Postgres.Config (PostgresStoreCfg (..))
-import Simplex.Messaging.Agent.Store.Postgres.Options (DBOpts (..))
-import Simplex.Messaging.Agent.Store.Shared (MigrationConfirmation (..))
-import Simplex.Messaging.Client.Agent (SMPClientAgentConfig (..), defaultSMPClientAgentConfig)
-import Simplex.Messaging.Transport
-import Simplex.Messaging.Transport.Server (ServerCredentials (..), mkTransportServerConfig)
-import Simplex.Messaging.Version
-import UnliftIO.Exception (bracket)
-
-import Control.Logger.Simple (logInfo, withGlobalLogging, LogConfig (..), setLogLevel, LogLevel (..))
-
-data BenchConfig = BenchConfig
-  { numClients :: Int,
-    sustainedMinutes :: Int,
-    pgConnStr :: ByteString,
-    serverPort :: ServiceName,
-    timeSeriesFile :: FilePath
-  }
-
-defaultBenchConfig :: BenchConfig
-defaultBenchConfig =
-  BenchConfig
-    { numClients = 5000,
-      sustainedMinutes = 5,
-      pgConnStr = "postgresql://smp@localhost:15432/smp_bench",
-      serverPort = "15001",
-      timeSeriesFile = "bench-timeseries.csv"
-    }
-
-parseArgs :: IO BenchConfig
-parseArgs = do
-  args <- getArgs
-  pure $ go args defaultBenchConfig
-  where
-    go [] c = c
-    go ("--clients" : n : rest) c = go rest c {numClients = read n}
-    go ("--minutes" : n : rest) c = go rest c {sustainedMinutes = read n}
-    go ("--pg" : s : rest) c = go rest c {pgConnStr = B.pack s}
-    go ("--port" : p : rest) c = go rest c {serverPort = p}
-    go ("--timeseries" : f : rest) c = go rest c {timeSeriesFile = f}
-    go (x : _) _ = error $ "Unknown argument: " <> x
-
-main :: IO ()
-main = withGlobalLogging LogConfig {lc_file = Nothing, lc_stderr = True} $ do
-  setLogLevel LogInfo
-  bc@BenchConfig {numClients, sustainedMinutes, serverPort, timeSeriesFile, pgConnStr} <- parseArgs
-  putStrLn $ "SMP Server Memory Benchmark"
-  putStrLn $ "  clients:  " <> show numClients
-  putStrLn $ "  sustain:  " <> show sustainedMinutes <> " min"
-  putStrLn $ "  pg:       " <> B.unpack pgConnStr
-  putStrLn $ "  port:     " <> serverPort
-  putStrLn ""
-
-  snapshotsRef <- newIORef []
-
-  let snap phase clients = do
-        s <- takeSnapshot phase clients
-        modifyIORef' snapshotsRef (s :)
-        putStrLn $ "  [" <> show phase <> "] live=" <> show (snapLive s `div` (1024 * 1024)) <> "MB large=" <> show (snapLarge s `div` (1024 * 1024)) <> "MB"
-        hFlush stdout
-
-  withBenchServer bc $ do
-    putStrLn "Phase 1: Baseline (no clients)"
-    snap "baseline" 0
-
-    putStrLn $ "Phase 2: Connecting " <> show numClients <> " TLS clients..."
-    handles <- connectN numClients "localhost" serverPort
-    putStrLn $ "  Connected " <> show (length handles) <> " clients"
-    snap "tls_connect" (length handles)
-
-    putStrLn "Phase 3: Creating queues (NEW + KEY)..."
-    simClients <- mapConcurrently createQueue handles
-    putStrLn $ "  Created " <> show (length simClients) <> " queues"
-    snap "queue_create" (length simClients)
-
-    putStrLn "Phase 4: Subscribing (SUB)..."
-    mapConcurrently_ subscribeQueue simClients
-    snap "subscribe" (length simClients)
-
-    -- Pair up clients: first half sends to second half
-    let halfN = length simClients `div` 2
-        senders = take halfN simClients
-        receivers = drop halfN simClients
-        pairs = zip senders receivers
-
-    putStrLn $ "Phase 5: Sending " <> show halfN <> " messages..."
-    g <- C.newRandom
-    forConcurrently_ pairs $ \(sender, receiver) -> do
-      (_, sKey) <- atomically $ C.generateAuthKeyPair C.SEd25519 g
-      sendMessage (scHandle sender) sKey (scSndId receiver) "benchmark test message payload 1234567890"
-    snap "msg_send" (length simClients)
-
-    putStrLn "Phase 6: Receiving and ACKing messages..."
-    forConcurrently_ receivers receiveAndAck
-    snap "msg_recv" (length simClients)
-
-    putStrLn $ "Phase 7: Sustained load (" <> show sustainedMinutes <> " min)..."
-    writeTimeSeriesHeader timeSeriesFile
-    -- Logger thread: snapshot every 10s
-    logger <- async $ forever $ do
-      threadDelay 10_000_000
-      s <- takeSnapshot "sustained" (length simClients)
-      appendTimeSeries timeSeriesFile s
-    -- Worker threads: continuous send/receive
-    let loopDurationUs = sustainedMinutes * 60 * 1_000_000
-    workersDone <- newTVarIO False
-    workers <- async $ do
-      deadline <- (+ loopDurationUs) <$> getMonotonicTimeUs
-      sustainedLoop g pairs deadline
-      atomically $ writeTVar workersDone True
-    -- Wait for workers
-    void $ atomically $ readTVar workersDone >>= \done -> when (not done) retry
-    cancel logger
-    cancel workers
-    snap "sustained_end" (length simClients)
-
-  snapshots <- reverse <$> readIORef snapshotsRef
-  printSummary snapshots
-  putStrLn $ "\nTime-series written to: " <> timeSeriesFile
-
-sustainedLoop :: TVar ChaChaDRG -> [(SimClient, SimClient)] -> Int -> IO ()
-sustainedLoop g pairs deadline = go
-  where
-    go = do
-      now <- getMonotonicTimeUs
-      when (now < deadline) $ do
-        forConcurrently_ pairs $ \(sender, receiver) -> do
-          (_, sKey) <- atomically $ C.generateAuthKeyPair C.SEd25519 g
-          sendMessage (scHandle sender) sKey (scSndId receiver) "sustained load message payload"
-        forConcurrently_ (map snd pairs) receiveAndAck
-        go
-
-getMonotonicTimeUs :: IO Int
-getMonotonicTimeUs = do
-  t <- getCurrentTime
-  pure $ round (utctDayTime t * 1_000_000)
-
-withBenchServer :: BenchConfig -> IO a -> IO a
-withBenchServer BenchConfig {pgConnStr, serverPort} action = do
-  started <- newEmptyTMVarIO
-  let srvCfg = benchServerConfig pgConnStr serverPort
-  bracket
-    (async $ runSMPServerBlocking started srvCfg Nothing)
-    cancel
-    (\_ -> waitForServer started >> action)
-  where
-    waitForServer started = do
-      r <- atomically $ takeTMVar started
-      if r
-        then putStrLn $ "Server started on port " <> serverPort
-        else error "Server failed to start"
-
-benchServerConfig :: ByteString -> ServiceName -> ServerConfig PostgresMsgStore
-benchServerConfig pgConn port =
-  let storeCfg = PostgresStoreCfg
-        { dbOpts = DBOpts {connstr = pgConn, schema = "smp_server", poolSize = 10, createSchema = True},
-          dbStoreLogPath = Nothing,
-          confirmMigrations = MCYesUp,
-          deletedTTL = 86400
-        }
-   in ServerConfig
-        { transports = [(port, transport @TLS, False)],
-          smpHandshakeTimeout = 120_000_000,
-          tbqSize = 128,
-          msgQueueQuota = 128,
-          maxJournalMsgCount = 256,
-          maxJournalStateLines = 16,
-          queueIdBytes = 24,
-          msgIdBytes = 24,
-          serverStoreCfg = SSCDatabase storeCfg,
-          storeNtfsFile = Nothing,
-          allowNewQueues = True,
-          newQueueBasicAuth = Nothing,
-          controlPortUserAuth = Nothing,
-          controlPortAdminAuth = Nothing,
-          dailyBlockQueueQuota = 20,
-          messageExpiration = Just defaultMessageExpiration,
-          expireMessagesOnStart = False,
-          expireMessagesOnSend = False,
-          idleQueueInterval = 14400,
-          notificationExpiration = defaultNtfExpiration,
-          inactiveClientExpiration = Nothing,
-          logStatsInterval = Nothing,
-          logStatsStartTime = 0,
-          serverStatsLogFile = "bench/tmp/stats.log",
-          serverStatsBackupFile = Nothing,
-          prometheusInterval = Nothing,
-          prometheusMetricsFile = "bench/tmp/metrics.txt",
-          pendingENDInterval = 500_000,
-          ntfDeliveryInterval = 200_000,
-          smpCredentials =
-            ServerCredentials
-              { caCertificateFile = Just "tests/fixtures/ca.crt",
-                privateKeyFile = "tests/fixtures/server.key",
-                certificateFile = "tests/fixtures/server.crt"
-              },
-          httpCredentials = Nothing,
-          smpServerVRange = supportedServerSMPRelayVRange,
-          Env.transportConfig = mkTransportServerConfig True (Just alpnSupportedSMPHandshakes) True,
-          controlPort = Nothing,
-          smpAgentCfg = defaultSMPClientAgentConfig {persistErrorInterval = 1},
-          allowSMPProxy = False,
-          serverClientConcurrency = 16,
-          information = Nothing,
-          startOptions = StartOptions {maintenance = False, compactLog = False, logLevel = LogInfo, skipWarnings = True, confirmMigrations = MCYesUp}
-        }
-

bench/Report.hs

@@ -1,113 +0,0 @@
-{-# LANGUAGE NamedFieldPuns #-}
-{-# LANGUAGE NumericUnderscores #-}
-{-# LANGUAGE OverloadedStrings #-}
-
-module Report
-  ( Snapshot (..),
-    takeSnapshot,
-    printSummary,
-    writeTimeSeriesHeader,
-    appendTimeSeries,
-  )
-where
-
-import Control.Concurrent (threadDelay)
-import Data.List (foldl')
-import Data.Text (Text)
-import qualified Data.Text as T
-import qualified Data.Text.IO as T
-import Data.Time.Clock (UTCTime, getCurrentTime)
-import Data.Time.Format.ISO8601 (iso8601Show)
-import Data.Word (Word32, Word64)
-import GHC.Stats (RTSStats (..), GCDetails (..), getRTSStats)
-import System.IO (Handle, IOMode (..), hFlush, hSetBuffering, BufferMode (..), withFile)
-import System.Mem (performMajorGC)
-
-data Snapshot = Snapshot
-  { snapTime :: UTCTime,
-    snapPhase :: Text,
-    snapLive :: Word64,
-    snapHeap :: Word64,
-    snapLarge :: Word64,
-    snapFrag :: Word64,
-    snapGCs :: Word32,
-    snapClients :: Int
-  }
-
-takeSnapshot :: Text -> Int -> IO Snapshot
-takeSnapshot phase clients = do
-  performMajorGC
-  threadDelay 1_000_000
-  rts <- getRTSStats
-  ts <- getCurrentTime
-  let GCDetails {gcdetails_live_bytes, gcdetails_mem_in_use_bytes, gcdetails_large_objects_bytes, gcdetails_block_fragmentation_bytes} = gc rts
-  pure
-    Snapshot
-      { snapTime = ts,
-        snapPhase = phase,
-        snapLive = gcdetails_live_bytes,
-        snapHeap = gcdetails_mem_in_use_bytes,
-        snapLarge = gcdetails_large_objects_bytes,
-        snapFrag = gcdetails_block_fragmentation_bytes,
-        snapGCs = gcs rts,
-        snapClients = clients
-      }
-
-printSummary :: [Snapshot] -> IO ()
-printSummary [] = putStrLn "No snapshots collected."
-printSummary snaps = do
-  putStrLn ""
-  putStrLn hdr
-  putStrLn $ replicate (length hdr) '-'
-  mapM_ printRow (zip (Snapshot {snapLive = 0, snapHeap = 0, snapLarge = 0, snapFrag = 0, snapGCs = 0, snapClients = 0, snapPhase = "", snapTime = snapTime (head snaps)} : snaps) snaps)
-  where
-    hdr = padR 20 "Phase" <> padL 12 "live_MB" <> padL 12 "large_MB" <> padL 12 "frag_MB" <> padL 12 "heap_MB" <> padL 10 "clients" <> padL 14 "d_live_MB" <> padL 14 "d_large_MB" <> padL 14 "KB/client"
-    printRow (prev, cur) =
-      putStrLn $
-        padR 20 (T.unpack $ snapPhase cur)
-          <> padL 12 (showMB $ snapLive cur)
-          <> padL 12 (showMB $ snapLarge cur)
-          <> padL 12 (showMB $ snapFrag cur)
-          <> padL 12 (showMB $ snapHeap cur)
-          <> padL 10 (show $ snapClients cur)
-          <> padL 14 (showDeltaMB (snapLive cur) (snapLive prev))
-          <> padL 14 (showDeltaMB (snapLarge cur) (snapLarge prev))
-          <> padL 14 (perClient cur)
-    showMB w = show (w `div` (1024 * 1024))
-    showDeltaMB a b
-      | a >= b = "+" <> show ((a - b) `div` (1024 * 1024))
-      | otherwise = "-" <> show ((b - a) `div` (1024 * 1024))
-    perClient Snapshot {snapClients, snapLive}
-      | snapClients > 0 = show (snapLive `div` fromIntegral snapClients `div` 1024)
-      | otherwise = "-"
-    padR n s = s <> replicate (max 0 (n - length s)) ' '
-    padL n s = replicate (max 0 (n - length s)) ' ' <> s
-
-csvHeader :: Text
-csvHeader = "timestamp,phase,rts_live,rts_heap,rts_large,rts_frag,rts_gc,clients"
-
-snapshotCsv :: Snapshot -> Text
-snapshotCsv Snapshot {snapTime, snapPhase, snapLive, snapHeap, snapLarge, snapFrag, snapGCs, snapClients} =
-  T.intercalate
-    ","
-    [ T.pack $ iso8601Show snapTime,
-      snapPhase,
-      tshow snapLive,
-      tshow snapHeap,
-      tshow snapLarge,
-      tshow snapFrag,
-      tshow snapGCs,
-      tshow snapClients
-    ]
-
-writeTimeSeriesHeader :: FilePath -> IO ()
-writeTimeSeriesHeader path = T.writeFile path (csvHeader <> "\n")
-
-appendTimeSeries :: FilePath -> Snapshot -> IO ()
-appendTimeSeries path snap =
-  withFile path AppendMode $ \h -> do
-    hSetBuffering h LineBuffering
-    T.hPutStrLn h $ snapshotCsv snap
-
-tshow :: Show a => a -> Text
-tshow = T.pack . show

bench/docker-compose.yml

@@ -1,46 +0,0 @@
-services:
-  postgres:
-    image: postgres:17
-    environment:
-      POSTGRES_USER: smp
-      POSTGRES_DB: smp_bench
-      POSTGRES_HOST_AUTH_METHOD: trust
-    volumes:
-      - ./init.sql:/docker-entrypoint-initdb.d/init.sql
-      - pgdata:/var/lib/postgresql/data
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U smp -d smp_bench"]
-      interval: 2s
-      timeout: 5s
-      retries: 10
-
-  bench:
-    build:
-      context: ..
-      dockerfile: bench/Dockerfile
-    depends_on:
-      postgres:
-        condition: service_healthy
-    environment:
-      BENCH_PG: "postgresql://smp@postgres/smp_bench"
-      BENCH_CLIENTS: "${BENCH_CLIENTS:-5000}"
-      BENCH_MINUTES: "${BENCH_MINUTES:-5}"
-    command:
-      - "--pg"
-      - "postgresql://smp@postgres/smp_bench"
-      - "--clients"
-      - "${BENCH_CLIENTS:-5000}"
-      - "--minutes"
-      - "${BENCH_MINUTES:-5}"
-      - "--timeseries"
-      - "/results/timeseries.csv"
-      - "+RTS"
-      - "-N"
-      - "-A16m"
-      - "-T"
-      - "-RTS"
-    volumes:
-      - ./results:/results
-
-volumes:
-  pgdata:

bench/init.sql

@@ -1,2 +0,0 @@
-CREATE EXTENSION IF NOT EXISTS pgcrypto;
-CREATE SCHEMA IF NOT EXISTS smp_server;

bench/run.sh

@@ -1,60 +0,0 @@
-#!/bin/bash
-set -e
-cd "$(dirname "$0")"
-
-mkdir -p results
-
-reset_db() {
-  docker compose down -v 2>/dev/null || true
-  docker compose up -d --wait postgres
-  echo "PostgreSQL ready."
-}
-
-if [ "$1" = "--compare-rts" ]; then
-  shift
-  docker compose build bench
-  for label_flags in \
-    "default:-N -A16m -T" \
-    "F1.2:-N -A16m -F1.2 -T" \
-    "F1.5:-N -A16m -F1.5 -T" \
-    "A4m:-N -A4m -T" \
-    "A4m-F1.2:-N -A4m -F1.2 -T" \
-    "compact:-N -A16m -c -T" \
-    "nonmoving:-N -A16m -xn -T"; do
-    label="${label_flags%%:*}"
-    flags="${label_flags#*:}"
-    echo ""
-    echo "=========================================="
-    echo "  RTS config: $label ($flags)"
-    echo "=========================================="
-    reset_db
-    docker compose run --rm \
-      -e BENCH_CLIENTS="${BENCH_CLIENTS:-1000}" \
-      -e BENCH_MINUTES="${BENCH_MINUTES:-2}" \
-      bench \
-      --pg "postgresql://smp@postgres/smp_bench" \
-      --clients "${BENCH_CLIENTS:-1000}" \
-      --minutes "${BENCH_MINUTES:-2}" \
-      --timeseries "/results/bench-${label}.csv" \
-      "$@" \
-      +RTS $flags -RTS
-  done
-  echo ""
-  echo "Done. Results in bench/results/"
-elif [ "$1" = "--local" ]; then
-  # Run natively (not in container) — requires local Postgres
-  shift
-  reset_db
-  cabal run smp-server-bench -f server_postgres -- \
-    --pg "postgresql://smp@localhost:15432/smp_bench" \
-    --clients "${BENCH_CLIENTS:-5000}" \
-    --minutes "${BENCH_MINUTES:-5}" \
-    "$@" \
-    +RTS -N -A16m -s -RTS
-else
-  # Run fully in containers
-  reset_db
-  docker compose run --rm bench "$@"
-fi
-
-docker compose down

cbits/getentropy_win.c

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: Apache-2.0
+// getentropy() shim for Windows, where it is absent from the CRT.
+// Follows the POSIX contract: fills `buffer` with `length` random bytes
+// (length must not exceed 256), returns 0 on success or -1 with errno set.
+#ifdef _WIN32
+#include <errno.h>
+#include <stddef.h>
+#include <windows.h>
+#include <bcrypt.h>
+
+int getentropy(void *buffer, size_t length) {
+    if (length > 256) {
+        errno = EIO;
+        return -1;
+    }
+    NTSTATUS status = BCryptGenRandom(NULL, (PUCHAR)buffer, (ULONG)length,
+                                      BCRYPT_USE_SYSTEM_PREFERRED_RNG);
+    if (!BCRYPT_SUCCESS(status)) {
+        errno = EIO;
+        return -1;
+    }
+    return 0;
+}
+#endif

docs/plans/memory-analysis-results.md

@@ -1,100 +0,0 @@
-## Memory Diagnostics Results
-
-### Data Collection
-
-Server: smp19.simplex.im, PostgreSQL backend, `useCache = False`
-RTS flags: `+RTS -N -A16m -I0.01 -Iw15 -s -RTS` (16 cores)
-
-### Mar 20 Data (1 hour, 07:19-08:19)
-
-```
-Time    rts_live  rts_heap  rts_large  rts_frag   clients  non-large
-07:19    7.5 GB    8.2 GB    5.5 GB    0.03 GB    14,000    2.0 GB
-07:24    6.4 GB   10.8 GB    5.2 GB    3.6 GB     14,806    1.2 GB
-07:29    8.2 GB   10.8 GB    6.5 GB    1.8 GB     15,667    1.7 GB
-07:34   10.0 GB   12.3 GB    7.9 GB    1.4 GB     15,845    2.1 GB
-07:39    6.7 GB   13.0 GB    5.3 GB    5.6 GB     16,589    1.4 GB
-07:44    8.5 GB   13.0 GB    6.7 GB    3.7 GB     16,283    1.8 GB
-07:49    6.5 GB   13.0 GB    5.2 GB    5.8 GB     16,532    1.3 GB
-07:54    6.0 GB   13.0 GB    4.8 GB    6.3 GB     16,636    1.2 GB
-07:59    6.4 GB   13.0 GB    5.1 GB    5.9 GB     16,769    1.3 GB
-08:04    8.3 GB   13.0 GB    6.5 GB    3.9 GB     17,352    1.8 GB
-08:09   10.2 GB   13.0 GB    8.0 GB    1.9 GB     17,053    2.2 GB
-08:14    5.6 GB   13.0 GB    4.5 GB    6.8 GB     17,147    1.1 GB
-08:19    7.6 GB   13.0 GB    6.1 GB    4.6 GB     17,496    1.5 GB
-```
-
-non-large = rts_live - rts_large (normal Haskell heap objects: Maps, TVars, closures)
-
-### Mar 19 Data (5.5 hours, 07:49-13:19)
-
-rts_heap grew from 10.1 GB to 20.7 GB over 5.5 hours.
-Post-GC rts_live floor rose from 5.5 GB to 9.1 GB.
-
-### Findings
-
-**1. Large/pinned objects dominate live data (60-80%)**
-
-`rts_large` = 4.5-8.0 GB out of 5.6-10.2 GB live. These are allocations > ~3KB that go on GHC's large object heap. They oscillate (not growing monotonically), meaning they are being allocated and freed constantly — transient, not leaked.
-
-**2. Fragmentation is the heap growth mechanism**
-
-`rts_heap ≈ rts_live + rts_frag`. The heap grows because pinned/large objects fragment GHC's block allocator. Once GHC expands the heap, it never shrinks. Growth pattern:
-- Large objects allocated → occupy blocks
-- Large objects freed → blocks can't be reused if ANY other object shares the block
-- New allocations need fresh blocks → heap expands
-- Heap never returns memory to OS
-
-**3. Non-large heap data is stable (~1.0-2.2 GB)**
-
-Normal Haskell objects (Maps, TVars, closures, client structures) account for only 1-2 GB. This scales with client count at ~100-130 KB/client and does NOT grow over time.
-
-**4. All tracked data structures are NOT the cause**
-
-- `clientSndQ=0, clientMsgQ=0` — TBQueues empty, no message accumulation
-- `smpQSubs` oscillates ~1.0-1.4M — entries are cleaned up, not leaking
-- `ntfStore` < 2K entries — negligible
-- All proxy agent maps near 0
-- `loadedQ=0` — useCache=False confirmed working
-
-**5. Source of large objects is unclear without heap profiling**
-
-The 4.5-8.0 GB of large objects could come from:
-- PostgreSQL driver (`postgresql-simple`/`libpq`) — pinned ByteStrings for query results
-- TLS library (`tls`) — pinned buffers per connection
-- Network socket I/O — pinned ByteStrings for recv/send
-- SMP protocol message blocks
-
-Cannot distinguish between these without `-hT` heap profiling (which is too expensive for this server).
-
-### Root Cause
-
-**GHC heap fragmentation from constant churn of large/pinned ByteString allocations.**
-
-Not a data structure leak. The live data itself is reasonable (5-10 GB for 15-17K clients). The problem is that GHC's copying GC cannot compact around pinned objects, so the heap grows with fragmentation and never shrinks.
-
-### Mitigation Options
-
-All are RTS flag changes — no rebuild needed, reversible by restart.
-
-**1. `-F1.2`** (reduce GC trigger factor from default 2.0)
-- Triggers major GC when heap reaches 1.2x live data instead of 2x
-- Reclaims fragmented blocks sooner
-- Trade-off: more frequent GC, slightly higher CPU
-- Risk: low — just makes GC run more often
-
-**2. Reduce `-A16m` to `-A4m`** (smaller nursery)
-- More frequent minor GC → short-lived pinned objects freed faster
-- Trade-off: more GC cycles, but each is smaller
-- Risk: low — may actually improve latency by reducing GC pause times
-
-**3. `+RTS -xn`** (nonmoving GC)
-- Designed for pinned-heavy workloads — avoids copying entirely
-- Available since GHC 8.10, improved in 9.x
-- Trade-off: different GC characteristics, less battle-tested
-- Risk: medium — different GC algorithm, should test first
-
-**4. Limit concurrent connections** (application-level)
-- Since large objects scale per-client, fewer clients = less fragmentation
-- Trade-off: reduced capacity
-- Risk: low but impacts users

docs/plans/memory-analysis.md

@@ -1,225 +0,0 @@
-## Root Cause Analysis: SMP Server Memory Growth (23.5GB)
-
-### Environment
-
-- **Server**: smp19.simplex.im, ~21,927 connected clients
-- **Storage**: PostgreSQL backend with `useCache = False`
-- **RTS flags**: `+RTS -N -A16m -I0.01 -Iw15 -s -RTS` (16 cores)
-- **Memory**: 23.5GB RES / 1031GB VIRT (75% of available RAM)
-
-### Log Summary
-
-- **Duration**: ~22 hours (Mar 16 12:12 → Mar 17 10:20)
-- **92,277 proxy connection errors** out of 92,656 total log lines (99.6%)
-- **292 unique failing destination servers**, top offender: `nowhere.moe` (12,875 errors)
-- Only **145 successful proxy connections**
-
----
-
-### Known Factor: GHC Heap Sizing
-
-With 16 cores and `-A16m`:
-- **Nursery**: 16 × 16MB = **256MB baseline**
-- GHC default major GC threshold = **2× live data** — if live data is 10GB, heap grows to ~20GB before major GC
-- The server is rarely idle with 22K clients, so major GC is deferred despite `-I0.01`
-- This is an amplifier — whatever the actual live data size is, GHC roughly doubles it
-
----
-
-### Candidate Structures That Could Grow Unboundedly
-
-Analysis of the full codebase identified these structures that either grow without bound or have uncertain cleanup:
-
-#### 1. `SubscribedClients` maps — `Env/STM.hs:378`
-
-Both `subscribers.queueSubscribers` and `ntfSubscribers.queueSubscribers` (and their `serviceSubscribers`) use `SubscribedClients (TMap EntityId (TVar (Maybe (Client s))))`.
-
-Comment at line 376: *"The subscriptions that were made at any point are not removed"*
-
-`deleteSubcribedClient` IS called on disconnect (Server.hs:1112) and DOES call `TM.delete`. But it only deletes if the current stored client matches — if another client already re-subscribed, the old client's disconnect won't remove the entry. This is by design for mobile client continuity, but the net effect on map size over time is unclear without measurement.
-
-#### 2. ProxyAgent's subscription TMaps — `Client/Agent.hs:145-151`
-
-The `SMPClientAgent` has 4 TMaps that accumulate one top-level entry per unique destination server and **never remove** them:
-
-- `activeServiceSubs :: TMap SMPServer (TVar ...)` (line 145)
-- `activeQueueSubs :: TMap SMPServer (TMap QueueId ...)` (line 146)
-- `pendingServiceSubs :: TMap SMPServer (TVar ...)` (line 149)
-- `pendingQueueSubs :: TMap SMPServer (TMap QueueId ...)` (line 150)
-
-Comment at line 262: *"these vars are never removed, they are only added"*
-
-These are only used for the proxy agent (SParty 'Sender), so they grow with each unique destination SMP server proxied to. With 292 unique servers in this log period, these are likely small — but long-running servers may accumulate thousands.
-
-`closeSMPClientAgent` (line 369) does NOT clear these 4 maps.
-
-#### 3. `NtfStore` — `NtfStore.hs:26`
-
-`NtfStore (TMap NotifierId (TVar [MsgNtf]))` — one entry per NotifierId.
-
-`deleteExpiredNtfs` (line 47) filters expired notifications from lists but does **not remove entries with empty lists** from the TMap. Over time, NotifierIds that no longer receive notifications leave zombie `TVar []` entries.
-
-`deleteNtfs` (line 44) does remove the full entry via `TM.lookupDelete` — but only called when a notifier is explicitly deleted.
-
-#### 4. `serviceLocks` in PostgresQueueStore — `Postgres.hs:112,469`
-
-`serviceLocks :: TMap CertFingerprint Lock` — one Lock per unique certificate fingerprint.
-
-`getCreateService` (line 469) calls `withLockMap (serviceLocks st) fp` which calls `getMapLock` (Agent/Client.hs:1029-1032) — this **unconditionally inserts** a Lock into the TMap. There is **no cleanup code** for serviceLocks anywhere. This is NOT guarded by `useCache`.
-
-#### 5. `sentCommands` per proxy client connection — `Client.hs:580`
-
-Each `PClient` has `sentCommands :: TMap CorrId (Request err msg)`. Entries are added per command sent (line 1369) and only removed when a response arrives (line 698). If a connection drops before all responses arrive, entries remain until the `PClient` is GC'd. Since `PClient` is captured by the connection thread which terminates on error, the `PClient` should become GC-eligible — but GC timing depends on heap pressure.
-
-#### 6. `subQ :: TQueue (ClientSub, ClientId)` — `Env/STM.hs:363`
-
-Unbounded `TQueue` for subscription changes. If the subscriber thread (`serverThread`) can't process changes fast enough, this queue grows without backpressure. With 22K clients subscribing/unsubscribing, sustained bursts could cause this queue to bloat.
-
----
-
-### Ruled Out
-
-1. **PostgreSQL queue cache**: `useCache = False` — `queues`, `senders`, `links`, `notifiers` TMaps are empty.
-2. **`notifierLocks`**: Guarded by `useCache` (Postgres.hs:377,405) — not used with `useCache = False`.
-3. **Client structures**: 22K × ~3KB = ~66MB — negligible.
-4. **TBQueues**: Bounded (`tbqSize = 128`).
-5. **Thread management**: `forkClient` uses weak refs + `finally` blocks. `endThreads` cleared on disconnect.
-6. **Proxy `smpClients`/`smpSessions`**: Properly cleaned on disconnect/expiry.
-7. **`smpSubWorkers`**: Properly cleaned on worker completion; also cleared in `closeSMPClientAgent`.
-8. **`pendingEvents`**: Atomically swapped empty every `pendingENDInterval`.
-9. **Stats IORef counters**: Fixed number, bounded.
-10. **DB connection pool**: Bounded `TBQueue` with bracket-based return.
-
----
-
-### Insufficient Data to Determine Root Cause
-
-Without measuring the actual sizes of these structures at runtime, we cannot determine which (if any) is the primary contributor. The following exact logging changes will identify the root cause.
-
----
-
-### EXACT LOGS TO ADD
-
-Add a new periodic logging thread in `src/Simplex/Messaging/Server.hs`.
-
-Insert at `Server.hs:197` (after `prometheusMetricsThread_`):
-
-```haskell
-        <> memoryDiagThread_ cfg
-```
-
-Then define:
-
-```haskell
-    memoryDiagThread_ :: ServerConfig s -> [M s ()]
-    memoryDiagThread_ ServerConfig {prometheusInterval = Just _} =
-      [memoryDiagThread]
-    memoryDiagThread_ _ = []
-
-    memoryDiagThread :: M s ()
-    memoryDiagThread = do
-      labelMyThread "memoryDiag"
-      Env { ntfStore = NtfStore ntfMap
-          , server = srv@Server {subscribers, ntfSubscribers}
-          , proxyAgent = ProxyAgent {smpAgent = pa}
-          , msgStore_ = ms
-          } <- ask
-      let interval = 300_000_000 -- 5 minutes
-      liftIO $ forever $ do
-        threadDelay interval
-        -- GHC RTS stats
-        rts <- getRTSStats
-        let liveBytes = gcdetails_live_bytes $ gc rts
-            heapSize = gcdetails_mem_in_use_bytes $ gc rts
-            gcCount = gcs rts
-        -- Server structures
-        clientCount <- IM.size <$> getServerClients srv
-        -- SubscribedClients (queue and service subscribers for both SMP and NTF)
-        smpQSubs <- M.size <$> getSubscribedClients (queueSubscribers subscribers)
-        smpSSubs <- M.size <$> getSubscribedClients (serviceSubscribers subscribers)
-        ntfQSubs <- M.size <$> getSubscribedClients (queueSubscribers ntfSubscribers)
-        ntfSSubs <- M.size <$> getSubscribedClients (serviceSubscribers ntfSubscribers)
-        -- Pending events
-        smpPending <- IM.size <$> readTVarIO (pendingEvents subscribers)
-        ntfPending <- IM.size <$> readTVarIO (pendingEvents ntfSubscribers)
-        -- NtfStore
-        ntfStoreSize <- M.size <$> readTVarIO ntfMap
-        -- ProxyAgent maps
-        let SMPClientAgent {smpClients, smpSessions, activeServiceSubs, activeQueueSubs, pendingServiceSubs, pendingQueueSubs, smpSubWorkers} = pa
-        paClients <- M.size <$> readTVarIO smpClients
-        paSessions <- M.size <$> readTVarIO smpSessions
-        paActSvc <- M.size <$> readTVarIO activeServiceSubs
-        paActQ <- M.size <$> readTVarIO activeQueueSubs
-        paPndSvc <- M.size <$> readTVarIO pendingServiceSubs
-        paPndQ <- M.size <$> readTVarIO pendingQueueSubs
-        paWorkers <- M.size <$> readTVarIO smpSubWorkers
-        -- Loaded queue counts
-        lc <- loadedQueueCounts $ fromMsgStore ms
-        -- Log everything
-        logInfo $
-          "MEMORY "
-            <> "rts_live=" <> tshow liveBytes
-            <> " rts_heap=" <> tshow heapSize
-            <> " rts_gc=" <> tshow gcCount
-            <> " clients=" <> tshow clientCount
-            <> " smpQSubs=" <> tshow smpQSubs
-            <> " smpSSubs=" <> tshow smpSSubs
-            <> " ntfQSubs=" <> tshow ntfQSubs
-            <> " ntfSSubs=" <> tshow ntfSSubs
-            <> " smpPending=" <> tshow smpPending
-            <> " ntfPending=" <> tshow ntfPending
-            <> " ntfStore=" <> tshow ntfStoreSize
-            <> " paClients=" <> tshow paClients
-            <> " paSessions=" <> tshow paSessions
-            <> " paActSvc=" <> tshow paActSvc
-            <> " paActQ=" <> tshow paActQ
-            <> " paPndSvc=" <> tshow paPndSvc
-            <> " paPndQ=" <> tshow paPndQ
-            <> " paWorkers=" <> tshow paWorkers
-            <> " loadedQ=" <> tshow (loadedQueueCount lc)
-            <> " loadedNtf=" <> tshow (loadedNotifierCount lc)
-            <> " ntfLocks=" <> tshow (notifierLockCount lc)
-```
-
-Note: `smpSubs.subsCount` (queueSubscribers size) and `smpSubs.subServicesCount` (serviceSubscribers size) are **already logged** in Prometheus (lines 475-496). The log above adds all other candidate structures plus GHC RTS memory stats.
-
-This produces a single log line every 5 minutes:
-
-```
-[INFO] MEMORY rts_live=10737418240 rts_heap=23488102400 rts_gc=4521 clients=21927 smpQSubs=1847233 smpSSubs=42 ntfQSubs=982112 ntfSSubs=31 smpPending=0 ntfPending=0 ntfStore=512844 paClients=12 paSessions=12 paActSvc=0 paActQ=0 paPndSvc=0 paPndQ=0 paWorkers=3 loadedQ=0 loadedNtf=0 ntfLocks=0
-```
-
-### What Each Metric Tells Us
-
-| Metric | What it reveals | If growing = suspect |
-|--------|----------------|---------------------|
-| `rts_live` | Actual live data after last major GC | Baseline — everything else should add up to this |
-| `rts_heap` | Total heap (should be ~2× rts_live) | If >> 2× live, fragmentation issue |
-| `clients` | Connected client count | Known: ~22K |
-| `smpQSubs` | SubscribedClients map size (queue subs) | If >> clients × avg_subs, entries not cleaned |
-| `smpSSubs` | SubscribedClients map size (service subs) | Should be small |
-| `ntfQSubs` | NTF SubscribedClients map (queue subs) | Same concern as smpQSubs |
-| `ntfSSubs` | NTF SubscribedClients map (service subs) | Should be small |
-| `smpPending` / `ntfPending` | Pending END/DELD events per client | If large, subscriber thread lagging |
-| `ntfStore` | NotifierId count in NtfStore | If growing monotonically, zombie entries |
-| `paClients` | Proxy connections to other servers | Should be <= unique dest servers |
-| `paSessions` | Active proxy sessions | Should match paClients |
-| `paActSvc` / `paActQ` | Proxy active subscriptions | If growing, entries never removed |
-| `paPndSvc` / `paPndQ` | Proxy pending subscriptions | If growing, resubscription stuck |
-| `paWorkers` | Active reconnect workers | If growing, workers stuck in retry |
-| `loadedQ` | Cached queues in store (0 with useCache=False) | Should be 0 |
-| `ntfLocks` | Notifier locks in store | Should be 0 with useCache=False |
-
-### Interpretation Guide
-
-**If `smpQSubs` is in the millions**: SubscribedClients is the primary leak. Entries accumulate for every queue ever subscribed to.
-
-**If `ntfStore` grows monotonically**: Zombie notification entries (empty lists after expiration). Fix: `deleteExpiredNtfs` should remove entries with empty lists.
-
-**If `paActSvc` + `paActQ` grow**: Proxy agent subscription maps are the leak. Fix: add cleanup when no active/pending subs exist for a server.
-
-**If `rts_live` is much smaller than `rts_heap`**: GHC heap fragmentation. Fix: tune `-F` flag (GC trigger factor) or use `-c` (compacting GC).
-
-**If `rts_live` ~ 10-12GB**: The live data is genuinely large. Look at which metric is the largest contributor.
-
-**If nothing above is large but `rts_live` is large**: The leak is in a structure not measured here — likely TLS connection buffers, ByteString retention from Postgres queries, or GHC runtime overhead. Next step would be heap profiling with `-hT`.

plans/2026-03-25-xftp-postgres-backend-design.md

@@ -0,0 +1,472 @@
+# XFTP Server PostgreSQL Backend
+
+## Overview
+
+Add PostgreSQL backend support to xftp-server, following the SMP server pattern. Supports bidirectional migration between STM (in-memory with StoreLog) and PostgreSQL backends.
+
+## Goals
+
+- PostgreSQL-backed file metadata storage as an alternative to STM + StoreLog
+- Polymorphic server code via `FileStoreClass` typeclass with IO-based methods (following `QueueStoreClass` pattern)
+- Bidirectional migration: StoreLog <-> PostgreSQL via CLI commands
+- Shared `server_postgres` cabal flag (same flag enables both SMP and XFTP Postgres support)
+- INI-based backend selection at runtime
+
+## Architecture
+
+### FileStoreClass Typeclass
+
+IO-based typeclass following the `QueueStoreClass` pattern — each method is a self-contained IO action, with the implementation responsible for its own atomicity (STM backend wraps in `atomically`, Postgres backend uses database transactions):
+
+```haskell
+class FileStoreClass s where
+  type FileStoreConfig s
+
+  -- Lifecycle
+  newFileStore :: FileStoreConfig s -> IO s
+  closeFileStore :: s -> IO ()
+
+  -- File operations
+  addFile :: s -> SenderId -> FileInfo -> RoundedFileTime -> ServerEntityStatus -> IO (Either XFTPErrorType ())
+  setFilePath :: s -> SenderId -> FilePath -> IO (Either XFTPErrorType ())
+  addRecipient :: s -> SenderId -> FileRecipient -> IO (Either XFTPErrorType ())
+  getFile :: s -> SFileParty p -> XFTPFileId -> IO (Either XFTPErrorType (FileRec, C.APublicAuthKey))
+  deleteFile :: s -> SenderId -> IO (Either XFTPErrorType ())
+  blockFile :: s -> SenderId -> BlockingInfo -> Bool -> IO (Either XFTPErrorType ())
+  deleteRecipient :: s -> RecipientId -> FileRec -> IO ()
+  ackFile :: s -> RecipientId -> IO (Either XFTPErrorType ())
+
+  -- Expiration (with LIMIT for Postgres; called in a loop until empty)
+  expiredFiles :: s -> Int64 -> Int -> IO [(SenderId, Maybe FilePath, Word32)]
+
+  -- Storage and stats (for init-time computation)
+  getUsedStorage :: s -> IO Int64
+  getFileCount :: s -> IO Int
+```
+
+- STM backend: each method wraps its STM transaction in `atomically` internally.
+- Postgres backend: each method runs its query via `withDB` / database connection internally.
+
+No polymorphic monad or `runStore` dispatcher needed — unlike `MsgStoreClass`, XFTP file operations are individually atomic and don't require grouping multiple operations into backend-dependent transactions.
+
+### PostgresFileStore Data Type
+
+```haskell
+data PostgresFileStore = PostgresFileStore
+  { dbStore :: DBStore,
+    dbStoreLog :: Maybe (StoreLog 'WriteMode)
+  }
+```
+
+- `dbStore` — connection pool created via `createDBStore`, runs schema migrations on init.
+- `dbStoreLog` — optional parallel log file (enabled by `db_store_log` INI setting). When present, every mutation (`addFile`, `setFilePath`, `deleteFile`, `blockFile`, `addRecipient`, `ackFile`) also writes to this log via a `withLog` wrapper. `withLog` is called AFTER the DB operation succeeds (so the log reflects committed state only). Log write failures are non-fatal (logged as warnings, do not fail the DB operation). This provides an audit trail and enables recovery via export.
+
+`closeFileStore` for Postgres calls `closeDBStore` (closes connection pool) then `mapM_ closeStoreLog dbStoreLog` (flushes and closes the parallel log). For STM, it closes the storeLog. Called from a `finally` block during server shutdown, matching SMP's `stopServer` → `closeMsgStore` → `closeQueueStore` pattern.
+
+### STMFileStore Type
+
+After extracting from current `Store.hs`, `STMFileStore` retains the file and recipient maps but no longer owns `usedStorage` (moved to `XFTPEnv`):
+
+```haskell
+data STMFileStore = STMFileStore
+  { files :: TMap SenderId FileRec,
+    recipients :: TMap RecipientId (SenderId, RcvPublicAuthKey)
+  }
+```
+
+`closeFileStore` for STM is a no-op (TMaps are garbage-collected; the env-level `storeLog` is closed separately by the server).
+
+### Error Handling
+
+Postgres operations follow SMP's `withDB` / `handleDuplicate` pattern:
+
+```haskell
+withDB :: Text -> PostgresFileStore -> (DB.Connection -> IO (Either XFTPErrorType a)) -> ExceptT XFTPErrorType IO a
+withDB op st action =
+  ExceptT $ E.try (withTransaction (dbStore st) action) >>= either logErr pure
+  where
+    logErr :: E.SomeException -> IO (Either XFTPErrorType a)
+    logErr e = logError ("STORE: " <> err) $> Left INTERNAL
+      where
+        err = op <> ", withDB, " <> tshow e
+
+handleDuplicate :: SqlError -> IO (Either XFTPErrorType a)
+handleDuplicate e = case constraintViolation e of
+  Just (UniqueViolation _) -> pure $ Left DUPLICATE_
+  _ -> E.throwIO e
+```
+
+- All DB operations wrapped in `withDB` — catches exceptions, logs, returns `INTERNAL`.
+- Unique constraint violations caught by `handleDuplicate` and mapped to `DUPLICATE_`.
+- UPDATE operations verified with `assertUpdated` — returns `AUTH` if 0 rows affected (matching SMP pattern, prevents silent failures when WHERE clause doesn't match).
+- Critical sections (DB write + TVar update) wrapped in `uninterruptibleMask_` to prevent async exceptions from leaving inconsistent state between DB and TVars.
+
+### FileRec and TVar Fields
+
+`FileRec` retains its `TVar` fields (matching SMP's `PostgresQueue` pattern):
+
+```haskell
+data FileRec = FileRec
+  { senderId :: SenderId,
+    fileInfo :: FileInfo,
+    filePath :: TVar (Maybe FilePath),
+    recipientIds :: TVar (Set RecipientId),
+    createdAt :: RoundedFileTime,
+    fileStatus :: TVar ServerEntityStatus
+  }
+```
+
+- **STM backend**: TVars are the source of truth, as currently.
+- **Postgres backend**: `getFile` reads from DB and creates a `FileRec` with fresh TVars populated from the DB row (matching SMP's `mkQ` pattern — `newTVarIO` per load). Mutation methods (`setFilePath`, `blockFile`, etc.) update both the DB (persistence) and the TVars (in-session consistency). The `recipientIds` TVar is initialized to `S.empty` — no subquery needed because no server code reads `recipientIds` directly; all recipient operations go through the typeclass methods (`addRecipient`, `deleteRecipient`, `ackFile`), which query the `recipients` table for Postgres.
+
+### usedStorage Ownership
+
+`usedStorage :: TVar Int64` moves from the store to `XFTPEnv`. The store typeclass does **not** manage `usedStorage` — it only provides `getUsedStorage` for init-time computation.
+
+- **STM init**: StoreLog replay calls `setFilePath` (which only sets the filePath TVar — the STM `setFilePath` implementation is changed to **not** update `usedStorage`). Similarly, STM `deleteFile` (Store.hs line 117) and `blockFile` (line 125) are changed to **not** update `usedStorage` — the server handles all `usedStorage` adjustments externally. After replay, `getUsedStorage` computes the sum over all file sizes (matching current `countUsedStorage` behavior).
+- **Postgres init**: `getUsedStorage` executes `SELECT COALESCE(SUM(file_size), 0) FROM files`.
+- **Runtime**: Server manages `usedStorage` TVar directly for reserve/commit/rollback during uploads, and adjusts after `deleteFile`/`blockFile` calls.
+
+**Note on `getUsedStorage` semantics**: The current STM `countUsedStorage` sums all file sizes unconditionally (including files without `filePath` set, i.e., created but not yet uploaded). The Postgres `getUsedStorage` matches this: `SELECT SUM(file_size) FROM files` (no `WHERE file_path IS NOT NULL`). In practice, orphaned files (created but never uploaded) are rare and short-lived (expired within 48h), so the difference is negligible. A future improvement could filter by `file_path IS NOT NULL` in both backends to reflect actual disk usage more accurately.
+
+### Server.hs Refactoring
+
+`Server.hs` becomes polymorphic over `FileStoreClass s`. Since all typeclass methods are IO, call sites replace `atomically` with direct IO calls to the store.
+
+**Call sites requiring changes** (exhaustive list):
+
+1. **`receiveServerFile`** (line 563): `atomically $ writeTVar filePath (Just fPath)` → `setFilePath store senderId fPath`. The `reserve` logic (line 551-555) stays as direct TVar manipulation on `usedStorage` from `XFTPEnv`.
+
+2. **`verifyXFTPTransmission`** (line 453): `atomically $ verify =<< getFile st party fId` — the `getFile` call and subsequent `readTVar fileStatus` are in a single `atomically` block. Refactored to: `getFile st party fId` (IO), then `readTVarIO (fileStatus fr)` from the returned `FileRec` (safe for both backends — STM TVar is the source of truth, Postgres TVar is a fresh snapshot from DB).
+
+3. **`retryAdd`** (line 516): Signature `XFTPFileId -> STM (Either XFTPErrorType a)` → `XFTPFileId -> IO (Either XFTPErrorType a)`. The `atomically` call (line 520) replaced with `liftIO`.
+
+4. **`deleteOrBlockServerFile_`** (line 620): Parameter `FileStore -> STM (Either XFTPErrorType ())` → `FileStoreClass s => s -> IO (Either XFTPErrorType ())`. The `atomically` call (line 626) removed — the store method is already IO. After the store action, server adjusts `usedStorage` TVar in `XFTPEnv` based on `fileInfo.size`.
+
+5. **`ackFileReception`** (line 605): `atomically $ deleteRecipient st rId fr` → `deleteRecipient st rId fr`.
+
+6. **Control port `CPDelete`/`CPBlock`** (lines 371, 377): `atomically $ getFile fs SFRecipient fileId` → `getFile fs SFRecipient fileId`.
+
+7. **`expireServerFiles`** (line 636): Replace per-file `expiredFilePath` iteration with batched `expiredFiles st old batchSize`, which returns `[(SenderId, Maybe FilePath, Word32)]` — the `Word32` file size is needed so the server can adjust the `usedStorage` TVar after each deletion. Called in a loop until the returned list is empty. The `itemDelay` between files applies to the deletion loop over each batch, not the query itself. STM backend ignores the batch size limit (returns all expired files from TMap scan); Postgres uses `LIMIT`.
+
+8. **`restoreServerStats`** (line 694): `FileStore {files, usedStorage} <- asks store` accesses store fields directly. Refactored to: `usedStorage` from `XFTPEnv` via `asks usedStorage`, file count via `getFileCount store`. STM: `M.size <$> readTVarIO files`. Postgres: `SELECT COUNT(*) FROM files`.
+
+### Store Config Selection
+
+GADT in `Env.hs`:
+
+```haskell
+data XFTPStoreConfig s where
+  XSCMemory :: Maybe FilePath -> XFTPStoreConfig STMFileStore
+#if defined(dbServerPostgres)
+  XSCDatabase :: PostgresFileStoreCfg -> XFTPStoreConfig PostgresFileStore
+#endif
+```
+
+`XFTPEnv` becomes polymorphic:
+
+```haskell
+data XFTPEnv s = XFTPEnv
+  { config :: XFTPServerConfig,
+    store :: s,
+    usedStorage :: TVar Int64,
+    storeLog :: Maybe (StoreLog 'WriteMode),
+    ...
+  }
+```
+
+The `M` monad (`ReaderT (XFTPEnv s) IO`) and all functions in `Server.hs` gain `FileStoreClass s =>` constraints.
+
+**StoreLog lifecycle per backend:**
+
+- **STM mode**: `storeLog = Just sl` (current behavior — append-only log for persistence and recovery).
+- **Postgres mode**: `storeLog = Nothing` (main storeLog disabled — Postgres is the source of truth). The optional parallel `dbStoreLog` inside `PostgresFileStore` provides audit/recovery if enabled via `db_store_log` INI setting.
+
+The existing `withFileLog` pattern in Server.hs continues to work unchanged — it maps over `Maybe (StoreLog 'WriteMode)`, which is `Nothing` in Postgres mode so the calls become no-ops.
+
+### Main.hs Store Type Dispatch
+
+The `Start` CLI command gains a `--confirm-migrations` flag (default `MCConsole` — manual prompt, matching SMP's `StartOptions`). For automated deployments, `--confirm-migrations up` auto-applies forward migrations. The import command uses `MCYesUp` (always auto-apply).
+
+Following SMP's existential dispatch pattern (`AStoreType` + `run`), `Main.hs` selects the store type from INI config and dispatches to the polymorphic server:
+
+```haskell
+runServer ini = do
+  let storeType = fromRight "memory" $ lookupValue "STORE_LOG" "store_files" ini
+  case storeType of
+    "memory" -> run $ XSCMemory (enableStoreLog $> storeLogFilePath)
+    "database" ->
+#if defined(dbServerPostgres)
+      run $ XSCDatabase PostgresFileStoreCfg {..}
+#else
+      exitError "server not compiled with Postgres support"
+#endif
+    _ -> exitError $ "Invalid store_files value: " <> storeType
+  where
+    run :: FileStoreClass s => XFTPStoreConfig s -> IO ()
+    run storeCfg = do
+      env <- newXFTPServerEnv storeCfg config
+      runReaderT (xftpServer config) env
+```
+
+**`newXFTPServerEnv` refactored signature:**
+
+```haskell
+newXFTPServerEnv :: FileStoreClass s => XFTPStoreConfig s -> XFTPServerConfig -> IO (XFTPEnv s)
+newXFTPServerEnv storeCfg config = do
+  (store, storeLog) <- case storeCfg of
+    XSCMemory storeLogPath -> do
+      st <- newFileStore ()
+      sl <- mapM (`readWriteFileStore` st) storeLogPath
+      pure (st, sl)
+    XSCDatabase dbCfg -> do
+      st <- newFileStore dbCfg
+      pure (st, Nothing)  -- main storeLog disabled for Postgres
+  usedStorage <- newTVarIO =<< getUsedStorage store
+  ...
+  pure XFTPEnv {config, store, usedStorage, storeLog, ...}
+```
+
+### Startup Config Validation
+
+Following SMP's `checkMsgStoreMode` pattern, `Main.hs` validates config before starting:
+
+- **`store_files=database` + StoreLog file exists** (without `db_store_log=on`): Error — "StoreLog file present but store_files is `database`. Use `xftp-server database import` to migrate, or set `db_store_log: on`."
+- **`store_files=database` + schema doesn't exist**: Error — "Create schema in PostgreSQL or use `xftp-server database import`."
+- **`store_files=memory` + Postgres schema exists**: Warning — "Postgres schema exists but store_files is `memory`. Data in Postgres will not be used."
+- **Binary compiled without `server_postgres` + `store_files=database`**: Error — "Server not compiled with Postgres support."
+
+## Module Structure
+
+```
+src/Simplex/FileTransfer/Server/
+  Store.hs                    -- FileStoreClass typeclass + shared types (FileRec, FileRecipient, etc.)
+  Store/
+    STM.hs                    -- STMFileStore (extracted from current Store.hs)
+    Postgres.hs               -- PostgresFileStore                [CPP-guarded]
+    Postgres/
+      Migrations.hs           -- Schema migrations                [CPP-guarded]
+      Config.hs               -- PostgresFileStoreCfg             [CPP-guarded]
+  StoreLog.hs                 -- Unchanged (interchange format for both backends + migration)
+  Env.hs                      -- XFTPStoreConfig GADT, polymorphic XFTPEnv
+  Main.hs                     -- Store selection, migration CLI commands
+  Server.hs                   -- Polymorphic over FileStoreClass
+```
+
+## PostgreSQL Schema
+
+Initial migration (`20260325_initial`):
+
+```sql
+CREATE TABLE files (
+  sender_id BYTEA NOT NULL PRIMARY KEY,
+  file_size INT4 NOT NULL,
+  file_digest BYTEA NOT NULL,
+  sender_key BYTEA NOT NULL,
+  file_path TEXT,
+  created_at INT8 NOT NULL,
+  status TEXT NOT NULL DEFAULT 'active'
+);
+
+CREATE TABLE recipients (
+  recipient_id BYTEA NOT NULL PRIMARY KEY,
+  sender_id BYTEA NOT NULL REFERENCES files ON DELETE CASCADE,
+  recipient_key BYTEA NOT NULL
+);
+
+CREATE INDEX idx_recipients_sender_id ON recipients (sender_id);
+CREATE INDEX idx_files_created_at ON files (created_at);
+```
+
+- `file_size` is `INT4` matching `Word32` in `FileInfo.size`
+- `sender_key` and `recipient_key` stored as `BYTEA` using binary encoding via `C.encodePubKey` / `C.decodePubKey` (matching SMP's `ToField`/`FromField` instances for `APublicAuthKey` — includes algorithm type tag in the binary format)
+- `file_path` nullable (set after upload completes via `setFilePath`)
+- `ON DELETE CASCADE` for recipients when file is hard-deleted
+- `created_at` stores rounded epoch seconds (1-hour precision, `RoundedFileTime`)
+- `status` as TEXT via `StrEncoding` (`ServerEntityStatus`: `EntityActive`, `EntityBlocked info`, `EntityOff`)
+- Hard deletes (no `deleted_at` column)
+- No PL/pgSQL functions needed; `setFilePath` uses `WHERE file_path IS NULL` to prevent duplicate uploads (the `UPDATE` itself acquires a row-level lock)
+- `used_storage` computed on startup: `SELECT COALESCE(SUM(file_size), 0) FROM files` (matches STM `countUsedStorage` — all files, see usedStorage Ownership section)
+
+### Migrations Module
+
+Following SMP's `QueueStore/Postgres/Migrations.hs` pattern:
+
+```haskell
+module Simplex.FileTransfer.Server.Store.Postgres.Migrations
+  ( xftpServerMigrations,
+  )
+where
+
+import Data.List (sortOn)
+import Data.Text (Text)
+import Simplex.Messaging.Agent.Store.Shared
+import Text.RawString.QQ (r)
+
+xftpSchemaMigrations :: [(String, Text, Maybe Text)]
+xftpSchemaMigrations =
+  [ ("20260325_initial", m20260325_initial, Nothing)
+  ]
+
+xftpServerMigrations :: [Migration]
+xftpServerMigrations = sortOn name $ map migration xftpSchemaMigrations
+  where
+    migration (name, up, down) = Migration {name, up, down = down}
+
+m20260325_initial :: Text
+m20260325_initial =
+  [r|
+CREATE TABLE files (
+  sender_id BYTEA NOT NULL PRIMARY KEY,
+  ...
+);
+  |]
+```
+
+The `Migration` type (from `Simplex.Messaging.Agent.Store.Shared`) has fields `{name :: String, up :: Text, down :: Maybe Text}`. Initial migration has `Nothing` for `down`. Future migrations should include `Just down_migration` for rollback support. Called via `createDBStore dbOpts xftpServerMigrations (MigrationConfig confirmMigrations Nothing)`.
+
+### Postgres Operations
+
+Key query patterns:
+
+- **`addFile`**: `INSERT INTO files (...) VALUES (...)`, return `DUPLICATE_` on unique violation.
+- **`setFilePath`**: `UPDATE files SET file_path = ? WHERE sender_id = ? AND file_path IS NULL`, verified with `assertUpdated` (returns `AUTH` if 0 rows affected — file not found or already uploaded). The `WHERE file_path IS NULL` prevents duplicate uploads; the `UPDATE` acquires a row lock implicitly. Only persists the path; `usedStorage` managed by server.
+- **`addRecipient`**: `INSERT INTO recipients (...)`, plus check for duplicates. No need for `recipientIds` TVar update — Postgres derives it from the table.
+- **`getFile`** (sender): `SELECT ... FROM files WHERE sender_id = ?`, returns auth key from `sender_key` column.
+- **`getFile`** (recipient): `SELECT f.*, r.recipient_key FROM recipients r JOIN files f ON ... WHERE r.recipient_id = ?`.
+- **`deleteFile`**: `DELETE FROM files WHERE sender_id = ?` (recipients cascade).
+- **`blockFile`**: `UPDATE files SET status = ? WHERE sender_id = ?`. When `deleted = True`, the server adjusts `usedStorage` externally (matching current STM behavior where `blockFile` only updates status and storage, not `filePath`).
+- **`expiredFiles`**: `SELECT sender_id, file_path, file_size FROM files WHERE created_at + ? < ? LIMIT ?` — batched query replaces per-file iteration, includes `file_size` for `usedStorage` adjustment. Called in a loop until no rows returned.
+
+## INI Configuration
+
+New keys in `[STORE_LOG]` section:
+
+```ini
+[STORE_LOG]
+enable: on
+store_files: memory            # memory | database
+db_connection: postgresql://xftp@/xftp_server_store
+db_schema: xftp_server
+db_pool_size: 10
+db_store_log: off
+expire_files_hours: 48
+```
+
+`store_files` selects the backend (`store_files` rather than `store_queues` because XFTP stores files, not queues):
+- `memory` -> `XSCMemory` (current behavior)
+- `database` -> `XSCDatabase` (requires `server_postgres` build flag)
+
+### INI Template Generation (`xftp-server init`)
+
+The `iniFileContent` function in `Main.hs` must be updated to generate the new keys in the `[STORE_LOG]` section. Following SMP's `iniDbOpts` pattern with `optDisabled'` (prefixes `"# "` when value equals default), Postgres keys are generated commented out by default:
+
+```ini
+[STORE_LOG]
+enable: on
+
+# File storage mode: `memory` or `database` (PostgreSQL).
+store_files: memory
+
+# Database connection settings for PostgreSQL database (`store_files: database`).
+# db_connection: postgresql://xftp@/xftp_server_store
+# db_schema: xftp_server
+# db_pool_size: 10
+
+# Write database changes to store log file
+# db_store_log: off
+
+expire_files_hours: 48
+```
+
+Reuses `iniDBOptions` from `Simplex.Messaging.Server.CLI` for runtime parsing (falls back to defaults when keys are commented out or missing). `enableDbStoreLog'` pattern (`settingIsOn "STORE_LOG" "db_store_log"`) controls `dbStoreLogPath`.
+
+### PostgresFileStoreCfg
+
+```haskell
+data PostgresFileStoreCfg = PostgresFileStoreCfg
+  { dbOpts :: DBOpts,
+    dbStoreLogPath :: Maybe FilePath,
+    confirmMigrations :: MigrationConfirmation
+  }
+```
+
+No `deletedTTL` (hard deletes).
+
+### Default DB Options
+
+```haskell
+defaultXFTPDBOpts :: DBOpts
+defaultXFTPDBOpts =
+  DBOpts
+    { connstr = "postgresql://xftp@/xftp_server_store",
+      schema = "xftp_server",
+      poolSize = 10,
+      createSchema = False
+    }
+```
+
+## Migration CLI
+
+Bidirectional migration via StoreLog as interchange format:
+
+```
+xftp-server database import [--database DB_CONN] [--schema DB_SCHEMA] [--pool-size N]
+xftp-server database export [--database DB_CONN] [--schema DB_SCHEMA] [--pool-size N]
+```
+
+No `--table` flag needed (unlike SMP which has queues/messages/all) — XFTP has a single entity type (files + recipients, always migrated together).
+
+CLI options reuse `dbOptsP` parser from `Simplex.Messaging.Server.CLI`.
+
+### Import (StoreLog -> PostgreSQL)
+
+1. Confirm: prompt user with database connection details and StoreLog path
+2. Read and replay StoreLog into temporary `STMFileStore`
+3. Connect to PostgreSQL, run schema migrations (`createSchema = True`, `confirmMigrations = MCYesUp`)
+4. Batch-insert file records into `files` table using PostgreSQL COPY protocol (matching SMP's `batchInsertQueues` pattern for performance). Progress reported every 10k files.
+5. Batch-insert recipient records into `recipients` table using COPY protocol
+6. Verify counts: `SELECT COUNT(*) FROM files` / `recipients` — warn if mismatch
+7. Rename StoreLog to `.bak` (prevents accidental re-import, preserves original for rollback)
+8. Report counts
+
+### Export (PostgreSQL -> StoreLog)
+
+1. Confirm: prompt user with database connection details and output path. Fail if output file already exists.
+2. Connect to PostgreSQL
+3. Open new StoreLog file for writing
+4. Fold over all file records, writing per file (in this order, matching existing `writeFileStore`): `AddFile` (with `ServerEntityStatus` — this preserves `EntityBlocked` state), `AddRecipients`, then `PutFile` (if `file_path` is set)
+5. Report counts
+
+Note: `AddFile` carries `ServerEntityStatus` which includes `EntityBlocked info`, so blocking state is preserved through export/import without needing separate `BlockFile` log entries.
+
+File data on disk is untouched by migration — only metadata moves between backends.
+
+## Cabal Integration
+
+Shared `server_postgres` flag. New Postgres modules added to existing conditional block:
+
+```cabal
+if flag(server_postgres)
+  cpp-options: -DdbServerPostgres
+  exposed-modules:
+    ...existing SMP modules...
+    Simplex.FileTransfer.Server.Store.Postgres
+    Simplex.FileTransfer.Server.Store.Postgres.Migrations
+    Simplex.FileTransfer.Server.Store.Postgres.Config
+```
+
+CPP guards (`#if defined(dbServerPostgres)`) in:
+- `Store.hs` — Postgres `FromField`/`ToField` instances for XFTP-specific types if needed
+- `Env.hs` — `XSCDatabase` constructor
+- `Main.hs` — database CLI commands, store selection for `database` mode, Postgres imports
+- `Server.hs` — Postgres-specific imports if needed
+
+## Testing
+
+- **Parameterized server tests**: Existing `xftpServerTests` refactored to accept a store type parameter (following SMP's `SpecWith (ASrvTransport, AStoreType)` pattern). The same server tests run against both STM and Postgres backends — STM tests run unconditionally, Postgres tests added under `#if defined(dbServerPostgres)` with `postgressBracket` for database lifecycle (drop → create → test → drop).
+- **Unit tests**: `PostgresFileStore` operations — add/get/delete/block/expire, duplicate detection, auth errors
+- **Migration round-trip**: STM store → export to StoreLog → import to Postgres → export back → verify StoreLog equality (including blocked file status)
+- **Tests location**: in `tests/` alongside existing XFTP tests, guarded by `server_postgres` CPP flag
+- **Test database**: PostgreSQL on `localhost:5432`, using a dedicated `xftp_server_test` schema (dropped and recreated per test run via `postgressBracket`, following SMP's test database lifecycle pattern)
+- **Test fixtures**: `testXFTPStoreDBOpts :: DBOpts` with `createSchema = True`, `confirmMigrations = MCYesUp`, in `tests/XFTPClient.hs`

plans/2026-03-25-xftp-postgres-implementation-plan.md

@@ -0,0 +1,648 @@
+# XFTP PostgreSQL Backend — Implementation Plan
+
+> **For agentic workers:** REQUIRED: Use superpowers-extended-cc:subagent-driven-development (if subagents available) or superpowers-extended-cc:executing-plans to implement this plan. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Add PostgreSQL backend support to xftp-server as an alternative to STM + StoreLog, with bidirectional migration.
+
+**Architecture:** Introduce `FileStoreClass` typeclass (IO-based, following `QueueStoreClass` pattern). Extract current STM store into `Store/STM.hs`, make `Server.hs` polymorphic, then add `Store/Postgres.hs` behind `server_postgres` CPP flag. `usedStorage` moves from store to `XFTPEnv` so the server manages quota tracking externally.
+
+**Tech Stack:** Haskell, postgresql-simple, STM, fourmolu, cabal with CPP flags
+
+**Design spec:** `plans/2026-03-25-xftp-postgres-backend-design.md`
+
+---
+
+## File Structure
+
+**Existing files modified:**
+- `src/Simplex/FileTransfer/Server/Store.hs` — rewritten: becomes typeclass + shared types
+- `src/Simplex/FileTransfer/Server/Env.hs` — polymorphic `XFTPEnv s`, `XFTPStoreConfig` GADT
+- `src/Simplex/FileTransfer/Server.hs` — polymorphic over `FileStoreClass s`
+- `src/Simplex/FileTransfer/Server/StoreLog.hs` — update for IO store functions
+- `src/Simplex/FileTransfer/Server/Main.hs` — INI config, dispatch, CLI commands
+- `simplexmq.cabal` — new modules
+- `tests/XFTPClient.hs` — Postgres test fixtures
+- `tests/Test.hs` — Postgres test group
+
+**New files created:**
+- `src/Simplex/FileTransfer/Server/Store/STM.hs` — `STMFileStore` (extracted from current `Store.hs`)
+- `src/Simplex/FileTransfer/Server/Store/Postgres.hs` — `PostgresFileStore` [CPP-guarded]
+- `src/Simplex/FileTransfer/Server/Store/Postgres/Config.hs` — `PostgresFileStoreCfg` [CPP-guarded]
+- `src/Simplex/FileTransfer/Server/Store/Postgres/Migrations.hs` — schema SQL [CPP-guarded]
+- `tests/CoreTests/XFTPStoreTests.hs` — Postgres store unit tests [CPP-guarded]
+
+---
+
+## Task 1: Move `usedStorage` from `FileStore` to `XFTPEnv`
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Store.hs`
+- Modify: `src/Simplex/FileTransfer/Server/Env.hs`
+- Modify: `src/Simplex/FileTransfer/Server.hs`
+
+- [ ] **Step 1: Remove `usedStorage` from `FileStore` in `Store.hs`**
+
+  1. Remove `usedStorage :: TVar Int64` field from `FileStore` record (line 47).
+  2. Remove `usedStorage <- newTVarIO 0` from `newFileStore` (line 75) and drop the field from the record construction (line 76).
+  3. In `setFilePath` (line 92-97): remove `modifyTVar' (usedStorage st) (+ fromIntegral (size fileInfo))` — keep only `writeTVar filePath (Just fPath)`. Change pattern from `\FileRec {fileInfo, filePath}` to `\FileRec {filePath}` (fileInfo is now unused — `-Wunused-matches` error).
+  4. In `deleteFile` (line 112-119): remove `modifyTVar' usedStorage $ subtract (fromIntegral $ size fileInfo)`. Change outer pattern match from `FileStore {files, recipients, usedStorage}` to `FileStore {files, recipients}`. Change inner pattern from `Just FileRec {fileInfo, recipientIds}` to `Just FileRec {recipientIds}` (`fileInfo` is now unused — `-Wunused-matches` error).
+  5. In `blockFile` (line 122-127): remove `when deleted $ modifyTVar' usedStorage $ subtract (fromIntegral $ size fileInfo)`. Change pattern match from `st@FileStore {usedStorage}` to `st`. The `deleted` parameter and `fileInfo` in the inner pattern become unused — prefix with `_` or remove from pattern to avoid `-Wunused-matches`.
+
+- [ ] **Step 2: Add `usedStorage` to `XFTPEnv` in `Env.hs`**
+
+  1. Add `usedStorage :: TVar Int64` field to `XFTPEnv` record (between `store` and `storeLog`, line 93).
+  2. In `newXFTPServerEnv` (line 112-126): replace lines 117-118:
+     ```
+     used <- countUsedStorage <$> readTVarIO (files store)
+     atomically $ writeTVar (usedStorage store) used
+     ```
+     with:
+     ```
+     usedStorage <- newTVarIO =<< countUsedStorage <$> readTVarIO (files store)
+     ```
+  3. Add `usedStorage` to the `pure XFTPEnv {..}` construction.
+
+- [ ] **Step 3: Update all `usedStorage` access sites in `Server.hs`**
+
+  1. Line 552: `us <- asks $ usedStorage . store` → `us <- asks usedStorage`.
+  2. Line 569: `us <- asks $ usedStorage . store` → `us <- asks usedStorage`.
+  3. Line 639: `usedStart <- readTVarIO $ usedStorage st` → `usedStart <- readTVarIO =<< asks usedStorage`.
+  4. Line 647: `usedEnd <- readTVarIO $ usedStorage st` → `usedEnd <- readTVarIO =<< asks usedStorage`.
+  5. Line 694: `FileStore {files, usedStorage} <- asks store` → split into `FileStore {files} <- asks store` and `usedStorage <- asks usedStorage`.
+  6. In `deleteOrBlockServerFile_` (line 620): after `void $ atomically $ storeAction st`, add usedStorage adjustment — `us <- asks usedStorage` then `atomically $ modifyTVar' us $ subtract (fromIntegral $ size fileInfo)` when file had a path (check `path` from `readTVarIO filePath` earlier in the function).
+
+- [ ] **Step 4: Build and verify**
+
+  Run: `cabal build`
+
+- [ ] **Step 5: Run existing tests**
+
+  Run: `cabal test --test-show-details=streaming --test-option=--match="/XFTP/"`
+
+- [ ] **Step 6: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs
+  git add src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs
+  git commit -m "refactor(xftp): move usedStorage from FileStore to XFTPEnv"
+  ```
+
+---
+
+## Task 2: Add `getUsedStorage`, `getFileCount`, `expiredFiles` functions
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Store.hs`
+- Modify: `src/Simplex/FileTransfer/Server/Env.hs`
+- Modify: `src/Simplex/FileTransfer/Server.hs`
+
+- [ ] **Step 1: Add three new functions to `Store.hs`**
+
+  1. Add to exports: `getUsedStorage`, `getFileCount`, `expiredFiles`.
+  2. Remove `expiredFilePath` from exports AND delete the function definition (dead code → `-Wunused-binds` error). Also remove `($>>=)` from import `Simplex.Messaging.Util (ifM, ($>>=))` → `Simplex.Messaging.Util (ifM)` — `$>>=` was only used by `expiredFilePath`.
+  3. Add import: `qualified Data.Map.Strict as M` (needed for `M.foldl'` in `getUsedStorage` and `M.toList` in `expiredFiles`).
+  4. Implement:
+     ```haskell
+     getUsedStorage :: FileStore -> IO Int64
+     getUsedStorage FileStore {files} =
+       M.foldl' (\acc FileRec {fileInfo = FileInfo {size}} -> acc + fromIntegral size) 0 <$> readTVarIO files
+
+     getFileCount :: FileStore -> IO Int
+     getFileCount FileStore {files} = M.size <$> readTVarIO files
+
+     expiredFiles :: FileStore -> Int64 -> Int -> IO [(SenderId, Maybe FilePath, Word32)]
+     expiredFiles FileStore {files} old _limit = do
+       fs <- readTVarIO files
+       fmap catMaybes . forM (M.toList fs) $ \(sId, FileRec {fileInfo = FileInfo {size}, filePath, createdAt = RoundedSystemTime createdAt}) ->
+         if createdAt + fileTimePrecision < old
+           then do
+             path <- readTVarIO filePath
+             pure $ Just (sId, path, size)
+           else pure Nothing
+     ```
+  5. Add imports: `Data.Maybe (catMaybes)`, `Data.Word (Word32)` (note: `qualified Data.Map.Strict as M` already added in item 3).
+
+- [ ] **Step 2: Replace `countUsedStorage` in `Env.hs`**
+
+  1. Replace `countUsedStorage <$> readTVarIO (files store)` with `getUsedStorage store` in `newXFTPServerEnv`.
+  2. Remove `countUsedStorage` function definition and its export.
+  3. Remove `qualified Data.Map.Strict as M` import if no longer used.
+
+- [ ] **Step 3: Update `restoreServerStats` in `Server.hs` to use `getFileCount`**
+
+  In `restoreServerStats` (line 694-696): replace `FileStore {files} <- asks store` and `_filesCount <- M.size <$> readTVarIO files` with `st <- asks store` and `_filesCount <- liftIO $ getFileCount st` (eliminates the `FileStore` pattern match — `files` binding no longer needed).
+
+- [ ] **Step 4: Replace `expireServerFiles` iteration in `Server.hs`**
+
+  1. Replace the body of `expireServerFiles` (lines 636-660). Remove `files' <- readTVarIO (files st)` and the `forM_ (M.keys files')` loop.
+  2. New body: call `expiredFiles st old 10000` in a loop. For each `(sId, filePath_, fileSize)` in returned list: apply `itemDelay`, remove disk file if present, call `atomically $ deleteFile st sId`, adjust `usedStorage` TVar by `fileSize`, increment `filesExpired` stat. Loop until `expiredFiles` returns `[]`.
+  3. Remove `Data.Map.Strict` import from Server.hs if no longer needed (was used for `M.size` and `M.keys` — now replaced by `getFileCount` and `expiredFiles`).
+
+- [ ] **Step 5: Build and verify**
+
+  Run: `cabal build`
+
+- [ ] **Step 6: Run existing tests**
+
+  Run: `cabal test --test-show-details=streaming --test-option=--match="/XFTP/"`
+
+- [ ] **Step 7: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs
+  git add src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs
+  git commit -m "refactor(xftp): add getUsedStorage, getFileCount, expiredFiles store functions"
+  ```
+
+---
+
+## Task 3: Change `Store.hs` functions from STM to IO
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Store.hs`
+- Modify: `src/Simplex/FileTransfer/Server.hs`
+- Modify: `src/Simplex/FileTransfer/Server/StoreLog.hs`
+
+- [ ] **Step 1: Change all Store.hs function signatures from STM to IO**
+
+  For each of: `addFile`, `setFilePath`, `addRecipient`, `getFile`, `deleteFile`, `blockFile`, `deleteRecipient`, `ackFile`:
+  1. Change return type from `STM (Either XFTPErrorType ...)` to `IO (Either XFTPErrorType ...)` (or `STM ()` to `IO ()` for `deleteRecipient`).
+  2. Wrap the function body in `atomically $ do ...`.
+  3. Keep `withFile` and `newFileRec` as internal STM helpers (called inside the `atomically` blocks).
+
+- [ ] **Step 2: Update Server.hs call sites — remove `atomically` wrappers**
+
+  1. Line 563 (`receiveServerFile`): change `atomically $ writeTVar filePath (Just fPath)` → add `st <- asks store` then `void $ liftIO $ setFilePath st senderId fPath` (design call site #1 — `store` is not in scope in `receiveServerFile`'s `receive` helper, so bind via `asks`; `void` avoids `-Wunused-do-bind` warning on the `Either` result).
+  2. Line 453 (`verifyXFTPTransmission`): split `atomically $ verify =<< getFile st party fId` into: `liftIO (getFile st party fId)` (IO→M lift), then pattern match on result, use `readTVarIO (fileStatus fr)` instead of `readTVar`.
+  3. Lines 371, 377 (control port `CPDelete`/`CPBlock`): change `ExceptT $ atomically $ getFile fs SFRecipient fileId` → `ExceptT $ liftIO $ getFile fs SFRecipient fileId` (inside `unliftIO u $ do` block which runs in M monad — `liftIO` required to lift IO into M).
+  4. Line 508 (`addFile` in `createFile`): the `ExceptT $ addFile st sId file ts EntityActive` — `addFile` is now IO, `ExceptT` wraps IO directly. Remove any `atomically`.
+  5. Line 514 (`addRecipient`): same — `ExceptT . addRecipient st sId` works directly in IO.
+  6. Line 516 (`retryAdd`): change parameter type from `(XFTPFileId -> STM (Either XFTPErrorType a))` to `(XFTPFileId -> IO (Either XFTPErrorType a))`. Line 520: change `atomically (add fId)` to `liftIO (add fId)`.
+  7. Line 605 (`ackFileReception`): change `atomically $ deleteRecipient st rId fr` to `liftIO $ deleteRecipient st rId fr`.
+  8. Line 620 (`deleteOrBlockServerFile_`): change third parameter type from `(FileStore -> STM (Either XFTPErrorType ()))` to `(FileStore -> IO (Either XFTPErrorType ()))`. Line 626: change `void $ atomically $ storeAction st` to `void $ liftIO $ storeAction st`.
+  9. `expireServerFiles` `delete` helper: change `atomically $ deleteFile st sId` to `liftIO $ deleteFile st sId` (deleteFile is now IO; `liftIO` required because the helper runs in M monad, not IO).
+
+- [ ] **Step 3: Update `StoreLog.hs` — remove `atomically` from replay**
+
+  In `readFileStore` (line 93), function `addToStore`:
+  1. Change `atomically (addToStore lr)` to `addToStore lr` — store functions are now IO.
+  2. The `addToStore` body calls `addFile`, `setFilePath`, `deleteFile`, `blockFile`, `ackFile` — all IO now, no `atomically` needed.
+  3. For `AddRecipients`: `runExceptT $ mapM_ (ExceptT . addRecipient st sId) rcps` — `addRecipient` returns `IO (Either ...)`, so `ExceptT . addRecipient st sId` works directly.
+
+- [ ] **Step 4: Build and verify**
+
+  Run: `cabal build`
+
+- [ ] **Step 5: Run existing tests**
+
+  Run: `cabal test --test-show-details=streaming --test-option=--match="/XFTP/"`
+
+- [ ] **Step 6: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server.hs src/Simplex/FileTransfer/Server/StoreLog.hs
+  git add src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server.hs src/Simplex/FileTransfer/Server/StoreLog.hs
+  git commit -m "refactor(xftp): change file store operations from STM to IO"
+  ```
+
+---
+
+## Task 4: Extract `FileStoreClass` typeclass, move STM impl to `Store/STM.hs`
+
+**Files:**
+- Rewrite: `src/Simplex/FileTransfer/Server/Store.hs`
+- Create: `src/Simplex/FileTransfer/Server/Store/STM.hs`
+- Modify: `src/Simplex/FileTransfer/Server/StoreLog.hs`
+- Modify: `src/Simplex/FileTransfer/Server/Env.hs`
+- Modify: `src/Simplex/FileTransfer/Server.hs`
+- Modify: `simplexmq.cabal`
+
+- [ ] **Step 1: Create `Store/STM.hs` — move all implementation code**
+
+  1. Create directory `src/Simplex/FileTransfer/Server/Store/`.
+  2. Create `src/Simplex/FileTransfer/Server/Store/STM.hs`.
+  3. Move from `Store.hs`: `FileStore` data type (rename to `STMFileStore`), all function implementations, internal helpers (`withFile`, `newFileRec`), all STM-specific imports.
+  4. Rename all `FileStore` references to `STMFileStore` in the new file.
+  5. Module declaration: `module Simplex.FileTransfer.Server.Store.STM` exporting only `STMFileStore (..)` — do NOT export standalone functions (`addFile`, `setFilePath`, etc.) to avoid name collisions with the typeclass methods from `Store.hs`.
+
+- [ ] **Step 2: Rewrite `Store.hs` as the typeclass module**
+
+  1. Add `{-# LANGUAGE TypeFamilies #-}` pragma to `Store.hs` (required for `type FileStoreConfig s` associated type).
+  2. Keep in `Store.hs`: `FileRec (..)`, `FileRecipient (..)`, `RoundedFileTime`, `fileTimePrecision` definitions and their `StrEncoding` instance.
+  3. Add `FileStoreClass` typeclass:
+     ```haskell
+     class FileStoreClass s where
+       type FileStoreConfig s
+
+       -- Lifecycle
+       newFileStore :: FileStoreConfig s -> IO s
+       closeFileStore :: s -> IO ()
+
+       -- File operations
+       addFile :: s -> SenderId -> FileInfo -> RoundedFileTime -> ServerEntityStatus -> IO (Either XFTPErrorType ())
+       setFilePath :: s -> SenderId -> FilePath -> IO (Either XFTPErrorType ())
+       addRecipient :: s -> SenderId -> FileRecipient -> IO (Either XFTPErrorType ())
+       getFile :: s -> SFileParty p -> XFTPFileId -> IO (Either XFTPErrorType (FileRec, C.APublicAuthKey))
+       deleteFile :: s -> SenderId -> IO (Either XFTPErrorType ())
+       blockFile :: s -> SenderId -> BlockingInfo -> Bool -> IO (Either XFTPErrorType ())
+       deleteRecipient :: s -> RecipientId -> FileRec -> IO ()
+       ackFile :: s -> RecipientId -> IO (Either XFTPErrorType ())
+
+       -- Expiration
+       expiredFiles :: s -> Int64 -> Int -> IO [(SenderId, Maybe FilePath, Word32)]
+
+       -- Stats
+       getUsedStorage :: s -> IO Int64
+       getFileCount :: s -> IO Int
+     ```
+  4. Do NOT re-export from `Store/STM.hs` — this would create a circular module dependency (Store.hs imports Store/STM.hs, Store/STM.hs imports Store.hs). Consumers must import `Store.STM` directly where they need `STMFileStore`.
+  5. Remove all STM-specific imports that are no longer needed.
+
+- [ ] **Step 3: Add `FileStoreClass` instance in `Store/STM.hs`**
+
+  1. Import `FileStoreClass` from `Simplex.FileTransfer.Server.Store`.
+  2. Inline all implementations directly in the instance body (do NOT delegate to standalone functions — the standalone names collide with typeclass method names, causing ambiguous occurrences for importers):
+     ```haskell
+     instance FileStoreClass STMFileStore where
+       type FileStoreConfig STMFileStore = ()
+       newFileStore () = do
+         files <- TM.emptyIO
+         recipients <- TM.emptyIO
+         pure STMFileStore {files, recipients}
+       closeFileStore _ = pure ()
+       addFile st sId fileInfo createdAt status = atomically $ ...
+       setFilePath st sId fPath = atomically $ ...
+       -- ... (each method's body is the existing function body, inlined)
+     ```
+  3. Remove the standalone top-level function definitions — they are now instance methods. Keep only `withFile` and `newFileRec` as internal helpers used by the instance methods.
+
+- [ ] **Step 4: Update importers**
+
+  1. `Env.hs`: add `import Simplex.FileTransfer.Server.Store.STM (STMFileStore (..))`. Change `FileStore` → `STMFileStore` in `XFTPEnv` type and `newXFTPServerEnv`. Change `store <- newFileStore` to `store <- newFileStore ()` (typeclass method now takes `FileStoreConfig STMFileStore` which is `()`). Keep `import Simplex.FileTransfer.Server.Store` for `FileRec`, `FileRecipient`, `FileStoreClass`, etc.
+  2. `Server.hs`: add `import Simplex.FileTransfer.Server.Store.STM`. Change `FileStore` → `STMFileStore` in any explicit type annotations. Import `FileStoreClass` from `Simplex.FileTransfer.Server.Store`.
+  3. `StoreLog.hs`: add `import Simplex.FileTransfer.Server.Store.STM` to access concrete `STMFileStore` type and store functions used during log replay. Change `FileStore` → `STMFileStore` in `readWriteFileStore` and `writeFileStore` parameter types.
+
+- [ ] **Step 5: Update cabal file**
+
+  Add `Simplex.FileTransfer.Server.Store.STM` to `exposed-modules` in the `!flag(client_library)` section, alongside existing XFTP server modules.
+
+- [ ] **Step 6: Build and verify**
+
+  Run: `cabal build`
+
+- [ ] **Step 7: Run existing tests**
+
+  Run: `cabal test --test-show-details=streaming --test-option=--match="/XFTP/"`
+
+- [ ] **Step 8: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server/Store/STM.hs src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs src/Simplex/FileTransfer/Server/StoreLog.hs
+  git add src/Simplex/FileTransfer/Server/Store.hs src/Simplex/FileTransfer/Server/Store/STM.hs src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs src/Simplex/FileTransfer/Server/StoreLog.hs simplexmq.cabal
+  git commit -m "refactor(xftp): extract FileStoreClass typeclass, move STM impl to Store.STM"
+  ```
+
+---
+
+## Task 5: Make `XFTPEnv` and `Server.hs` polymorphic over `FileStoreClass`
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Env.hs`
+- Modify: `src/Simplex/FileTransfer/Server.hs`
+- Modify: `src/Simplex/FileTransfer/Server/Main.hs`
+- Modify: `tests/XFTPClient.hs` (if it calls `runXFTPServerBlocking` directly)
+
+- [ ] **Step 1: Make `XFTPEnv` polymorphic in `Env.hs`**
+
+  1. Add `XFTPStoreConfig` GADT: `data XFTPStoreConfig s where XSCMemory :: Maybe FilePath -> XFTPStoreConfig STMFileStore`.
+  2. Change `data XFTPEnv` to `data XFTPEnv s` — field `store :: FileStore` becomes `store :: s`.
+  3. Change `newXFTPServerEnv :: XFTPServerConfig -> IO XFTPEnv` to `newXFTPServerEnv :: FileStoreClass s => XFTPStoreConfig s -> XFTPServerConfig -> IO (XFTPEnv s)`.
+  4. Pattern match on `XSCMemory storeLogPath` in `newXFTPServerEnv` body. Create store via `newFileStore ()`, storeLog via `mapM (`readWriteFileStore` st) storeLogPath`.
+
+- [ ] **Step 2: Make `Server.hs` polymorphic**
+
+  1. Change `type M a = ReaderT XFTPEnv IO a` to `type M s a = ReaderT (XFTPEnv s) IO a`.
+  2. Add `FileStoreClass s =>` constraint to all functions using `M s a`. Use `forall s.` in signatures of functions that have `where`-block bindings with `M s` type annotations — `ScopedTypeVariables` requires explicit `forall` to bring `s` into scope for inner type signatures (matching SMP's `smpServer :: forall s. MsgStoreClass s => ...` pattern). Full list: `xftpServer`, `processRequest`, `verifyXFTPTransmission`, `processXFTPRequest` and all its `where`-bound functions (`createFile`, `addRecipients`, `receiveServerFile`, `sendServerFile`, `deleteServerFile`, `ackFileReception`, `retryAdd`, `addFileRetry`, `addRecipientRetry`), `deleteServerFile_`, `blockServerFile`, `deleteOrBlockServerFile_`, `expireServerFiles`, `randomId`, `getFileId`, `withFileLog`, `incFileStat`, `saveServerStats`, `restoreServerStats`, `randomDelay` (inside `#ifdef slow_servers` CPP block). Also update `encodeXftp` (line 236) and `runCPClient` (line 339) which use explicit `ReaderT XFTPEnv IO` instead of the `M` alias — change to `ReaderT (XFTPEnv s) IO`.
+  3. Change `runXFTPServerBlocking` and `runXFTPServer` to take `XFTPStoreConfig s` parameter.
+  4. Add `closeFileStore store` call to the server shutdown path (in the `finally` block or `stopServer` equivalent — after saving stats, before logging "Server stopped"). This ensures Postgres connection pool and `dbStoreLog` are properly closed. For STM this is a no-op.
+
+- [ ] **Step 3: Update `Main.hs` dispatch**
+
+  1. In `runServer`: construct `XSCMemory (enableStoreLog $> storeLogFilePath)`.
+  2. Add dispatch function that calls the updated `runXFTPServer` (which creates `started` internally):
+     ```haskell
+     run :: FileStoreClass s => XFTPStoreConfig s -> IO ()
+     run storeCfg = runXFTPServer storeCfg serverConfig
+     ```
+  3. Call `run` with the `XSCMemory` config.
+
+- [ ] **Step 4: Update test helper if needed**
+
+  If `tests/XFTPClient.hs` calls `runXFTPServerBlocking` directly, update the call to pass an `XSCMemory` config. Check the `withXFTPServer` / `serverBracket` helper.
+
+- [ ] **Step 5: Build and verify**
+
+  Run: `cabal build && cabal build test:simplexmq-test`
+
+- [ ] **Step 6: Run existing tests**
+
+  Run: `cabal test --test-show-details=streaming --test-option=--match="/XFTP/"`
+
+- [ ] **Step 7: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs src/Simplex/FileTransfer/Server/Main.hs
+  git add src/Simplex/FileTransfer/Server/Env.hs src/Simplex/FileTransfer/Server.hs src/Simplex/FileTransfer/Server/Main.hs tests/XFTPClient.hs simplexmq.cabal
+  git commit -m "refactor(xftp): make XFTPEnv and server polymorphic over FileStoreClass"
+  ```
+
+---
+
+## Task 6: Add Postgres config, migrations, and store skeleton
+
+**Files:**
+- Create: `src/Simplex/FileTransfer/Server/Store/Postgres/Config.hs`
+- Create: `src/Simplex/FileTransfer/Server/Store/Postgres/Migrations.hs`
+- Create: `src/Simplex/FileTransfer/Server/Store/Postgres.hs`
+- Modify: `src/Simplex/FileTransfer/Server/Env.hs`
+- Modify: `simplexmq.cabal`
+
+- [ ] **Step 1: Create `Store/Postgres/Config.hs`**
+
+  ```haskell
+  module Simplex.FileTransfer.Server.Store.Postgres.Config
+    ( PostgresFileStoreCfg (..),
+      defaultXFTPDBOpts,
+    )
+  where
+
+  import Simplex.Messaging.Agent.Store.Postgres.Options (DBOpts (..))
+  import Simplex.Messaging.Agent.Store.Shared (MigrationConfirmation)
+
+  data PostgresFileStoreCfg = PostgresFileStoreCfg
+    { dbOpts :: DBOpts,
+      dbStoreLogPath :: Maybe FilePath,
+      confirmMigrations :: MigrationConfirmation
+    }
+
+  defaultXFTPDBOpts :: DBOpts
+  defaultXFTPDBOpts =
+    DBOpts
+      { connstr = "postgresql://xftp@/xftp_server_store",
+        schema = "xftp_server",
+        poolSize = 10,
+        createSchema = False
+      }
+  ```
+
+- [ ] **Step 2: Create `Store/Postgres/Migrations.hs`**
+
+  Full migration module with `xftpServerMigrations :: [Migration]` and `m20260325_initial` containing CREATE TABLE SQL for `files` and `recipients` tables plus indexes. Follow SMP's `QueueStore/Postgres/Migrations.hs` pattern exactly: tuple list → `sortOn name . map migration`.
+
+- [ ] **Step 3: Create `Store/Postgres.hs` with stub instance**
+
+  1. Define `PostgresFileStore` with `dbStore :: DBStore` and `dbStoreLog :: Maybe (StoreLog 'WriteMode)`.
+  2. `instance FileStoreClass PostgresFileStore` with `error "not implemented"` for all methods except `newFileStore` (calls `createDBStore` + opens `dbStoreLog`) and `closeFileStore` (closes both). `type FileStoreConfig PostgresFileStore = PostgresFileStoreCfg`.
+  3. Add `withDB`, `handleDuplicate`, `assertUpdated`, `withLog` helpers.
+
+- [ ] **Step 4: Add `XSCDatabase` GADT constructor in `Env.hs` (CPP-guarded)**
+
+  ```haskell
+  #if defined(dbServerPostgres)
+  import Simplex.FileTransfer.Server.Store.Postgres (PostgresFileStore)
+  import Simplex.FileTransfer.Server.Store.Postgres.Config (PostgresFileStoreCfg)
+  #endif
+
+  data XFTPStoreConfig s where
+    XSCMemory :: Maybe FilePath -> XFTPStoreConfig STMFileStore
+  #if defined(dbServerPostgres)
+    XSCDatabase :: PostgresFileStoreCfg -> XFTPStoreConfig PostgresFileStore
+  #endif
+  ```
+
+- [ ] **Step 5: Update cabal**
+
+  Add to existing `if flag(server_postgres)` block:
+  ```
+  Simplex.FileTransfer.Server.Store.Postgres
+  Simplex.FileTransfer.Server.Store.Postgres.Config
+  Simplex.FileTransfer.Server.Store.Postgres.Migrations
+  ```
+
+- [ ] **Step 6: Build both ways**
+
+  Run: `cabal build && cabal build -fserver_postgres`
+
+- [ ] **Step 7: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Store/Postgres.hs src/Simplex/FileTransfer/Server/Store/Postgres/Config.hs src/Simplex/FileTransfer/Server/Env.hs
+  git add src/Simplex/FileTransfer/Server/Store/Postgres.hs src/Simplex/FileTransfer/Server/Store/Postgres/Config.hs src/Simplex/FileTransfer/Server/Store/Postgres/Migrations.hs src/Simplex/FileTransfer/Server/Env.hs simplexmq.cabal
+  git commit -m "feat(xftp): add PostgreSQL store skeleton with schema migration"
+  ```
+
+---
+
+## Task 7: Implement `PostgresFileStore` operations
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Store/Postgres.hs`
+
+- [ ] **Step 1: Implement `addFile`**
+
+  `INSERT INTO files (sender_id, file_size, file_digest, sender_key, file_path, created_at, status) VALUES (?,?,?,?,NULL,?,?)`. Catch unique violation with `handleDuplicate` → `DUPLICATE_`. Call `withLog "addFile"` after.
+
+- [ ] **Step 2: Implement `getFile`**
+
+  For `SFSender`: `SELECT ... FROM files WHERE sender_id = ?`. Construct `FileRec` with `newTVarIO` per TVar field. `recipientIds = S.empty`.
+  For `SFRecipient`: `SELECT f.*, r.recipient_key FROM recipients r JOIN files f ON r.sender_id = f.sender_id WHERE r.recipient_id = ?`.
+
+- [ ] **Step 3: Implement `setFilePath`**
+
+  `UPDATE files SET file_path = ? WHERE sender_id = ? AND file_path IS NULL`. Use `assertUpdated`. Call `withLog "setFilePath"`.
+
+- [ ] **Step 4: Implement `addRecipient`**
+
+  `INSERT INTO recipients (recipient_id, sender_id, recipient_key) VALUES (?,?,?)`. `handleDuplicate` → `DUPLICATE_`. Call `withLog "addRecipient"`.
+
+- [ ] **Step 5: Implement `deleteFile`, `blockFile`**
+
+  `deleteFile`: `DELETE FROM files WHERE sender_id = ?` (CASCADE). `withLog "deleteFile"`.
+  `blockFile`: `UPDATE files SET status = ? WHERE sender_id = ?`. `assertUpdated`. `withLog "blockFile"`.
+
+- [ ] **Step 6: Implement `deleteRecipient`, `ackFile`**
+
+  `deleteRecipient`: `DELETE FROM recipients WHERE recipient_id = ?`. `withLog "deleteRecipient"`.
+  `ackFile`: same + return `Left AUTH` if 0 rows.
+
+- [ ] **Step 7: Implement `expiredFiles`, `getUsedStorage`, `getFileCount`**
+
+  `expiredFiles`: `SELECT sender_id, file_path, file_size FROM files WHERE created_at + ? < ? LIMIT ?`.
+  `getUsedStorage`: `SELECT COALESCE(SUM(file_size), 0) FROM files`.
+  `getFileCount`: `SELECT COUNT(*) FROM files`.
+
+- [ ] **Step 8: Add `ToField`/`FromField` instances**
+
+  For `RoundedFileTime` (Int64 wrapper), `ServerEntityStatus` (Text via StrEncoding), `C.APublicAuthKey` (Binary via `encodePubKey`/`decodePubKey`). Check SMP's `QueueStore/Postgres.hs` for existing instances to import.
+
+- [ ] **Step 9: Wrap mutation operations in `uninterruptibleMask_`**
+
+  Operations that combine a DB write with a TVar update (e.g., `getFile` constructs `FileRec` with `newTVarIO`) must be wrapped in `E.uninterruptibleMask_` to prevent async exceptions from leaving inconsistent state. Follow SMP's `addQueue_`, `deleteStoreQueue` pattern.
+
+- [ ] **Step 10: Build**
+
+  Run: `cabal build -fserver_postgres`
+
+- [ ] **Step 11: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Store/Postgres.hs
+  git add src/Simplex/FileTransfer/Server/Store/Postgres.hs
+  git commit -m "feat(xftp): implement PostgresFileStore operations"
+  ```
+
+---
+
+## Task 8: Add INI config, Main.hs dispatch, startup validation
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Main.hs`
+- Modify: `src/Simplex/FileTransfer/Server/Env.hs`
+
+- [ ] **Step 1: Update `iniFileContent` in `Main.hs`**
+
+  Add to `[STORE_LOG]` section: `store_files: memory`, commented-out `db_connection`, `db_schema`, `db_pool_size`, `db_store_log` keys. Follow SMP's `optDisabled'` pattern for commented defaults.
+
+- [ ] **Step 2: Add `StartOptions` and `--confirm-migrations` flag**
+
+  ```haskell
+  data StartOptions = StartOptions
+    { confirmMigrations :: MigrationConfirmation
+    }
+  ```
+  Add to `Start` command parser with default `MCConsole`. Thread through to `runServer`.
+
+- [ ] **Step 3: Add store_files INI parsing and CPP-guarded Postgres dispatch**
+
+  In `runServer`: read `store_files` from INI (`fromRight "memory" $ lookupValue "STORE_LOG" "store_files" ini`). Add `"database"` branch (CPP-guarded) that constructs `PostgresFileStoreCfg` using `iniDBOptions ini defaultXFTPDBOpts` and `enableDbStoreLog'` pattern. Non-postgres build: `exitError`.
+
+- [ ] **Step 4: Add `XSCDatabase` branch in `newXFTPServerEnv` (`Env.hs`)**
+
+  CPP-guarded pattern match on `XSCDatabase dbCfg`: `newFileStore dbCfg`, `storeLog = Nothing`.
+
+- [ ] **Step 5: Add startup config validation**
+
+  Add `checkFileStoreMode` (CPP-guarded) before `run`: validate conflicting storeLog file + database mode, missing schema, etc. per design doc.
+
+- [ ] **Step 6: Build both ways**
+
+  Run: `cabal build && cabal build -fserver_postgres`
+
+- [ ] **Step 7: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Main.hs src/Simplex/FileTransfer/Server/Env.hs
+  git add src/Simplex/FileTransfer/Server/Main.hs src/Simplex/FileTransfer/Server/Env.hs
+  git commit -m "feat(xftp): add PostgreSQL INI config, store dispatch, startup validation"
+  ```
+
+---
+
+## Task 9: Add database import/export CLI commands
+
+**Files:**
+- Modify: `src/Simplex/FileTransfer/Server/Main.hs`
+
+- [ ] **Step 1: Add `Database` CLI command (CPP-guarded)**
+
+  Add `Database StoreCmd DBOpts` constructor to `CliCommand`. Add `database` subcommand parser with `import`/`export` subcommands + `dbOptsP defaultXFTPDBOpts`.
+
+- [ ] **Step 2: Implement `importFileStoreToDatabase`**
+
+  1. `confirmOrExit` with database details.
+  2. Create temporary `STMFileStore`, replay StoreLog via `readWriteFileStore`.
+  3. Create `PostgresFileStore` with `createSchema = True`, `confirmMigrations = MCYesUp`.
+  4. Batch-insert files using PostgreSQL COPY protocol. Progress every 10k.
+  5. Batch-insert recipients using COPY protocol.
+  6. Verify counts: `SELECT COUNT(*)` — warn on mismatch.
+  7. Rename StoreLog to `.bak`.
+  8. Report counts.
+
+- [ ] **Step 3: Implement `exportDatabaseToStoreLog`**
+
+  1. `confirmOrExit`. Fail if output file exists.
+  2. Create `PostgresFileStore` from config.
+  3. Open StoreLog for writing.
+  4. Fold over file records: write `AddFile` (with status), `AddRecipients`, `PutFile` per file.
+  5. Close StoreLog, report counts.
+
+- [ ] **Step 4: Build**
+
+  Run: `cabal build -fserver_postgres`
+
+- [ ] **Step 5: Format and commit**
+
+  ```bash
+  fourmolu -i src/Simplex/FileTransfer/Server/Main.hs
+  git add src/Simplex/FileTransfer/Server/Main.hs
+  git commit -m "feat(xftp): add database import/export CLI commands"
+  ```
+
+---
+
+## Task 10: Add Postgres tests
+
+**Files:**
+- Modify: `tests/XFTPClient.hs`
+- Modify: `tests/Test.hs`
+- Create: `tests/CoreTests/XFTPStoreTests.hs`
+
+- [ ] **Step 1: Add test fixtures in `tests/XFTPClient.hs`**
+
+  ```haskell
+  testXFTPStoreDBOpts :: DBOpts
+  testXFTPStoreDBOpts =
+    DBOpts
+      { connstr = "postgresql://test_xftp_server_user@/test_xftp_server_db",
+        schema = "xftp_server_test",
+        poolSize = 10,
+        createSchema = True
+      }
+  ```
+  Add `testXFTPDBConnectInfo :: ConnectInfo` matching the connection string.
+
+- [ ] **Step 2: Add Postgres server test group in `tests/Test.hs`**
+
+  CPP-guarded block that runs existing `xftpServerTests` with Postgres store config, wrapped in `postgressBracket testXFTPDBConnectInfo`. Parameterize `withXFTPServer` to accept store config if needed.
+
+- [ ] **Step 3: Create `tests/CoreTests/XFTPStoreTests.hs` — unit tests**
+
+  Test `PostgresFileStore` operations directly:
+  - `addFile` + `getFile SFSender` round-trip.
+  - `addFile` duplicate → `DUPLICATE_`.
+  - `getFile` nonexistent → `AUTH`.
+  - `setFilePath` + verify `WHERE file_path IS NULL` guard.
+  - `addRecipient` + `getFile SFRecipient` round-trip.
+  - `deleteFile` cascades recipients.
+  - `blockFile` + verify status.
+  - `expiredFiles` batch semantics.
+  - `getUsedStorage`, `getFileCount` correctness.
+
+- [ ] **Step 4: Add migration round-trip test**
+
+  Create `STMFileStore` with test data (files + recipients + blocked status) → export to StoreLog → import to Postgres → export back → compare StoreLog files byte-for-byte.
+
+- [ ] **Step 5: Build and run tests**
+
+  ```bash
+  cabal build -fserver_postgres test:simplexmq-test
+  cabal test --test-show-details=streaming --test-option=--match="/XFTP/" -fserver_postgres
+  ```
+
+- [ ] **Step 6: Format and commit**
+
+  ```bash
+  fourmolu -i tests/CoreTests/XFTPStoreTests.hs tests/XFTPClient.hs
+  git add tests/CoreTests/XFTPStoreTests.hs tests/XFTPClient.hs tests/Test.hs
+  git commit -m "test(xftp): add PostgreSQL backend tests"
+  ```

plans/2026-06-01-bbs-bindings.md

@@ -0,0 +1,126 @@
+# BBS+ Bindings for simplexmq
+
+Haskell FFI bindings to libbbs for BBS+ signatures. General-purpose - the module knows nothing about specific applications.
+
+## How BBS+ works
+
+BBS+ signs a fixed list of N messages. Each message is an arbitrary byte array. The signer signs all N messages at once with one signature.
+
+The holder of the signature can then generate a proof that selectively discloses some messages and hides others. The verifier learns the disclosed messages and confirms they were signed by the signer, but learns nothing about the hidden messages. Different proofs from the same signature are unlinkable.
+
+Key constraint: the total number of messages N is fixed at signing time. The verifier must know N. A proof generated from a 3-message signature cannot be verified as a 2-message proof.
+
+## Types
+
+```haskell
+newtype BBSSecretKey = BBSSecretKey ByteString  -- 32 bytes
+newtype BBSPublicKey = BBSPublicKey ByteString  -- 96 bytes (BLS12-381 G2 point)
+newtype BBSSignature = BBSSignature ByteString  -- 80 bytes
+newtype BBSProof = BBSProof ByteString          -- 272 + 32 * numUndisclosed bytes
+newtype BBSHeader = BBSHeader ByteString        -- always-disclosed context (e.g. protocol identifier)
+newtype BBSPresHeader = BBSPresHeader ByteString -- random nonce for proof unlinkability
+```
+
+All newtypes get StrEncoding (base64url), ToJSON/FromJSON (via strToJSON/strParseJSON), Eq, Show.
+
+## Functions
+
+```haskell
+bbsKeyGen :: IO (Either String BBSKeyPair)  -- BBSKeyPair = (BBSPublicKey, BBSSecretKey)
+
+-- pk is derived from sk internally, so it is not a parameter
+bbsSign
+  :: BBSSecretKey
+  -> BBSHeader            -- always-disclosed context
+  -> [ByteString]         -- all N messages
+  -> IO (Either String BBSSignature)
+
+-- C order: pk, signature, header, presentation_header, disclosed_indexes, messages
+bbsProofGen
+  :: BBSPublicKey
+  -> BBSSignature
+  -> BBSHeader            -- must match what was signed
+  -> BBSPresHeader        -- random nonce bound into the proof
+  -> [Int]                -- disclosed indexes (0-based)
+  -> [ByteString]         -- all N messages (needed internally, hidden ones not revealed in proof)
+  -> IO (Either String BBSProof)
+
+-- C order: pk, proof, header, presentation_header, disclosed_indexes, n, messages
+bbsProofVerify
+  :: BBSPublicKey
+  -> BBSProof
+  -> BBSHeader            -- must match what was signed
+  -> BBSPresHeader        -- must match what was used in bbsProofGen
+  -> [Int]                -- disclosed indexes
+  -> Int                  -- total message count N
+  -> [ByteString]         -- disclosed messages only
+  -> IO Bool
+```
+
+## How applications use it
+
+An application defines:
+- A message layout: which index means what
+- Which indexes are disclosed vs hidden
+- How to encode application values as ByteString messages
+
+### Badge example (in simplex-chat, not in this module)
+
+Message layout (always 3 messages):
+- Index 0: master secret (32 random bytes) - HIDDEN
+- Index 1: expiry (UTF-8 encoded timestamp string) - DISCLOSED
+- Index 2: badge type (UTF-8 encoded, e.g. "supporter") - DISCLOSED
+
+Signing (v2, on the server):
+```
+bbsSign sk header [ms, encodeUtf8 "2026-07-31", encodeUtf8 "supporter"]
+```
+
+Proof generation (v2, on the client):
+```
+bbsProofGen pk sig header presHeader [1, 2] [ms, encodeUtf8 "2026-07-31", encodeUtf8 "supporter"]
+```
+
+Proof verification (v1, on the recipient):
+```
+bbsProofVerify pk proof header presHeader 3 [1, 2] [encodeUtf8 "2026-07-31", encodeUtf8 "supporter"]
+```
+
+The recipient only sees the proof, presentationHeader, expiry string, and badge type string. They verify these were signed by the server (pk is hardcoded). They never see the master secret.
+
+Expiry is always present as a string. Monthly badges use a date like `"2026-07-31"`, lifetime badges use `"lifetime"`. BBS+ doesn't interpret the bytes - expiry semantics are the application's responsibility. This keeps the message count fixed at 3 for all badge types.
+
+## libbbs C API mapping
+
+```c
+int bbs_keygen_full(ciphersuite, sk, pk)
+int bbs_sign(ciphersuite, sk, pk, signature, header, header_len, n, messages, message_lens)
+int bbs_proof_gen(ciphersuite, pk, signature, proof, header, header_len, presentation_header, presentation_header_len, disclosed_indexes, disclosed_indexes_len, n, messages, message_lens)
+int bbs_proof_verify(ciphersuite, pk, proof, proof_len, header, header_len, presentation_header, presentation_header_len, disclosed_indexes, disclosed_indexes_len, n, messages, message_lens)
+```
+
+We use `bbs_sha256_ciphersuite`. The header parameter is exposed in all Haskell functions - the application decides what to put there. Tests use `"SimpleX"` as header.
+
+The `presentation_header` parameter is what we call `presentationHeader`.
+
+In `bbs_proof_verify`, the `n` parameter is the total number of messages (not the number of disclosed messages). The `messages` array contains only the disclosed messages, and `disclosed_indexes` maps each to its position in the original message list.
+
+## Build
+
+Submodules in cbits/:
+- `cbits/libbbs` - https://github.com/Fraunhofer-AISEC/libbbs
+- `cbits/blst` - https://github.com/supranational/blst (libbbs dependency)
+
+C sources in cabal: `cbits/blst/src/server.c`, `cbits/blst/build/assembly.S`, libbbs source files.
+Include dirs: `cbits/blst/bindings/`, `cbits/blst/src/`, `cbits/libbbs/include/`, `cbits/libbbs/src/`.
+C flags: `-D__BLST_PORTABLE__` for cross-CPU-generation compatibility.
+
+## Tests
+
+- Keygen produces keys of correct size
+- Sign + proofGen + proofVerify roundtrip succeeds
+- Tampered proof fails verification
+- Tampered disclosed message fails verification
+- Wrong public key fails verification
+- Two proofs from same credential with different nonces both verify
+- Proof size matches expected (272 + 32 * numUndisclosed)

plans/2026-06-27-service-subscriptions-memory-leak.md

@@ -0,0 +1,57 @@
+## Root cause: orphaned `Sub` entries in the service client's `subscriptions` map
+
+**The leak is service-specific and was introduced by PR #1667 "messaging services" (`f0b7a4be`).** A long-lived messaging-service connection accumulates per-queue `Sub` records in its `Client.subscriptions` map that are **never removed** when the associated queues are deleted or unassociated — only the counter is decremented. Over normal queue churn the map grows monotonically for the entire lifetime of the service connection.
+
+### The proof — an asymmetry between two handlers in `serverThread`
+
+Both individual queue subscriptions and service subscriptions store a `Sub` per queue in `Client.subscriptions` (= `clientSubs` for the SMP subscriber thread, wired at `Server.hs:189`). When a queue ends/is deleted, the two paths diverge:
+
+**Individual subscriber — entry IS removed** (`Server.hs:332`, `346`):
+```haskell
+CSAEndSub qId -> atomically (endSub c qId) >>= a unsub_   -- :332
+  ...
+endSub c qId = TM.lookupDelete qId (clientSubs c) >>= (removeWhenNoSubs c $>)  -- :346
+```
+
+**Service subscriber — entry is NOT removed** (`Server.hs:336-340`):
+```haskell
+CSAEndServiceSub qId -> atomically $ do
+  modifyTVar' (clientServiceSubs c) decrease   -- decrements serviceSubsCount
+  modifyTVar' totalServiceSubs decrease        -- decrements global count
+  where decrease = subtractServiceSubs (1, queueIdHash qId)
+  -- never touches (clientSubs c) — the Sub for qId stays forever
+```
+
+### Where the orphaned entries are added (both new in this PR)
+- `Server.hs:1860-1862` — on service subscribe (`SSUB`), one `Sub` inserted per queue that has a pending message.
+- `Server.hs:2039-2043` (`newServiceDeliverySub`) — on **every** `SEND` to a service-associated queue with no existing sub, a `Sub` is inserted into the service client's `subscriptions`. After delivery the thread state resets to `NoSub` (`:2069`) but the map entry remains as a "already delivering" marker (`:1856-1859`).
+
+### Why they leak
+The only places the service client's `subscriptions` map is cleared are:
+- `clientDisconnected` — `swapTVar subscriptions M.empty` (`Server.hs:1097`) — only on disconnect.
+- `CSADecreaseSubs` — `swapTVar (clientSubs c) M.empty` (`Server.hs:343`) — only on full service takeover by another connection.
+- `delQueueAndMsgs` — `TM.lookupDelete entId $ subscriptions clnt` (`Server.hs:2164`) — but `clnt` here is **the recipient deleting its own queue, not the service client**. The service's entry for that queue is reached only via the `CSDeleted → endServiceSub → CSAEndServiceSub` path (`Server.hs:306, 313, 336`), which decrements the counter but leaves the map entry.
+
+**Concrete scenario (fully traced):** Service `S` subscribes (`SSUB`) and stays connected for days. Recipient `R` owns service-associated queue `Q`. A `SEND` to `Q` inserts a `Sub` into `S.subscriptions[Q]` (`:2042`). `R` later deletes `Q` → `delQueueAndMsgs` runs on `R`'s connection, removes `Q` from `R.subscriptions`, decrements counters, enqueues `CSDeleted Q (Just S)` (`:2167`) → `serverThread` runs `CSAEndServiceSub Q` for `S` (`:336`), decrementing `S.serviceSubsCount` but **leaving `S.subscriptions[Q]` in place**. Net: one orphaned `Sub` (record + 2 TVars) per service-associated queue ever deleted/unassociated, never reclaimed until `S` disconnects. The logical counter `serviceSubsCount` correctly drops, so the map size diverges from the counter — making the leak invisible to the existing service-sub metric.
+
+### Verdict
+This is a deterministic, static-provable memory leak — no production logging needed to confirm the existence; the asymmetry between `CSAEndSub` (removes) and `CSAEndServiceSub` (doesn't) is the smoking gun. It is specific to messaging-service certificate clients, which is exactly the population added by the services/certificate PR.
+
+### Secondary findings (lower impact, same PR area, not the primary cause)
+- **`forkClient` register-after-fork race** (`Server.hs:1356-1359`): if the forked action's `finally` delete (`:1358`) runs before the parent's `IM.insert` (`:1359`), a `Weak ThreadId` of a dead thread is left in `endThreads` until disconnect. Pre-existing, tiny per-entry, but exercised far more by the PR's higher END/DELD volume.
+- **Wrong-client counter decrement** (`Server.hs:2166`): `delQueueAndMsgs` decrements `serviceSubsCount` of the *deleting* client, not the service; harmless for non-service deleters (floored at 0) but corrupts accounting if a service deletes its own queue.
+
+---
+
+### Recommended fix (mirror `endSub` in the service path)
+Make `CSAEndServiceSub` also delete the per-queue `Sub` and cancel its delivery thread, exactly as `CSAEndSub`/`endSub` do for individual subscribers. Roughly:
+
+```haskell
+CSAEndServiceSub qId -> do
+  s_ <- atomically $ do
+    modifyTVar' (clientServiceSubs c) decrease
+    modifyTVar' totalServiceSubs decrease
+    TM.lookupDelete qId (clientSubs c) <* removeWhenNoSubs c
+  forM_ unsub_ $ \unsub -> mapM_ unsub s_
+  where decrease = subtractServiceSubs (1, queueIdHash qId)
+```

plans/20260328_01_server_batched_sub_processing.md

@@ -0,0 +1,152 @@
+# Server: batched SUB command processing
+
+Implementation plan for Part 1 of [RFC 2026-03-28-subscription-performance](../rfcs/2026-03-28-subscription-performance.md).
+
+## Current state
+
+When a batch of ~135 SUB commands arrives, the server already batches:
+- Queue record lookups (`getQueueRecs` in `receive`, Server.hs:1151)
+- Command verification (`verifyLoadedQueue`, Server.hs:1152)
+
+But command processing is per-command (`foldrM process` in `client`, Server.hs:1372-1375). Each SUB calls `subscribeQueueAndDeliver` which calls `tryPeekMsg` - one DB query per queue. For Postgres, that's ~135 individual `SELECT ... FROM messages WHERE recipient_id = ? ORDER BY message_id ASC LIMIT 1` queries per batch.
+
+## Goal
+
+Replace ~135 individual message peek queries with 1 batched query per batch. No protocol changes.
+
+## Implementation
+
+### Step 1: Add `tryPeekMsgs` to MsgStoreClass
+
+File: `src/Simplex/Messaging/Server/MsgStore/Types.hs`
+
+Add to `MsgStoreClass`:
+
+```haskell
+tryPeekMsgs :: s -> [StoreQueue s] -> ExceptT ErrorType IO (Map RecipientId Message)
+```
+
+Returns a map from recipient ID to earliest pending message for each queue that has one. Queues with no messages are absent from the map.
+
+### Step 2: Parameterize `deliver` to accept pre-fetched message
+
+File: `src/Simplex/Messaging/Server.hs`
+
+Currently `deliver` (inside `subscribeQueueAndDeliver`, line 1641) calls `tryPeekMsg ms q`. Add a parameter for an optional pre-fetched message:
+
+```haskell
+deliver :: Maybe Message -> (Bool, Maybe Sub) -> M s ResponseAndMessage
+deliver prefetchedMsg (hasSub, sub_) = do
+  stats <- asks serverStats
+  fmap (either ((,Nothing) . err) id) $ liftIO $ runExceptT $ do
+    msg_ <- maybe (tryPeekMsg ms q) (pure . Just) prefetchedMsg
+    ...
+```
+
+When `Nothing` is passed, falls back to individual `tryPeekMsg` (existing behavior). When `Just msg` is passed, uses it directly (batched path).
+
+### Step 3: Pre-fetch messages before the processing loop
+
+File: `src/Simplex/Messaging/Server.hs`
+
+Currently (lines 1372-1375):
+
+```haskell
+forever $
+  atomically (readTBQueue rcvQ)
+    >>= foldrM process ([], [])
+    >>= \(rs_, msgs) -> ...
+```
+
+Add a pre-fetch step before the existing loop:
+
+```haskell
+forever $ do
+  batch <- atomically (readTBQueue rcvQ)
+  msgMap <- prefetchMsgs batch
+  foldrM (process msgMap) ([], []) batch
+    >>= \(rs_, msgs) -> ...
+```
+
+`prefetchMsgs` scans the batch, collects queues from SUB commands that have a verified queue (`q_ = Just (q, _)`), calls `tryPeekMsgs` once, returns the map. For batches with no SUBs it returns an empty map (no DB call).
+
+`process` passes the looked-up message (or Nothing) through to `processCommand` and down to `deliver`.
+
+The `foldrM process` loop, `processCommand`, `subscribeQueueAndDeliver`, and all other command handlers stay structurally the same. Only `deliver` gains one parameter, and the `client` loop gains one pre-fetch call.
+
+### Step 4: Review
+
+Review the typeclass signature and server usage. Confirm the interface has the right shape before implementing store backends.
+
+### Step 5: Implement for each store backend
+
+#### Postgres
+
+File: `src/Simplex/Messaging/Server/MsgStore/Postgres.hs`
+
+Single query using `DISTINCT ON`:
+
+```sql
+SELECT DISTINCT ON (recipient_id)
+  recipient_id, msg_id, msg_ts, msg_quota, msg_ntf_flag, msg_body
+FROM messages
+WHERE recipient_id IN ?
+ORDER BY recipient_id, message_id ASC
+```
+
+Build `Map RecipientId Message` from results.
+
+#### STM
+
+File: `src/Simplex/Messaging/Server/MsgStore/STM.hs`
+
+Loop over queues, call `tryPeekMsg` for each, collect into map.
+
+#### Journal
+
+File: `src/Simplex/Messaging/Server/MsgStore/Journal.hs`
+
+Loop over queues, call `tryPeekMsg` for each, collect into map.
+
+### Step 6: Handle edge cases
+
+1. **Mixed batches**: `prefetchMsgs` collects only SUB queues. Non-SUB commands get Nothing for the pre-fetched message and process unchanged.
+
+2. **Already-subscribed queues**: Include in pre-fetch - `deliver` is called for re-SUBs too (delivers pending message).
+
+3. **Service subscriptions**: The pre-fetch doesn't care about service state. `sharedSubscribeQueue` handles service association in STM; message peek is the same.
+
+4. **Error queues**: Verification errors from `receive` are Left values in the batch. `prefetchMsgs` only looks at Right values with SUB commands.
+
+5. **Empty pre-fetch**: If batch has no SUBs (e.g., all ACKs), `prefetchMsgs` returns empty map, no DB call made.
+
+### Step 7: Batch other commands (future, not in scope)
+
+The same pattern (pre-fetch before loop, parameterize handler) can extend to:
+- `ACK` with `tryDelPeekMsg` - batch delete+peek
+- `GET` with `tryPeekMsg` - same map lookup
+
+Lower priority since these don't have the N-at-once pattern of subscriptions.
+
+## File changes summary
+
+| File | Change |
+|---|---|
+| `src/Simplex/Messaging/Server/MsgStore/Types.hs` | Add `tryPeekMsgs` to typeclass |
+| `src/Simplex/Messaging/Server/MsgStore/Postgres.hs` | Implement `tryPeekMsgs` with batch SQL |
+| `src/Simplex/Messaging/Server/MsgStore/STM.hs` | Implement `tryPeekMsgs` as loop |
+| `src/Simplex/Messaging/Server/MsgStore/Journal.hs` | Implement `tryPeekMsgs` as loop |
+| `src/Simplex/Messaging/Server.hs` | Add `prefetchMsgs`, parameterize `deliver` |
+
+## Testing
+
+1. Existing server tests must pass unchanged (correctness preserved).
+2. Add a test that subscribes a batch of queues (some with pending messages, some without) and verifies all get correct SOK + MSG responses.
+3. Prometheus metrics: existing `qSub` stat should still increment correctly.
+
+## Performance expectation
+
+For 300K queues across ~2200 batches:
+- Before: ~300K individual DB queries
+- After: ~2200 batched DB queries (one per batch of ~135)
+- ~136x reduction in DB round-trips

plans/20260401_01_batch_queue_associations.md

@@ -0,0 +1,126 @@
+# Server: batch queue service associations
+
+When a batch of SUB or NSUB commands arrives from a service client, each command that needs a new or removed service association calls `setQueueService` individually - one DB write per command. For 135 commands per batch, that's 135 individual `UPDATE msg_queues` queries.
+
+## Goal
+
+Reduce to at most 2 DB queries per batch (one for rcv associations, one for ntf associations), using `UPDATE ... RETURNING recipient_id` to identify which queues were actually updated.
+
+Also fuse message pre-fetch and association batching into a single batch preparation step with a clean contract.
+
+## Contract
+
+```haskell
+prepareBatch :: Maybe ServiceId -> NonEmpty (VerifiedTransmission s) -> M s (Either ErrorType (Map RecipientId (Maybe Message, Maybe (Either ErrorType ()))))
+```
+
+`Left e` = batch-level failure (message pre-fetch or association query failed entirely). All SUBs/NSUBs in the batch get this error.
+
+`Right map` = per-queue results as a tuple:
+- `Maybe Message` - pre-fetched message for SUB queues, `Nothing` for NSUB or no message
+- `Maybe (Either ErrorType ())` - association result. `Nothing` = no update needed. `Just (Right ())` = update succeeded. `Just (Left e)` = update failed for this queue.
+
+One map, one lookup per queue. `processCommand` passes both values to `subscribeQueueAndDeliver` / `subscribeNotifications` -> `sharedSubscribeQueue`.
+
+Queues not in the map (non-SUB/NSUB commands, failed verification) are not affected.
+
+## prepareBatch implementation
+
+One accumulating fold over the batch, collecting three lists:
+- `subMsgQs :: [StoreQueue s]` - SUB queues for message pre-fetch
+- `rcvAssocQs :: [StoreQueue s]` - SUB queues needing `rcv_service_id` update (`clntServiceId /= rcvServiceId qr`)
+- `ntfAssocQs :: [StoreQueue s]` - NSUB queues needing `ntf_service_id` update (`clntServiceId /= ntfServiceId` from `NtfCreds`)
+
+Classification reads from the already-loaded `QueueRec` in `VerifiedTransmission` - no extra DB query.
+
+Then three store calls (each skipped if its list is empty):
+1. `tryPeekMsgs ms subMsgQs` -> `Map RecipientId Message`
+2. `setRcvQueueServices (queueStore ms) clntServiceId rcvAssocQs` -> `Set RecipientId`
+3. `setNtfQueueServices (queueStore ms) clntServiceId ntfAssocQs` -> `Set RecipientId`
+
+Then one pass to merge results into `Map RecipientId (Maybe Message, Maybe (Either ErrorType ()))`:
+- For each SUB queue: `(M.lookup rId msgMap, assocResult rId rcvUpdated rcvAssocQs)`
+- For each NSUB queue: `(Nothing, assocResult rId ntfUpdated ntfAssocQs)`
+
+Where `assocResult rId updated assocQs` = if the queue was in `assocQs` (needed update), then `Just (Right ())` if `rId` is in `updated`, else `Just (Left AUTH)`. If not in `assocQs` (no update needed), `Nothing`.
+
+If any of the three calls fails entirely, return `Left e`.
+
+## Store interface
+
+Replace the polymorphic `setQueueServices` with two plain functions in `QueueStoreClass`:
+
+```haskell
+setRcvQueueServices :: s -> Maybe ServiceId -> [q] -> IO (Set RecipientId)
+setNtfQueueServices :: s -> Maybe ServiceId -> [q] -> IO (Set RecipientId)
+```
+
+No `SParty p` polymorphism. Each function knows its column.
+
+### Postgres implementation
+
+`setRcvQueueServices`:
+```sql
+UPDATE msg_queues SET rcv_service_id = ?
+WHERE recipient_id IN ? AND deleted_at IS NULL
+RETURNING recipient_id
+```
+
+`setNtfQueueServices`:
+```sql
+UPDATE msg_queues SET ntf_service_id = ?
+WHERE recipient_id IN ? AND notifier_id IS NOT NULL AND deleted_at IS NULL
+RETURNING recipient_id
+```
+
+After each batch query, for each queue in the returned set:
+1. Read QueueRec TVar, update with new serviceId
+2. Write store log entry
+
+### STM implementation
+
+Loop over queues, call existing per-item logic, collect succeeded `RecipientId`s into a Set.
+
+## Downstream changes in Server.hs
+
+### processCommand
+
+Gains one parameter: `Map RecipientId (Maybe Message, Maybe (Either ErrorType ()))`.
+
+SUB case: `M.lookup entId prepared` gives `Just (msg_, assocResult)` or `Nothing`. Pass both to `subscribeQueueAndDeliver`.
+
+NSUB case: `M.lookup entId prepared` gives `Just (Nothing, assocResult)` or `Nothing`. Pass `assocResult` to `subscribeNotifications`.
+
+Forwarded commands: pass `M.empty`.
+
+### subscribeQueueAndDeliver
+
+Takes `Maybe Message` and `Maybe (Either ErrorType ())` as before. No change in how it uses them.
+
+### sharedSubscribeQueue
+
+Takes `Maybe (Either ErrorType ())`. On paths needing association update:
+- `Just (Left e)` -> return error
+- `Just (Right ())` -> skip `setQueueService`, proceed with STM work
+- `Nothing` -> no update needed, proceed with existing logic
+
+## Implementation order (top-down)
+
+1. Define the `prepareBatch` contract and thread one map through `processCommand` -> `subscribeQueueAndDeliver` / `subscribeNotifications` -> `sharedSubscribeQueue` (Server.hs)
+2. Implement `prepareBatch` with the fold, three calls, and merge (Server.hs)
+3. Add `setRcvQueueServices` and `setNtfQueueServices` to `QueueStoreClass` (Types.hs)
+4. Implement for Postgres with batch `UPDATE ... RETURNING` (Postgres.hs)
+5. Implement for STM as loop (STM.hs)
+6. Implement for Journal as delegation (Journal.hs)
+
+At step 2, store functions can initially be stubs returning empty sets. Steps 3-6 fill in the real implementations.
+
+## Files changed
+
+| File | Change |
+|---|---|
+| `src/Simplex/Messaging/Server.hs` | `prepareBatch` with fold + merge; one map parameter through `processCommand` -> `subscribeQueueAndDeliver` / `subscribeNotifications` -> `sharedSubscribeQueue` |
+| `src/Simplex/Messaging/Server/QueueStore/Types.hs` | Add `setRcvQueueServices`, `setNtfQueueServices` to `QueueStoreClass` |
+| `src/Simplex/Messaging/Server/QueueStore/Postgres.hs` | Implement with batch `UPDATE ... RETURNING` + per-item TVar/log updates |
+| `src/Simplex/Messaging/Server/QueueStore/STM.hs` | Implement as loop |
+| `src/Simplex/Messaging/Server/MsgStore/Journal.hs` | Delegate to underlying store |

plans/20260522_01_smp_public_namespaces.md

@@ -0,0 +1,455 @@
+# Server: SMP support for public namespaces
+
+> **⚠ Implementation diverged from this plan.** Six audit rounds reshaped the
+> original design. **The shipped code differs in several load-bearing ways:**
+>
+> - **Wire format**: `NameRecord` is now JSON (aeson), not the custom binary
+>   ABNF this plan documents. See `protocol/simplex-messaging.md` §Resolver
+>   commands and `src/Simplex/Messaging/Protocol.hs` ToJSON/FromJSON instances.
+> - **No cache**: the TTL + FIFO + byte-cap cache, in-flight coalescing,
+>   `psqueues` dep, and `cache_*` INI keys are all gone. Every RSLV becomes
+>   one `eth_call` bounded by `rpcMaxConcurrency` + `rpcTimeoutMs`. See
+>   `src/Simplex/Messaging/Server/Names.hs`.
+> - **No `allow_dangerous_colocation` flag**: the proxy co-location guard
+>   was demoted to a startup `logWarn` (the flag was always-on because
+>   `[PROXY]` has no enable toggle).
+> - **Module shape**: `Names/Resolver.hs` was merged into `Names.hs`; only
+>   `Names/Eth/RPC.hs` and `Names/Eth/SNRC.hs` remain as separate modules.
+> - **Test list**: of the 15 specs listed below, ~7 shipped; the rest were
+>   either superseded by the cache removal (CacheSpec) or deferred
+>   (ForwardedRslvSpec, MockRpcSpec, StartupGuardSpec, UrlValidationSpec,
+>   EipChecksumSpec).
+>
+> Sources of truth: `CHANGELOG.md` (release notes),
+> `protocol/simplex-messaging.md` §Resolver commands (wire format),
+> `src/Simplex/Messaging/Server/Names*.hs` (implementation). This file is
+> retained as historical context; do not treat it as a specification.
+
+Implementation plan for Part 2 of [RFC 2026-05-21-public-namespaces](https://github.com/simplex-chat/simplex-chat/blob/ep/namespace/docs/rfcs/2026-05-21-public-namespaces.md). Adds a forwarded-only `RSLV <lookup_key>` SMP command that returns `NAME <NameRecord>` read from the SNRC contract via a Reth+Nimbus JSON-RPC endpoint. Smp-server becomes name-capable by `[NAMES] enable: on`.
+
+Out of scope: `Simplex.Messaging.Client` API, agent-side resolution flow, `ServerRoles.names` in the agent, default-router list, reverse resolution, multicoin/text records, state proofs.
+
+## Architecture
+
+```mermaid
+sequenceDiagram
+  participant C as Client
+  participant P as Proxy (storage role)
+  participant N as Name server (names role)
+  participant E as Ethereum endpoint<br/>(Reth+Nimbus)
+
+  C ->> P: PFWD(enc(RSLV key))
+  P ->> N: RFWD(enc(RSLV key))
+  note over N: verifyTransmission True →<br/>vc SResolver (RSLV _) → VRVerified
+  N ->> N: cache lookup
+  alt cache miss
+    N ->> E: eth_call(SNRC, namehash(key))
+    E -->> N: ABI bytes
+    note over N: ABI decode + zero-owner check + cache insert
+  end
+  N -->> P: RFWD(enc(NAME rec | ERR AUTH))
+  P -->> C: PRES(enc(NAME rec | ERR AUTH))
+```
+
+RSLV is **forwarded-only** — direct RSLV is rejected `CMD PROHIBITED`. This preserves the RFC's two-server resolution: the name server sees the lookup key but never the client's IP, session, or identity.
+
+## Protocol
+
+Shared library: `src/Simplex/Messaging/Protocol.hs` and `src/Simplex/Messaging/Transport.hs`.
+
+**Version.** `Transport.hs:226`: `namesSMPVersion = VersionSMP 20`. Bump `currentClientSMPRelayVersion`, `currentServerSMPRelayVersion`, `proxiedSMPRelayVersion` to 20. Pre-v20 binaries lack the `RSLV_` tag; v20 binaries with sessions negotiated at v < 20 reject `RSLV_` at the parameter parser. The proxied-version bump 18 → 20 is safe (v19's `RecipientService`/`NotifierService` aren't in the forwarded whitelist; v18's `BLOCKED info` is already version-branched at `Protocol.hs:1943`).
+
+**Party kind.** Append `Resolver` to `Party` (line 335); add `SResolver` (line 349), `TestEquality` clause (line 361), `PartyI Resolver` (line 394). `queueParty SResolver = Nothing` (falls through line 412). `partyClientRole SResolver = Nothing`.
+
+**`RSLV` command.**
+
+```haskell
+RSLV :: LookupKey -> Command Resolver
+newtype LookupKey = LookupKey ByteString
+
+instance Encoding LookupKey where
+  smpEncode (LookupKey s) = smpEncode s
+  smpP = do
+    n <- lenP
+    when (n > 64) $ fail "LookupKey too large"
+    LookupKey <$> A.take n
+```
+
+Name-syntax validation is client-side per RFC; the server treats the key as opaque bytes. Tag `"RSLV"`, version guard inside `protocolP v (CT SResolver RSLV_)`: `| v >= namesSMPVersion -> Cmd SResolver . RSLV <$> _smpP`.
+
+**Testnet/mainnet selector**: how the `#testnet:name` namespace appears in `LookupKey` bytes is determined by the SNRC contract (Part 1) — confirm with Part 1 before merging.
+
+**`NAME` response.**
+
+```haskell
+NAME :: NameRecord -> BrokerMsg
+```
+
+Tag `"NAME"`. Symmetric version guards on encode (in `encodeProtocol v`) and decode (in `protocolP v NAME_`): `| v >= namesSMPVersion -> ...`. `NameRecord` has **no `Encoding` typeclass instance** — the typeclass cannot version-branch. Use top-level helpers `nameRecBytes :: VersionSMP -> NameRecord -> ByteString` and `parseNameRec :: VersionSMP -> Parser NameRecord`, mirroring the `IDS QIK` precedent at `Protocol.hs:1912–1979`.
+
+**`NameRecord` schema and wire layout.**
+
+```haskell
+data NameRecord = NameRecord
+  { nrDisplayName  :: Text                    -- ≤255 bytes UTF-8
+  , nrOwner        :: NameOwner               -- 20 raw bytes
+  , nrChannelLinks :: [NameLink]
+  , nrContactLinks :: [NameLink]
+  , nrAdminAddress :: Maybe Text
+  , nrAdminEmail   :: Maybe Text
+  , nrExpiry       :: Int64                   -- Unix seconds, ≥ 0
+  , nrIsTest       :: Bool
+  }
+
+newtype NameOwner = NameOwner ByteString   -- bare ctor NOT exported; smart ctor enforces length 20
+newtype NameLink  = NameLink  Text         -- bare ctor NOT exported; smart ctor enforces ≤1024 bytes
+
+unNameOwner :: NameOwner -> ByteString
+unNameOwner (NameOwner bs) = bs
+
+unNameLink :: NameLink -> Text
+unNameLink (NameLink t) = t
+```
+
+Field additions are gated by future SMP version bumps (matching the `IDS QIK` precedent at `Protocol.hs:1912–1979`) — no separate record-version field.
+
+| Field | Encoding | Max bytes |
+|---|---|---|
+| `nrDisplayName` | 1-byte length prefix + UTF-8 | 1 + 255 |
+| `nrOwner` | 20 raw bytes, no prefix | 20 |
+| `nrChannelLinks`, `nrContactLinks` | 1-byte count + per-element (Word16 BE len + UTF-8); combined cap **8 entries** across both lists | 1 + Σ(2 + ≤1024) |
+| `nrAdminAddress`, `nrAdminEmail` | `'0'` or `'1'` + (1-byte length + UTF-8 if `'1'`) | 1 + 1 + 255 |
+| `nrExpiry` | two big-endian `Word32` | 8 |
+| `nrIsTest` | `'T'` or `'F'` | 1 |
+
+`Encoding NameLink` reads the Word16 length **before** `A.take` allocates — going through the existing `Large` wrapper allows up to 65 535 bytes per element. There is no `Encoding [a]` instance — use `smpEncodeList` / `smpListP` / a bounded variant:
+
+```haskell
+smpListPUpTo :: Encoding a => Int -> Parser [a]
+smpListPUpTo cap = do
+  n <- lenP
+  when (n > cap) $ fail "list too long"
+  A.count n smpP
+
+parseNameRec _v = do
+  nrDisplayName  <- smpP
+  nrOwner        <- smpP
+  nrChannelLinks <- smpListPUpTo 8
+  nrContactLinks <- smpListPUpTo (8 - length nrChannelLinks)
+  nrAdminAddress <- smpP
+  nrAdminEmail   <- smpP
+  nrExpiry       <- smpP
+  when (nrExpiry < 0) $ fail "expiry must be non-negative"
+  nrIsTest       <- smpP
+  pure NameRecord{..}
+```
+
+Both list parsers fail at the count step before allocating; the second inherits the residual budget. Canonical encoding by construction: every primitive has exactly one valid byte form — two name servers reading the same SNRC state produce byte-identical responses.
+
+**Wire-size budget.** `paddedProxiedTLength = 16226` is the plaintext input to `cbEncrypt` (`Server.hs:2117`); `pad` reserves 2 bytes → framed transmission ≤ 16 224 bytes. Combined-link cap 8 yields max payload ≈ 9 050 bytes — generous margin.
+
+**Error semantics.** A single wire code: `ERR AUTH`. Per RFC, this collapses every failure (name not found, malformed key, names disabled, RPC unreachable, decode error, timeout). Resolver internally distinguishes the cause for stats only.
+
+**Forwarded-only access.** Direct RSLV is rejected with `CMD PROHIBITED`. The shape of `THAuthServer` alone cannot discriminate direct from forwarded (`Transport.hs:852` sets `sessSecret' = Just _` for every v6+ direct client too). An explicit `forwarded :: Bool` flag is threaded through `verifyTransmission` (see below).
+
+## Server changes
+
+All edits in `src/Simplex/Messaging/Server.hs`.
+
+**`forwarded :: Bool` plumbing.** Three signatures change:
+
+- `verifyTransmission :: Bool -> ...` (line 1233) — direct path passes `False` (lines 1152–1153), forwarded path passes `True` (line 2129).
+- `verifyLoadedQueue :: Bool -> ...` (line 1238) — receives the flag from `verifyTransmission` (lines 1235, 1240).
+- `verifyQueueTransmission :: Bool -> ...` (line 1244) — receives and uses the flag.
+
+New `vc` clauses inside `verifyQueueTransmission`:
+
+```haskell
+vc SResolver (RSLV _) | forwarded = VRVerified Nothing
+                      | otherwise = VRFailed (CMD PROHIBITED)
+vc SResolver _ = VRFailed (CMD PROHIBITED)   -- defensive catch-all
+```
+
+**Forwarded whitelist** (`Server.hs:2132`):
+
+```haskell
+Cmd SResolver (RSLV _) -> True
+```
+
+**`processCommand` branch** (alongside line 1481):
+
+```haskell
+Cmd SResolver (RSLV (LookupKey key)) -> do
+  st <- asks (rslvStats . serverStats)
+  incStat (rslvReqs st)
+  asks namesEnv >>= \case
+    Nothing -> incStat (rslvDisabled st)  $> response (corrId, NoEntity, ERR AUTH)
+    Just nenv -> liftIO (resolveName nenv key) >>= \case
+      Right rec     -> incStat (rslvSucc st)     $> response (corrId, NoEntity, NAME rec)
+      Left NotFound -> incStat (rslvNotFound st) $> response (corrId, NoEntity, ERR AUTH)
+      Left _        -> incStat (rslvEthErrs st)  $> response (corrId, NoEntity, ERR AUTH)
+```
+
+**Shutdown.** Add `closeNamesEnv :: NamesEnv -> IO ()` calling `closeManager`. Wire into `closeServer` (`Server.hs:247`):
+
+```haskell
+closeServer = do
+  asks (smpAgent . proxyAgent) >>= liftIO . closeSMPClientAgent
+  asks namesEnv >>= liftIO . mapM_ closeNamesEnv
+```
+
+In-flight `resolveName` calls during shutdown receive `ConnectionClosed` → `EthHttpErr` → masked-leader cleanup runs → waiters unblock with `ERR AUTH`.
+
+**`incStat` relocation.** Defined at `Server.hs:2220`, currently unexported. Move to `Server/Stats.hs` (one-line transplant + export) so `Resolver.hs` can use it.
+
+**Co-located proxy warning.** `newEnv` logs a startup warning whenever `allowSMPProxy = True` and `namesConfig = Just _`. RSLV is the first slow forwarded command; on a proxy host it can serialise other forwarded commands on the same proxy-relay session up to `rpcTimeoutMs` per cache miss. The warning is not a hard refusal because `[PROXY]` has no `enable: on/off` toggle — proxy is always on for every smp-server. `forkForwardedCmd` async dispatch is the longer-term fix, tracked as a follow-up; once the proxy role is gateable per-server, the warning can be tightened back to a refusal.
+
+## Resolver subtree
+
+New module tree at `src/Simplex/Messaging/Server/Names/`:
+
+| Module | Contents |
+|---|---|
+| `Names.hs` | Façade — re-exports `NamesConfig`, `NamesEnv`, `ResolveError`, `resolveName`, `newNamesEnv`, `closeNamesEnv`. |
+| `Names/Resolver.hs` | All types + cache + in-flight + `resolveName`. Helpers exported directly (no `.Internal` per codebase convention). **Test seam**: `NamesEnv` holds `ethCall` as a function value, so tests construct stubs via `newNamesEnvWith`. |
+| `Names/Eth/RPC.hs` | `EthRpcEnv`; `ethCallReal` via `http-client` + `withResponse` + `brReadSome rpcMaxResponseBytes`. JSON-RPC error / HTTP error split. `rpcMaxConcurrency` semaphore. `Authorization` header from `rpcAuth`. |
+| `Names/Eth/SNRC.hs` | `EthAddress`, Keccak-256 namehash via `crypton`'s `Crypto.Hash.Algorithms.Keccak_256` (mirroring `Crypto.hs:1023–1025` for SHA3), hand-rolled bounded Solidity ABI codec, `getRecord` with zero-owner detection. **Ethereum's Keccak ≠ NIST SHA3-256.** |
+
+**ABI codec invariants**, enforced before any allocation: `offset + 32 ≤ buf.length`; `offset + 32 + length ≤ buf.length`; `offset ≥ headEnd` (no backward jumps); every length ≤ per-field cap; `string[]` outer length × 32 ≤ buf.length; recursion depth ≤ 2; `uint256 → Int64` rejects if any high 24 bytes non-zero; UTF-8 via `decodeUtf8'` returns `EthDecodeErr`.
+
+**Zero-owner → `NotFound`**: ENS-style resolvers return zeroed records for non-existent names. After ABI decode, if `nrOwner == NameOwner (B.replicate 20 0)` return `Left NotFound`.
+
+**Errors.**
+
+```haskell
+data ResolveError = NotFound | EthHttpErr | EthRpcErr { rpcCode :: Int, rpcMessage :: Text }
+                  | EthDecodeErr | TimedOut
+```
+
+All collapse to `ERR AUTH`. `EthRpcErr` carries JSON-RPC `error` object — method-not-found (SNRC not deployed at `snrc_address`) is logged immediately on the first error after a recent success: `logError "NAMES: JSON-RPC error from endpoint — check snrc_address: <code> <message>"`. No automatic retry.
+
+**Cache.** TTL + FIFO eviction. `TVar (OrdPSQ LookupKey Word64 NameRecord, Int)` — priority = monotonic-ns at insert; the `Int` is running byte count. `cacheLookup` is one STM transaction (read, expiry-check, expired-delete-with-byte-decrement). `cacheInsert` is one STM transaction: while `size > cacheMaxEntries` OR `bytes + sizeOf(rec) > cacheMaxBytes`, `minView` to drop oldest, then `insert`. Byte counter prevents `100 000 × 9 KB ≈ 900 MB` worst-case blow-up.
+
+**Request coalescing** (async-exception safe via `E.mask`):
+
+```haskell
+resolveName env bs = do
+  let k = LookupKey bs
+  now <- getMonotonicTimeNSec
+  atomically (cacheLookup env k now) >>= \case
+    Just rec -> incStat (rslvCacheHits ...) $> Right rec
+    Nothing  -> do
+      incStat (rslvCacheMiss ...)
+      ticket <- atomically $ TM.lookup k (inflight env) >>= \case
+        Just mv -> pure (Waiter mv)
+        Nothing -> newEmptyTMVar >>= \mv -> TM.insert k mv (inflight env) $> Leader mv
+      case ticket of
+        Waiter mv -> atomically (readTMVar mv)
+        Leader mv -> E.mask $ \restore -> do
+          r <- restore (fetchOnceTimed env bs)
+                 `E.catch` \(e :: E.SomeException) -> pure (Left (mapEthErr e))
+          atomically $ putTMVar mv r >> TM.delete k (inflight env)
+          case r of Right rec -> atomically (cacheInsert env k now rec); Left _ -> pure ()
+          pure r
+
+fetchOnceTimed env bs =
+  System.Timeout.timeout (rpcTimeoutMs (config env) * 1000) (fetchOnce env bs) >>= \case
+    Just r  -> pure r
+    Nothing -> pure (Left TimedOut)
+```
+
+`E.mask` ensures `putTMVar + TM.delete` runs even on async exception; `fetchOnceTimed` runs under `restore` so it remains interruptible. Waiters always see a value; the in-flight TMap entry is always removed.
+
+`fetchOnce`, `mapEthErr`, `scrubUrl`, `cacheLookup`, `cacheInsert` are internal to `Resolver.hs`. `getMonotonicTimeNSec` from `GHC.Clock` — first monotonic-clock use in the codebase; clock-jump safe.
+
+**STM contention.** Cache hits are read-only `readTVar` — STM scales. Cache writes under sustained miss traffic can retry; `CacheSpec` asserts < 5% retry at 4 readers + 1 writer @ 1k RPS. If observed higher, swap `TVar` for `IORef` + `atomicModifyIORef'`.
+
+**Multicoin and text records** are not in `NameRecord`. If Part 1 contract returns them from `getRecord`, extend `NameRecord` and the wire-size budget. **Confirm with Part 1 author before implementing `Eth/SNRC.hs`.**
+
+## Configuration
+
+`ServerConfig` (`Env/STM.hs:142`) gains one field `namesConfig :: Maybe NamesConfig`. `Env` (`Env/STM.hs:261`) gains `namesEnv :: Maybe NamesEnv`. `newEnv` constructs it after `proxyAgent` (line 605) with the co-location guard.
+
+```haskell
+data NamesConfig = NamesConfig
+  { ethereumEndpoint     :: Text          -- http(s), no userinfo, explicit port required
+  , snrcAddress          :: NameOwner     -- 20 bytes
+  , rpcAuth              :: Maybe RpcAuth -- required when https & non-loopback host
+  , cacheSeconds         :: Int           -- 300
+  , cacheMaxEntries      :: Int           -- 100000
+  , cacheMaxBytes        :: Int           -- 67108864 (64 MB)
+  , rpcTimeoutMs         :: Int           -- 3000
+  , rpcMaxResponseBytes  :: Int           -- 262144 (256 KB)
+  , rpcMaxConcurrency    :: Int           -- 8
+  }
+
+data RpcAuth = AuthBearer Text | AuthBasic Text Text
+```
+
+INI parsing in `Server/Main.hs`:
+
+- `validateUrl` (using new `network-uri` dep): accepts only http(s), non-empty host, **explicit port** (rejects `http://localhost` defaulting to 80 while Reth is on 8545), no userinfo, no query/fragment. Rejects `https://...` without `rpc_auth` when host is non-loopback. On rejection: `logError` + `exitFailure`.
+- `parseEthAddr`: accepts `0x[0-9a-fA-F]{40}` and the same without `0x`. Mixed-case → verify EIP-55 checksum and reject mismatch (catches typos).
+- `parseRpcAuth`: reads optional `rpc_auth` key; format `bearer <token>` or `basic <user>:<pass>`.
+- `scrubUrl`: strips userinfo from all log lines mentioning the endpoint, including inside `mapEthErr`.
+- Transition-aware error logging: log immediately on first error after a recent success, then at most hourly while persisting + summary at every stats reset.
+
+Default INI template (`Server/Main/Init.hs`, after `[PROXY]`):
+
+```
+[NAMES]
+# Public-namespace resolution (SNRC on Ethereum).
+# Requires an Ethereum JSON-RPC endpoint (Reth+Nimbus). See deployment guide.
+# Cannot be combined with [PROXY] enable: on by default — see allow_dangerous_colocation.
+# Restart required to change settings.
+enable: off
+# Same-host:
+# ethereum_endpoint: http://127.0.0.1:8545
+# Central Reth via Caddy:
+# ethereum_endpoint: https://eth.simplex.chat:443
+# rpc_auth: basic <username>:<password>
+# snrc_address: 0x0000000000000000000000000000000000000000
+# cache_seconds: 300
+# cache_max_entries: 100000
+# cache_max_bytes: 67108864
+# rpc_timeout_ms: 3000
+# rpc_max_response_bytes: 262144
+# rpc_max_concurrency: 8
+# allow_dangerous_colocation: off
+```
+
+Upgrade from a pre-v6.6 INI: missing `[NAMES]` section → disabled. No operator action required.
+
+## Operator deployment
+
+Two supported topologies. smp-server is agnostic — only `ethereum_endpoint` changes.
+
+**Topology A (same-host)**: smp-server, Caddy (optional), Reth, Nimbus all on one box. `ethereum_endpoint: http://127.0.0.1:8545`.
+
+**Topology B (central Reth, N smp-server hosts — recommended for fleets)**: one operator runs one eth host with Reth+Nimbus behind Caddy on public HTTPS. Each smp-server has its own credential.
+
+```mermaid
+flowchart LR
+  subgraph eth-host
+    Caddy["Caddy<br/>(public :443, basic auth)"]
+    Reth["Reth<br/>(127.0.0.1:8545)"]
+    Nimbus["Nimbus"]
+    Caddy --> Reth
+    Nimbus -- Engine API (jwt.hex) --> Reth
+  end
+  subgraph smp-host-1
+    S1["smp-server #1"]
+  end
+  subgraph smp-host-N
+    SN["smp-server #N"]
+  end
+  S1 -- HTTPS + Authorization --> Caddy
+  SN -- HTTPS + Authorization --> Caddy
+  Reth <-- Ethereum p2p --> internet
+  Nimbus <-- beacon sync --> internet
+```
+
+Sharing one Reth across **multiple operators** is **not** supported — collapses the RFC's two-server resolution privacy.
+
+**Reth + Nimbus**: Reth (execution layer) holds Ethereum state on ~260 GB pruned NVMe; Nimbus (consensus light client) follows beacon-chain headers. Paired via Engine API on `127.0.0.1:8551` with a shared `jwt.hex`. Recommended Reth flags:
+
+```bash
+reth node \
+  --http.addr 127.0.0.1 \
+  --http.api eth \                     # only eth namespace
+  --rpc.gascap 50000000 \              # cap gas per eth_call
+  --rpc.max-response-size 5242880 \    # 5 MB
+  --http.corsdomain none \
+  --authrpc.jwtsecret /opt/eth/jwt.hex \
+  --authrpc.addr 127.0.0.1 --authrpc.port 8551
+```
+
+**Caddy + Let's Encrypt + Basic auth** (Topology B):
+
+```caddy
+eth.simplex.chat {
+  basicauth {
+    smp-server-1 $2a$14$<bcrypt-hash-1>
+    smp-server-2 $2a$14$<bcrypt-hash-2>
+  }
+  log { format filter { wrap json; fields { request>headers>Authorization delete } } }
+  reverse_proxy 127.0.0.1:8545
+}
+```
+
+Caddy auto-fetches Let's Encrypt cert. Each smp-server has its own credential; revoking one = delete the line. `Authorization` stripped from access logs. Port 80 needed for the ACME HTTP-01 challenge (use TLS-ALPN-01 or DNS-01 to drop it). The threat being defended against is DoS (SNRC state is public); mTLS would be overkill. WireGuard/Tailscale are alternative network-layer approaches — both compatible with the plan.
+
+**Capacity.** One Reth+Nimbus box handles a realistic operator fleet by 10–1000× margin. Per-smp-server peak RSLV ≈ 1700 RPS (pessimistic); cache hit rate ≥ 95% → ~85 RPS cache miss per smp-server; 10 smp-servers → ~850 RPS aggregate cache miss reaching Reth; Reth `eth_call` throughput on warm NVMe ≈ 1k–10k RPS. Sizing: 8 vCPU, 32 GB RAM, 1 TB NVMe is comfortable. Scale-out path: more Reth+Nimbus pairs, smp-servers round-robin or shard.
+
+## Implementation
+
+**Order**:
+
+1. Protocol: party/SParty/PartyI, RSLV+tag, NAME+tag, NameRecord + helpers, version constants in `Transport.hs`.
+2. `verifyTransmission`/`verifyLoadedQueue`/`verifyQueueTransmission` `forwarded :: Bool` flag + `vc SResolver` clauses.
+3. Forwarded whitelist + `processCommand` branch + `incStat` move to `Stats.hs`.
+4. Env plumbing: `Server/Env/STM.hs`, `Server/Main.hs` INI parse, `Server/Main/Init.hs` template.
+5. Resolver subtree: `Eth/SNRC.hs` → `Eth/RPC.hs` → `Resolver.hs`.
+6. `NameResolverStats` sub-record + CSV log + Prometheus `names =` block.
+7. Replace stub in (3) with real `resolveName`.
+8. Tests.
+9. `protocol/simplex-messaging.md`: header version line 1 (`19 → 20`), sentence at line 86, version-history list (lines 93–105) v20 entry, TOC (lines 25–68) "Resolver commands" subsection, new section with ABNF + byte layout + error semantics, "Router security requirements" paragraph about names-role outbound HTTP, cross-ref `Transport.hs:226`.
+10. `CHANGELOG.md`: v6.6 entry.
+
+**Cabal** (`simplexmq.cabal`): bump `version: 6.6.0.0`. Add to `if !flag(client_library)` block: `http-client >=0.7 && <0.8`, `http-client-tls >=0.3 && <0.4`, `network-uri >=2.6 && <2.7`, `psqueues >=0.2.7 && <0.3`. Expose 4 new `Server.Names.*` modules in the same block. `crypton` already provides `Keccak_256`.
+
+**Files changed**:
+
+| File | Change |
+|---|---|
+| `Protocol.hs` | Resolver party + RSLV/NAME tags + version guards; `NameRecord` + newtypes + smart ctors; `nameRecBytes`/`parseNameRec`/`smpListPUpTo` helpers (no Encoding NameRecord instance); `LookupKey` parser-side cap |
+| `Transport.hs` | `namesSMPVersion = 20`; bump current/proxied SMP versions |
+| `Server.hs` | Thread `forwarded :: Bool`; `vc SResolver` clauses; whitelist (2132); Resolver branch in `processCommand` (1481); `closeServer` calls `closeNamesEnv`; CSV log (579–618); **remove** local `incStat` |
+| `Server/Env/STM.hs` | `namesConfig` field; `namesEnv` field; `newEnv` constructs `NamesEnv` with co-location guard |
+| `Server/Main.hs` | `[NAMES]` parse: `validateUrl`/`parseEthAddr`/`parseRpcAuth`; `scrubUrl` in logs |
+| `Server/Main/Init.hs` | `[NAMES]` block in default INI |
+| `Server/Stats.hs` | `incStat` moved here + exported; `NameResolverStats` sub-record + helpers; `rslvStats` field |
+| `Server/Prometheus.hs` | `names =` metric block |
+| `Server/Names.hs` (new) | Façade re-exports |
+| `Server/Names/Resolver.hs` (new) | All resolver types + cache + coalescing + `fetchOnceTimed` + `newNamesEnv[With]` + `closeNamesEnv` |
+| `Server/Names/Eth/RPC.hs` (new) | `EthRpcEnv`, `ethCallReal` with bounded body + concurrency semaphore + `Authorization` header |
+| `Server/Names/Eth/SNRC.hs` (new) | `EthAddress`, Keccak namehash, bounded ABI (8 invariants), `getRecord` with zero-owner detection |
+| `simplexmq.cabal` | Bump `6.6.0.0`; 4 new deps + 4 new modules in `if !flag(client_library)` block |
+| `protocol/simplex-messaging.md` | Header version, version-history v20 entry, new "Resolver commands" section |
+| `CHANGELOG.md` | v6.6 entry |
+
+## Testing
+
+`tests/SMPNamesTests/` registered in `tests/Test.hs:112–151`. Build only when `client_library = False`.
+
+1. **ProtocolEncodingSpec** — `nameRecBytes` ↔ `parseNameRec` round-trip; oversized fields rejected at parse; combined-list cap 8 enforced; negative `nrExpiry` rejected; canonical encoding byte-stable.
+2. **MaxSizeSpec** — max `NameRecord` encodes ≤ ~9 KB; `encodeTransmission v ≤ paddedProxiedTLength - 2`; `cbEncrypt` succeeds.
+3. **CommandTagSpec** — `"RSLV"`/`"NAME"` parse; v < 20 sessions reject `RSLV_` at parameter parser.
+4. **ForwardedGateSpec** — direct RSLV → `CMD PROHIBITED`; forwarded RSLV reaches handler.
+5. **ForwardedRslvSpec** — RSLV wrapped in PFWD reaches the handler end-to-end. **Test infra cost**: first protocol-level PFWD test; budget for `runProxiedSmpCommand` helper performing `PRXY`/`PKEY`/`PFWD` manually.
+6. **CacheSpec** — hit avoids RPC; TTL expiry forces re-fetch; bytes cap evicts before entries cap on large records; concurrent same-key callers issue one RPC; leader exception → all waiters get `Left _`, TMap entry removed; leader async-cancel → cleanup STM still runs.
+7. **AbiSpec** — encode/decode against pinned fixtures (`tests/fixtures/snrc/`); QuickCheck fuzz on random buffers ≤ `rpcMaxResponseBytes` must never crash.
+8. **NamehashSpec** — Keccak-256 reference vectors; assert Keccak ≠ SHA3-256.
+9. **MockRpcSpec** — fake HTTP server; missing → `EthHttpErr`; slow → `TimedOut`; multi-GB body truncated → `EthDecodeErr`. `rpcAuth = AuthBasic` sends correct header.
+10. **Uint256OverflowSpec** — `expiry > Int64.maxBound` → `EthDecodeErr`.
+11. **ZeroOwnerSpec** — `owner = 0x000...000` → `NotFound`.
+12. **StartupGuardSpec** — `allowSMPProxy + names.enable` aborts; `allow_dangerous_colocation = on` starts with warning.
+13. **UrlValidationSpec** — userinfo/scheme/host/port edge cases; rejects `https://` without `rpc_auth` for non-loopback.
+14. **EipChecksumSpec** — `parseEthAddr` accepts lower/upper; verifies mixed-case checksum; rejects typos.
+15. **AbiBoundsSpec** — each of 8 ABI invariants triggers `EthDecodeErr` without crash/allocation blow-up.
+
+Integration against real Reth+Nimbus mainnet deferred to ops.
+
+## Threat model, scope, coordination
+
+| Actor | Can | Cannot |
+|---|---|---|
+| Name server | See lookup-key bytes; see query timing; see Eth endpoint URL (operator-self) | See client IP/session; correlate clients across queries |
+| Compromised Eth endpoint | Poison this server's cache for one TTL window; see every lookup key the server queries | Bypass two-server agreement (client-side, out of scope) |
+| Adversarial client (high-rate unique keys) | Cache-thrash DoS; fill `Manager` connection pool up to `managerConnCount = 8` | Bypass `rpcMaxResponseBytes` or `fetchOnceTimed` |
+| Adversarial proxy (slow inner RSLVs) | Block other forwarded commands on that proxy connection up to `rpcTimeoutMs` per miss | Affect other proxy connections |
+| Operator with footgun config (https no auth, public Eth RPC) | (rejected at startup, or operator-acknowledged data leak) | — |
+
+Mitigations: caching + coalescing + `rpcTimeoutMs` + `rpcMaxResponseBytes` + `rpcMaxConcurrency`; co-location refused at startup; URL validation; Caddy + auth in front of Reth; Reth's own gas/size caps. Timing side-channels (cache-hit vs miss latency) not mitigated — flagged for post-MVP. State proofs deferred to post-MVP per RFC.
+
+**Cross-repo coordination.** The `simplex-chat` `ep/namespace` branch currently contains only the RFC commit — no agent-side wire-format code yet. This plan's wire format is validated only by simplexmq's own tests until a matching agent PR lands (structurally weak — encoder/decoder bugs are mutually consistent with themselves). Coordinate with the agent-side implementer **before merging** on: exact `NameRecord` field order and types; `LookupKey` namespace-prefix convention; error-code semantics; Part 1 SNRC contract `getRecord` ABI surface.

protocol/overview-tjr.md

@@ -225,13 +225,13 @@ For encryption primitives, threat model, and detailed security analysis, see [Se
 
 SimpleX provides these security properties:
 
-- **End-to-end encryption** with forward secrecy via double ratchet protocol, with optional post-quantum protection.
+- **End-to-end encryption** using Double Ratchet algorithm with forward secrecy and post-quantum cryptography.
 
 - **No shared identifiers** across connections — contacts cannot prove they communicate with the same user.
 
 - **Sender deniability** — neither routers nor recipients can cryptographically prove message origin.
 
-- **Transport metadata protection** — fixed-size blocks, 2-hop onion routing, and connection isolation frustrate traffic correlation.
+- **Transport metadata protection** — fixed-size blocks, 2-hop onion routing, and optional connection isolation frustrate traffic correlation.
 
 - **Out-of-band key exchange** — connection requests passed outside the network protect against MITM attacks.
 

protocol/simplex-messaging.md

@@ -1,4 +1,4 @@
-Version 19, 2025-01-24
+Version 20, 2026-05-25
 
 # Simplex Messaging Protocol (SMP)
 
@@ -67,6 +67,9 @@ Version 19, 2025-01-24
     - [Queue deleted notification](#queue-deleted-notification)
     - [Error responses](#error-responses)
     - [OK response](#ok-response)
+  - [Resolver commands](#resolver-commands)
+    - [Resolve name command](#resolve-name-command)
+    - [Name record response](#name-record-response)
 - [Transport connection with the SMP router](#transport-connection-with-the-SMP-router)
   - [General transport protocol considerations](#general-transport-protocol-considerations)
   - [TLS transport encryption](#tls-transport-encryption)
@@ -83,7 +86,7 @@ It's designed with the focus on communication security and integrity, under the
 
 It is designed as a low level protocol for other application protocols to solve the problem of secure and private message transmission, making [MITM attack][1] very difficult at any part of the message transmission system.
 
-This document describes SMP protocol version 19. Versions 1-5 are discontinued. The version history:
+This document describes SMP protocol version 20. Versions 1-5 are discontinued. The version history:
 
 - v1: binary protocol encoding
 - v2: message flags (used to control notifications)
@@ -103,6 +106,7 @@ This document describes SMP protocol version 19. Versions 1-5 are discontinued.
 - v17: create notification credentials with NEW command
 - v18: support client notices in BLOCKED error
 - v19: service subscriptions to messages (SUBS, NSUBS, SOKS, ENDS, ALLS commands)
+- v20: public namespaces resolver (RSLV command, RNAME response) — direct or forwarded via PFWD
 
 ## Introduction
 
@@ -424,6 +428,8 @@ Simplex messaging router implementations MUST NOT create, store or send to any o
 
 - Any other information that may compromise privacy or [forward secrecy][4] of communication between clients using simplex messaging routers (the routers cannot compromise forward secrecy of any application layer protocol, such as double ratchet).
 
+Routers with the names role make outbound HTTP calls to a backing resolver service (the reference implementation is `scripts/resolver/snrc-resolve.py`, which in turn makes JSON-RPC calls to an Ethereum endpoint) to read `NameRecord` data; the lookup key reaches that resolver and its upstream RPC endpoint. Operators MUST run both the resolver process and its upstream RPC endpoint themselves (loopback Reth + Nimbus, or a self-hosted central deployment) — sharing them across multiple operators collapses the two-server privacy property because the resolver / RPC operator would see every lookup key across all of them. The names role and the SMP-proxy role MUST NOT be enabled on the same router by default: a client forwarding `RSLV` through a proxy that is also the names router would expose both its connection and the lookup key to one operator, collapsing the two-server privacy property. (Resolution itself runs on a forked thread, so a slow `RSLV` does not serialise other forwarded commands on the session.)
+
 ## Message delivery notifications
 
 Supporting message delivery while the client mobile app is not running requires sending push notifications with the device token. All alternative mechanisms for background message delivery are unreliable, particularly on iOS platform.
@@ -1422,6 +1428,120 @@ When the command is successfully executed by the router, it should respond with
 ok = %s"OK"
 ```
 
+### Resolver commands
+
+Resolver commands implement public-namespace name resolution on the names-role
+router. A names router translates an opaque lookup key (such as `alice` or
+`alice.simplex.eth`) into a `NameRecord` carrying the channel and contact links
+the named party publishes.
+
+**Direct or forwarded.** RSLV is an unauthenticated command accepted both
+directly from a transport client and inside a `PFWD` block via the SMP proxy;
+the client chooses. Forwarded delivery preserves the two-server privacy property
+of the resolver design: the names router sees the lookup key but never the
+client IP, session, or identity, while the proxy router sees the client
+connection but cannot read the encrypted lookup key inside the forwarded
+transmission. Direct delivery is simpler but exposes the client's connection to
+the names router, so clients SHOULD prefer the forwarded path when proxying is
+available.
+
+**Backing store.** This protocol does not prescribe where the names router
+reads `NameRecord` from. The reference implementation forwards each RSLV to a
+companion REST resolver process (`scripts/resolver/snrc-resolve.py`) that
+queries the SNRC contract on Ethereum; alternative backings (different chains,
+DHT, etc.) are valid as long as they expose the documented HTTP shape (`GET
+/resolve/<name>` returning a `NameRecord` on 200, 404 / 400 for unknown names
+or TLDs, 502 for upstream RPC failures) or substitute a different transport
+while still returning a `NameRecord` matching the encoding below.
+
+#### Resolve name command
+
+The `RSLV` command carries the canonical fully-qualified name directly as the
+payload (not JSON):
+
+```abnf
+rslv = %s"RSLV" SP domain   ; domain = canonical name as non-space bytes, consuming the remainder of the transmission
+```
+
+`domain` is the UTF-8 canonical fully-qualified name with the TLD always
+explicit (e.g. `privacy.simplex`, `test.testing`, `example.com`), bounded to
+253 bytes.
+
+**Server-side validation.** The names router parses `domain` as a
+fully-qualified name (TLD required — bare labels are rejected) and forwards it
+to the configured backing resolver, which is the source of truth for which
+on-chain registry maps to each TLD.
+
+The names router responds with either an `RNAME` response carrying the resolved
+record, or an `ERR NAME` error whose subcode a client iterating across several
+configured servers can act on distinctly:
+
+| Response | Condition | Client action |
+|---|---|---|
+| `RNAME` | record resolved | use it |
+| `ERR NAME NOT_FOUND` | name not registered, unknown TLD, or malformed name | authoritative "no such name" — stop |
+| `ERR NAME NO_RESOLVER` | this router has no resolver (names role not enabled) | skip this server, try the next |
+| `ERR NAME RESOLVER <detail>` | transient failure: backing resolver error (upstream 5xx, transport, timeout, decode) | transient — retry or surface, do not treat as "not found" |
+
+A client SHOULD NOT broadcast a `name` to further servers after a name-capable
+router has answered (`NOT_FOUND` or `RESOLVER`), since that router has already
+seen the lookup key; `NO_RESOLVER` discloses nothing about the name beyond the
+fact that this router cannot resolve, so iterating past it is safe.
+
+#### Name record response
+
+The `RNAME` response carries a JSON-encoded record as the payload:
+
+```abnf
+rname = %s"RNAME" SP json-bytes   ; json-bytes consumes the remainder of the transmission
+```
+
+`json-bytes` MUST be a UTF-8 JSON object with the following schema:
+
+| Field | JSON type | Constraints |
+|---|---|---|
+| `name` | string | ≤ 255 bytes UTF-8 |
+| `nickname` | string | ≤ 255 bytes UTF-8; senders MUST emit the empty string `""` when unset |
+| `website` | string | ≤ 255 bytes UTF-8; same empty-string-when-unset rule |
+| `location` | string | ≤ 255 bytes UTF-8; same empty-string-when-unset rule |
+| `simplexContact` | array of strings | each a SimpleX contact link (primary first); empty array `[]` when unset |
+| `simplexChannel` | array of strings | each a SimpleX channel link (primary first); empty array `[]` when unset |
+| `eth` | string or null | ≤ 255 bytes UTF-8; senders MUST emit `null` when unset; receivers MUST also accept absent keys as unset |
+| `btc` | string or null | ≤ 255 bytes UTF-8; same null / absent rules |
+| `xmr` | string or null | ≤ 255 bytes UTF-8; same null / absent rules |
+| `dot` | string or null | ≤ 255 bytes UTF-8; same null / absent rules |
+| `owner` | string | `"0x"` followed by 40 lowercase hex characters (20 raw bytes) |
+| `resolver` | string | `"0x"` followed by 40 lowercase hex characters; the resolver contract address that produced the record |
+
+Text fields (`nickname`, `website`, `location`) use the empty string `""` as
+the "unset" sentinel: a backing resolver with no value for the field MUST emit
+an empty string, not JSON `null` and not an absent key. Link fields
+(`simplexContact`, `simplexChannel`) are arrays, primary link first, and use the
+empty array `[]` when unset. Coin fields (`eth`, `btc`, `xmr`, `dot`) use JSON
+`null` as the "unset" sentinel and MAY also be absent from the object entirely.
+
+The backing resolver filters records that are expired or otherwise unavailable
+(the names router then returns `ERR NAME NOT_FOUND` to the client), so the wire
+format carries no expiry field. Testnet-vs-mainnet status is derived from the
+queried TLD rather than an in-record flag.
+
+Receivers MUST tolerate extra unknown fields (forward-compatibility for future
+field additions). Adding a required field is a breaking change requiring an
+SMP version bump.
+
+**Field order is not significant.** Receivers parse JSON by key name, so object
+key order, insignificant whitespace, and number formatting carry no meaning;
+records are interpreted by decoded value, never compared byte-for-byte. Peers
+MUST NOT rely on a byte-canonical form — a different resolver or server may emit
+the same record with different key order or spacing. This order-independence is
+what makes the format forward-compatible (see the unknown-field rule above).
+
+**Wire-size budget.** The names router caps the resolver response it will
+accept (`resolver_max_response_bytes`, ≤ 16000 bytes, the default) so the
+re-encoded `RNAME` stays within the SMP proxied transmission budget of 16224
+bytes; a response over the cap is rejected as `ERR NAME RESOLVER`. The link
+arrays are bounded by this overall budget rather than a fixed per-field count.
+
 ## Transport connection with the SMP router
 
 ### General transport protocol considerations

rfcs/2026-03-28-subscription-performance.md

@@ -0,0 +1,90 @@
+# Subscription performance
+
+No protocol changes. This is an implementation RFC addressing subscription performance bottlenecks in both the SMP router and the agent.
+
+## Problem
+
+Subscribing large numbers of queues is slow. A messaging client with ~300K queues per router across 3 routers takes over 1 hour to subscribe. For comparison, the NTF server with ~1M queues per router across 12 routers took 20-30 minutes (prior to NTF client services, now in master).
+
+Even on fast networks (cloud VMs), a client with 1.1M active subscriptions needed ~1.5M attempts (commands sent) to fully subscribe - ~36% retry rate caused by the timeout cascade described below.
+
+### Root causes
+
+#### 1. Router: per-command processing in batches
+
+Batch verification and queue lookups are already done efficiently for the whole batch in `Server.hs`. But `processCommand` is called per-command in a loop - each SUB does its own individual DB query for message peek/delivery. With ~135 SUBs per batch (current SMP version), that's 135 individual DB queries per batch instead of 1 batched query.
+
+For 300K queues, that's ~2200 batches x 135 queries = ~300K individual DB queries on the router, which is the dominant bottleneck when using PostgreSQL storage.
+
+NSUB is cheaper because it just registers for notifications without message delivery - no per-queue DB query.
+
+#### 2. Agent: all queues read and sent at once
+
+`getUserServerRcvQueueSubs` reads all queues for a `(userId, server)` pair in one query with no LIMIT. For 300K queues, the entire result set is loaded into memory, then all ~2200 batches are queued to send without waiting for responses.
+
+The NTF server agent uses cursor-style reading with configurable batch sizes (900 subs per chunk, 90K per DB fetch) and waits for each chunk to be processed before fetching the next.
+
+#### 3. No backpressure on sends
+
+`nonBlockingWriteTBQueue` bypasses the `sndQ` bound by forking a thread when the queue is full. All batches are queued immediately, and all their response timers start simultaneously. A 30-second per-response timeout means later batches time out not because the router is slow to respond to them specifically, but because they're waiting in the router's receive queue behind thousands of earlier commands.
+
+This causes cascading timeouts: timed-out responses trigger `resubscribeSMPSession`, which retries all pending subs. Three consecutive timeouts can trigger connection drop via the monitor thread, causing a full reconnection and retry of everything.
+
+## Solution
+
+### Part 1: Router - batched command processing
+
+Move the per-command processing loop inside command handlers so that commands of the same type within a batch can be processed together.
+
+Current flow:
+```
+receive batch -> verify all -> lookup queues all -> for each command: processCommand (individual DB query)
+```
+
+Proposed flow:
+```
+receive batch -> verify all -> lookup queues all -> group by command type -> process group:
+  SUB group: one batched message peek query for all queues
+  NSUB group: batch registration (already cheap, but can batch DB writes)
+  other commands: process individually as before
+```
+
+For SUB, the batched processing would:
+1. Collect all queue IDs from the SUB group
+2. Perform a single DB query to peek messages for all queues
+3. Distribute results back to individual responses
+
+This reduces ~135 DB queries per batch to 1, cutting router-side DB load by ~100x for subscriptions.
+
+Commands where batching doesn't matter (SEND, ACK, KEY, etc.) continue to be processed individually.
+
+### Part 2: Agent - cursor-based subscription with backpressure
+
+Replace the all-at-once fetch-and-send pattern with cursor-style batching, similar to what the NTF server agent does.
+
+Changes to `subscribeUserServer`:
+1. Fetch queues in fixed-size batches (e.g., configurable, default ~1000) using LIMIT/OFFSET or cursor-based pagination.
+2. Send each batch and wait for responses before sending the next.
+3. Remove the use of `nonBlockingWriteTBQueue` for subscription batches - use blocking writes or structured backpressure so response timers don't start until the batch is actually sent.
+
+This ensures:
+- Memory usage is bounded (not 300K queue records in memory at once)
+- Response timeouts are meaningful (timer starts when the router receives the batch, not when it's queued locally)
+- Retries are scoped to the failed batch, not all pending subs
+- Works on slow/lossy networks by naturally pacing sends
+
+### Part 3: Response timeout for batches
+
+The current per-response 30-second timeout doesn't account for batch processing time. Options:
+
+1. **Stagger deadlines**: later responses in a batch get proportionally more time. The `rcvConcurrency` field was designed for this but is never used.
+2. **Per-batch timeout**: instead of timing individual responses, timeout the entire batch with a budget proportional to batch size.
+3. **No timeout for subscription responses**: since subscriptions are sent as batches with backpressure (Part 2), and the connection is monitored by pings, individual response timeouts may not be needed. A subscription that doesn't get a response will be retried on reconnect.
+
+## Priority and ordering
+
+Part 1 (router batching) gives the biggest improvement and is independent of Parts 2/3.
+
+Part 2 (agent cursor + backpressure) eliminates the retry cascade and is critical for slow networks.
+
+Part 3 (timeout handling) is a refinement that can be addressed after Parts 1 and 2.

scripts/docker/entrypoint-smp-server

@@ -67,14 +67,14 @@ if [ ! -f "${confd}/smp-server.ini" ]; then
 
   # Fix path to certificates
   if [ -n "${WEB_MANUAL}" ]; then
-    sed -i -e 's|^[^#]*https: |#&|' \
-           -e 's|^[^#]*cert: |#&|' \
-           -e 's|^[^#]*key: |#&|' \
-           -e 's|^port:.*|port: 5223|' \
+    sed -i -e 's|^[^#]*https = |#&|' \
+           -e 's|^[^#]*cert = |#&|' \
+           -e 's|^[^#]*key = |#&|' \
+           -e 's|^port = .*|port = 5223|' \
            "${confd}/smp-server.ini"
   else
-    sed -i -e "s|cert: /etc/opt/simplex/web.crt|cert: $cert_path/$ADDR.crt|" \
-           -e "s|key: /etc/opt/simplex/web.key|key: $cert_path/$ADDR.key|" \
+    sed -i -e "s|cert = /etc/opt/simplex/web.crt|cert = $cert_path/$ADDR.crt|" \
+           -e "s|key = /etc/opt/simplex/web.key|key = $cert_path/$ADDR.key|" \
            "${confd}/smp-server.ini"
   fi
 fi

scripts/docker/entrypoint-xftp-server

@@ -76,7 +76,7 @@ if [ ! -f "${confd}/file-server.ini" ]; then
 
   # Optionally, set password
   if [ -n "${PASS}" ]; then
-    sed -i -e "/^# create_password:/a create_password: $PASS" \
+    sed -i -e "/^# create_password =/a create_password = $PASS" \
            "${confd}/file-server.ini"
   fi
 fi

scripts/main/simplex-servers-update

@@ -237,11 +237,11 @@ checks() {
     exit 1
   fi
 
+  mkdir -p "$path_conf_info" "$path_tmp_bin"
+
   check_versions
   check_distro
 
-  mkdir -p $path_conf_info $path_tmp_bin
-
   return 0
 }
 

scripts/resolver/.env

@@ -0,0 +1,22 @@
+# ============================================================================
+# Required settings — the stack will not start without these.
+# ============================================================================
+
+# Ethereum network: mainnet (the SNRC `.testing` contracts live on mainnet)
+# or holesky (test). Mainnet full sync needs ~1 day and ~1.2 TB NVMe.
+NETWORK=mainnet
+
+# Beacon checkpoint-sync URL — used ONCE on first sync. Must expose the heavy
+# /eth/v2/debug/beacon/states/finalized endpoint (generic beacon APIs do not;
+# use a dedicated checkpoint provider). List: https://eth-clients.github.io/checkpoint-sync-endpoints/
+#   mainnet: https://mainnet-checkpoint-sync.attestant.io  (also beaconstate.info, sync-mainnet.beaconcha.in)
+#   holesky: https://checkpoint-sync.holesky.ethpandaops.io
+TRUSTED_NODE_URL=https://mainnet-checkpoint-sync.attestant.io
+
+# ============================================================================
+# Optional overrides — sensible defaults are baked into docker-compose.yml,
+# so leave these commented unless you need to change them.
+# ============================================================================
+
+# Nimbus NAT (default: any). For a stable public node set an explicit IP:
+#   NAT=extip:1.2.3.4        # your public IPv4: curl -s ifconfig.me

scripts/resolver/README.md

@@ -0,0 +1,146 @@
+# Self-hosted SNRC stack
+
+One `docker compose up` runs the self-hosted SimpleX Namespace (SNRC) backend
+against **Ethereum mainnet** (where the `.testing` contracts live):
+
+| # | Component | What it does |
+|---|---|---|
+| 1 | **reth + nimbus** | self-hosted Ethereum node (`--minimal` — enough for the resolver's `eth_call` at chain head) |
+| 2 | **resolver** | the REST resolver the smp-server's `[NAMES]` role queries (`snrc-resolve.py`) |
+
+## Requirements
+
+- **Docker** + Compose v2.
+- **≥ 300 GB NVMe SSD** for `reth --minimal` (~260 GB on mainnet; TLC, not QLC
+  — QLC stalls during sync) + **32 GB RAM**, fast multi-core CPU.
+- **~1 day** for the initial reth sync. The resolver returns errors until reth
+  has caught up — that's expected.
+- Firewall: open p2p ports `30303` (tcp/udp) and `9000` (tcp/udp).
+
+## 1. Configure
+
+Edit `.env` — the defaults work as-is; override only if needed:
+
+```sh
+NETWORK=mainnet                                               # default
+TRUSTED_NODE_URL=https://mainnet-checkpoint-sync.attestant.io # default
+```
+
+Everything else (NAT) has a working default baked into `docker-compose.yml`;
+uncomment the hints in `.env` only to override.
+
+## 2. Run
+
+```sh
+cd scripts/resolver
+docker compose up -d
+docker compose logs -f reth resolver
+```
+
+`depends_on` handles ordering automatically (start node → start resolver).
+
+## 3. Wait for the node to sync
+
+```sh
+docker compose logs --tail=20 reth
+```
+
+This is the long pole (~1 day on mainnet). Until reth is synced the resolver
+returns `502`.
+
+## Verify
+
+Run these once the stack is up (the node-dependent ones pass after sync):
+
+**1. reth is reachable and reporting a block:**
+```sh
+curl -s -X POST http://127.0.0.1:8545 \
+  -H 'content-type: application/json' \
+  -d '{"jsonrpc":"2.0","method":"eth_blockNumber","params":[],"id":1}' | jq
+```
+
+**2. resolver is healthy:**
+```sh
+curl -s http://127.0.0.1:8000/health | jq
+# → {"ok": true, "rpc": "http://reth:8545", "registries": {"testing": "0x…", "simplex": ""}}
+```
+
+**3. resolver resolves a live name** (`foobar.testing` is a populated test name):
+```sh
+curl -s http://127.0.0.1:8000/resolve/foobar.testing | jq
+# → {"name":"foobar.testing","nickname":"Foo","simplexContact":["https://smp16.simplex.im/a#…"], … }
+```
+
+**Wire your smp-server:** in its `[NAMES]` section set
+`resolver_endpoint: http://127.0.0.1:8000` (no auth needed for loopback).
+
+## Ports (all loopback unless noted)
+
+| Service | Host | Purpose |
+|---|---|---|
+| reth JSON-RPC | `127.0.0.1:8545` | smp-server RPC |
+| reth p2p | `:30303` tcp/udp | Ethereum sync (open on firewall) |
+| nimbus p2p | `:9000` tcp/udp | beacon sync (open on firewall) |
+| nimbus REST | `127.0.0.1:5052` | beacon API |
+| **resolver** | `127.0.0.1:8000` | SNRC REST (`/resolve`, `/health`) |
+
+## Caveats
+
+- **All images track `:latest`** (reth, nimbus) — you get upstream fixes on each
+  `docker compose pull`; re-run the verify checks after pulling.
+- All ports bind to loopback; expose only what you put behind a TLS reverse proxy.
+
+## Teardown
+
+```sh
+docker compose down       # stop, keep all state
+docker compose down -v    # also wipe volumes → full re-sync
+```
+
+`down -v` wipes the chain data (full re-sync on the next `up`).
+
+---
+
+## Resolver API reference
+
+The resolver (`snrc-resolve.py`, host `127.0.0.1:8000`) is also runnable
+standalone for local dev (no Docker), via [`uv`](https://docs.astral.sh/uv/):
+
+```sh
+uv run scripts/resolver/service/snrc-resolve.py  # defaults to local reth + mainnet .testing
+```
+
+### Response shape
+
+```jsonc
+{
+  "name": "foobar.testing",
+  "nickname": "Foo", "website": "https://foo.bar", "location": "",
+  "simplexContact": ["https://smp16.simplex.im/a#…", "https://smp11…"],  // primary first, fallbacks after
+  "simplexChannel": [],
+  "eth": null, "btc": "bc1q…", "xmr": "4ANz…", "dot": "139G…",
+  "owner": "0xd83b…", "resolver": "0x80fa…"
+}
+```
+
+`simplexContact`/`simplexChannel` are arrays (a name can advertise multiple SMP
+servers; clients try them in order). On-chain they're a single comma-separated
+text record; the resolver splits/trims/drops-empties. Address encodings are
+canonical per chain (EIP-55 / bech32 / SS58 / Monero-base58). Subnames work
+identically (`bar.foobar.testing`).
+
+### Status codes
+
+| Status | Meaning |
+|---|---|
+| 200 | resolved |
+| 400 | TLD not configured, or not a fully-qualified name |
+| 404 | name has no resolver set on the registry |
+| 502 | upstream RPC error / reth not synced |
+
+### Configuring registries
+
+Defaults to mainnet `.testing` (`0x03f438…`); `.simplex` is unset until
+deployed. Override per TLD via env on the `resolver` service in
+`docker-compose.yml` (`SNRC_REGISTRY_TESTING` / `SNRC_REGISTRY_SIMPLEX`), or as
+env vars for the standalone script.

scripts/resolver/docker-compose.yml

@@ -0,0 +1,160 @@
+services:
+  # One-shot setup (runs as root): generates /jwt/jwt.hex and chowns the
+  # nimbus-data volume to UID 1000 (the user Nimbus runs as inside its image).
+  # Without this chown Nimbus gets "Permission denied" on its data dir
+  # because docker creates fresh named volumes owned by root.
+  init:
+    image: alpine:latest
+    volumes:
+      - jwt:/jwt
+      - nimbus-data:/nimbus-data
+    command: >
+      sh -c '
+        set -e;
+        if [ ! -f /jwt/jwt.hex ]; then
+          apk add --no-cache openssl >/dev/null;
+          openssl rand -hex 32 | tr -d "\n" > /jwt/jwt.hex;
+          chmod 644 /jwt/jwt.hex;
+          echo "Generated /jwt/jwt.hex";
+        else
+          echo "jwt.hex already exists";
+        fi;
+        chown 1000:1000 /nimbus-data;
+        echo "Chowned /nimbus-data to 1000:1000";
+      '
+    restart: "no"
+
+  # One-shot: fetches a recent finalised checkpoint into the Nimbus data dir
+  # using the trustedNodeSync subcommand. Skipped if the data dir is already
+  # initialised, so subsequent compose-ups are no-ops.
+  nimbus-checkpoint-sync:
+    image: statusim/nimbus-eth2:multiarch-latest
+    depends_on:
+      init:
+        condition: service_completed_successfully
+    volumes:
+      - nimbus-data:/home/user/nimbus-eth2/build/data
+    entrypoint:
+      - sh
+      - -c
+      - |
+        if [ -d /home/user/nimbus-eth2/build/data/${NETWORK}/db ]; then
+          echo "Nimbus data dir already initialised — skipping checkpoint sync";
+          exit 0;
+        fi;
+        /home/user/nimbus-eth2/build/nimbus_beacon_node trustedNodeSync \
+          --network=${NETWORK} \
+          --data-dir=/home/user/nimbus-eth2/build/data/${NETWORK} \
+          --trusted-node-url=${TRUSTED_NODE_URL} \
+          --backfill=false
+    restart: "no"
+
+  # One-shot: downloads a pre-synced snapshot from snapshots.reth.rs into the
+  # Reth data dir. Turns a multi-day from-scratch sync into a ~hour download.
+  # Skipped if the data dir is already initialised — re-runs are no-ops.
+  # Privacy note: snapshots.reth.rs sees this download (operator existence).
+  # Subsequent eth_call traffic stays local.
+  reth-snapshot-init:
+    image: ghcr.io/paradigmxyz/reth:latest
+    depends_on:
+      init:
+        condition: service_completed_successfully
+    volumes:
+      - reth-data:/data
+    entrypoint:
+      - sh
+      - -c
+      - |
+        if [ -f /data/.snapshot-done ] || [ -d /data/db ]; then
+          echo "Reth data already initialised — skipping snapshot download";
+          exit 0;
+        fi;
+        echo "Downloading Reth ${NETWORK} --minimal snapshot...";
+        reth download --datadir /data --chain ${NETWORK} --minimal && \
+        touch /data/.snapshot-done && \
+        echo "Snapshot download complete"
+    restart: "no"
+
+  reth:
+    image: ghcr.io/paradigmxyz/reth:latest
+    depends_on:
+      reth-snapshot-init:
+        condition: service_completed_successfully
+    volumes:
+      - reth-data:/data
+      - jwt:/jwt:ro
+    ports:
+      # JSON-RPC for smp-server. Bound to loopback — put Caddy in front for remote access.
+      - "127.0.0.1:8545:8545"
+      # p2p (Ethereum network). Open these on your firewall for sync.
+      - "30303:30303/tcp"
+      - "30303:30303/udp"
+    command: >
+      node
+      --datadir /data
+      --chain ${NETWORK}
+      --minimal
+      --authrpc.jwtsecret /jwt/jwt.hex
+      --authrpc.addr 0.0.0.0 --authrpc.port 8551
+      --http
+      --http.addr 0.0.0.0 --http.port 8545
+      --http.api eth,net
+      --rpc.gascap 50000000
+      --port 30303
+      --discovery.port 30303
+    restart: unless-stopped
+
+  nimbus:
+    image: statusim/nimbus-eth2:multiarch-latest
+    depends_on:
+      nimbus-checkpoint-sync:
+        condition: service_completed_successfully
+    volumes:
+      - nimbus-data:/home/user/nimbus-eth2/build/data
+      - jwt:/jwt:ro
+    ports:
+      - "9000:9000/tcp"
+      - "9000:9000/udp"
+      - "127.0.0.1:5052:5052"
+    command: >
+      --network=${NETWORK}
+      --data-dir=/home/user/nimbus-eth2/build/data/${NETWORK}
+      --el=http://reth:8551
+      --jwt-secret=/jwt/jwt.hex
+      --non-interactive
+      --rest --rest-address=0.0.0.0 --rest-port=5052
+      --nat=${NAT:-any}
+    restart: unless-stopped
+
+  # SNRC REST resolver. Talks to reth on the compose-internal network,
+  # exposes /resolve and /health on 127.0.0.1:8000 by default. The
+  # smp-server points its [NAMES] resolver_endpoint at this URL.
+  # To change the host port, edit the LEFT side of the port mapping below.
+  resolver:
+    build:
+      context: ./service
+      dockerfile: Dockerfile
+    depends_on:
+      # reth's `service_started` is sufficient — the resolver tolerates
+      # eth_call failures gracefully (returns 502 with the error body), so
+      # starting before reth has finished snapshot replay just yields a few
+      # 502s until the chain is queryable. The upstream reth image doesn't
+      # ship a HEALTHCHECK, so we can't gate on healthy.
+      reth:
+        condition: service_started
+    environment:
+      SNRC_RPC: http://reth:8545
+      SNRC_BIND: 0.0.0.0
+      # Registry addresses cascade through the script's own defaults
+      # (mainnet `.testing`; `.simplex` unconfigured). Set explicitly here
+      # only if you're deploying against a different network or contract.
+      # SNRC_REGISTRY_TESTING: 0x...
+      # SNRC_REGISTRY_SIMPLEX: 0x...
+    ports:
+      - "127.0.0.1:8000:8000"
+    restart: unless-stopped
+
+volumes:
+  reth-data:
+  nimbus-data:
+  jwt:

scripts/resolver/service/Dockerfile

@@ -0,0 +1,48 @@
+# syntax=docker/dockerfile:1.7
+# ---------- builder ----------
+# Use the official uv image (Astral) on top of a slim Python base.
+# uv resolves and installs the lockfile-free pyproject.toml in seconds and
+# produces a portable .venv we can copy into the runtime stage.
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim AS builder
+
+ENV UV_LINK_MODE=copy \
+    UV_COMPILE_BYTECODE=1 \
+    UV_PYTHON_DOWNLOADS=never \
+    UV_NO_PROGRESS=1
+
+WORKDIR /app
+
+# Install deps first (separate layer) — script edits won't bust this cache.
+COPY pyproject.toml ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --no-dev --no-install-project
+
+# Script is added after the dep layer for cache friendliness.
+COPY snrc-resolve.py ./
+
+# ---------- runtime ----------
+# Slim runtime — only the venv + script. No uv, no apt.
+FROM python:3.13-slim AS runtime
+
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PATH="/app/.venv/bin:$PATH"
+
+# Non-root user (matches resolver privacy posture: it has no need for root).
+RUN groupadd --system --gid 10001 snrc && \
+    useradd  --system --uid 10001 --gid snrc --no-create-home --shell /usr/sbin/nologin snrc
+
+WORKDIR /app
+COPY --from=builder --chown=snrc:snrc /app /app
+
+USER snrc:snrc
+
+EXPOSE 8000
+
+# Liveness check hits the script's own /health route. ThreadingHTTPServer is
+# fast enough that 3s is generous for a localhost probe; restart if it stops
+# responding entirely.
+HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
+    CMD ["python", "-c", "import urllib.request, sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=3).status == 200 else 1)"]
+
+ENTRYPOINT ["python", "snrc-resolve.py"]

scripts/resolver/service/pyproject.toml

@@ -0,0 +1,13 @@
+[project]
+name = "snrc-resolve"
+version = "0.1.0"
+description = "SimpleX Namespace (SNRC) resolver — REST API over ENS-shaped Ethereum registries"
+readme = "README.md"
+requires-python = ">=3.11"
+license = "AGPL-3.0-only"
+dependencies = [
+  "eth-hash[pycryptodome]>=0.7",
+]
+
+[tool.uv]
+package = false

scripts/resolver/service/snrc-resolve.py

@@ -0,0 +1,517 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.11"
+# dependencies = [
+#   "eth-hash[pycryptodome]>=0.7",
+# ]
+# ///
+"""SimpleX Namespace (SNRC) resolver — REST API.
+
+Resolves names like `alice.testing` / `bob.simplex` against the SNRC
+deployment on Ethereum mainnet (or any compatible ENS-shaped registry)
+and returns a flat JSON document with these fields:
+
+  name, nickname, website, location,
+  simplexContact, simplexChannel,    -- list[str], primary first
+  eth, btc, xmr, dot,
+  owner, resolver
+
+`simplexContact` and `simplexChannel` are arrays so a name can advertise
+multiple SMP servers for redundancy. Clients SHOULD try the URLs in the
+order returned. The on-chain text record stores them as a single
+`LINK_SEPARATOR` (`;`)-joined string; this resolver splits and trims into a list.
+
+All keys are valid Haskell record-field identifiers (lowercase initial,
+no dots), so consumers can derive aeson FromJSON instances directly
+without a key-rewriting layer.
+
+Usage:
+  ./snrc-resolve.py                    # serve on :8000
+
+  curl -s http://127.0.0.1:8000/resolve/foobar.testing | jq .
+  curl -s http://127.0.0.1:8000/health
+
+Environment:
+  SNRC_RPC               JSON-RPC endpoint (default: http://127.0.0.1:8545)
+  SNRC_REGISTRY_TESTING  ENSRegistry for the .testing deployment
+                         (default: mainnet,
+                          0x58fc46996d975c57883564648bda5206d1a0102b)
+  SNRC_REGISTRY_SIMPLEX  ENSRegistry for the .simplex deployment
+                         (default: empty — TLD not yet deployed)
+  SNRC_PORT              Listen port (default: 8000)
+  SNRC_BIND              Bind address (default: 0.0.0.0)
+
+Each TLD is a separate SNRC deployment with its own ENSRegistry; the
+resolver dispatches by the queried name's rightmost label.
+
+Dependencies are declared inline (PEP 723) at the top of this file. Run with:
+  uv run snrc-resolve.py          # uv resolves & caches deps; one-line setup
+  python snrc-resolve.py          # if eth-hash[pycryptodome] is already installed
+
+Addresses are returned in each chain's canonical presentation:
+  eth  EIP-55 mixed-case checksummed hex      (e.g. 0xEa65A0…1572)
+  btc  bech32(m) for segwit/taproot, base58check for P2PKH/P2SH
+       (e.g. bc1q…  /  1A1zP1…)
+  dot  SS58 with Polkadot network prefix 0    (e.g. 15oF4u…)
+  xmr  Monero base58                          (e.g. 4Aux5y…)
+Unrecognised payloads fall back to `0x`-prefixed raw hex.
+"""
+
+import hashlib
+import json
+import os
+import sys
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from urllib.parse import unquote, urlparse
+from urllib.request import Request, urlopen
+
+from eth_hash.auto import keccak
+
+RPC = os.environ.get("SNRC_RPC", "http://127.0.0.1:8545")
+BIND = os.environ.get("SNRC_BIND", "0.0.0.0")
+PORT = int(os.environ.get("SNRC_PORT", "8000"))
+
+# Each TLD is its own SNRC deployment with its own ENSRegistry. Dispatch
+# happens on the rightmost label of the queried name. Empty / unset means
+# "not deployed" — requests for that TLD return 400 with a clear error.
+# `... or "..."` makes the script's defaults the single source of truth:
+# unset AND empty-string both fall through to the literal. docker-compose
+# can therefore pass `SNRC_REGISTRY_TESTING=${SNRC_REGISTRY_TESTING:-}`
+# without duplicating the registry address.
+REGISTRIES = {
+    "testing": os.environ.get("SNRC_REGISTRY_TESTING", "")
+    or "0x58fc46996d975c57883564648bda5206d1a0102b",  # mainnet .testing
+    "simplex": os.environ.get("SNRC_REGISTRY_SIMPLEX", ""),  # not deployed yet
+}
+
+# SLIP-44 coin types (https://github.com/satoshilabs/slips/blob/master/slip-0044.md)
+COIN_ETH = 60
+COIN_BTC = 0
+COIN_XMR = 128
+COIN_DOT = 354
+
+ZERO_ADDR = "0x0000000000000000000000000000000000000000"
+
+
+# ---------- RPC + ABI helpers (mirrors ens-lookup.py shape) ----------
+
+def rpc(method, params):
+    body = json.dumps(
+        {"jsonrpc": "2.0", "method": method, "params": params, "id": 1}
+    ).encode()
+    # Set a non-default User-Agent; Cloudflare-fronted public RPCs (drpc,
+    # publicnode, etc.) reject `Python-urllib/3.x` with 403.
+    req = Request(
+        RPC,
+        data=body,
+        headers={
+            "Content-Type": "application/json",
+            "User-Agent": "snrc-resolve/1.0",
+        },
+    )
+    res = json.loads(urlopen(req, timeout=15).read())
+    if "error" in res:
+        raise RuntimeError(res["error"])
+    return res["result"]
+
+
+def namehash(name: str) -> bytes:
+    node = b"\x00" * 32
+    if name:
+        for label in reversed(name.split(".")):
+            node = keccak(node + keccak(label.encode()))
+    return node
+
+
+def selector(signature: str) -> str:
+    return "0x" + keccak(signature.encode())[:4].hex()
+
+
+def eth_call(to: str, data: str) -> str:
+    return rpc("eth_call", [{"to": to, "data": data}, "latest"])
+
+
+def decode_address(hex_data: str) -> str:
+    return "0x" + hex_data[-40:]
+
+
+def decode_bytes(hex_data: str) -> bytes:
+    raw = bytes.fromhex(hex_data[2:] if hex_data.startswith("0x") else hex_data)
+    if len(raw) < 64:
+        return b""
+    length = int.from_bytes(raw[32:64], "big")
+    return raw[64:64 + length]
+
+
+def encode_text_call(node: bytes, key: str) -> str:
+    sel = selector("text(bytes32,string)")
+    head = node.hex() + (0x40).to_bytes(32, "big").hex()
+    key_bytes = key.encode()
+    body = len(key_bytes).to_bytes(32, "big").hex() + key_bytes.hex()
+    body += "00" * ((-len(key_bytes)) % 32)
+    return sel + head + body
+
+
+def text(resolver: str, node: bytes, key: str) -> str:
+    raw = decode_bytes(eth_call(resolver, encode_text_call(node, key)))
+    return raw.decode("utf-8", errors="replace") if raw else ""
+
+
+def encode_addr_multicoin_call(node: bytes, coin_type: int) -> str:
+    """ENSIP-9 addr(bytes32 node, uint256 coinType) — both static, no offsets."""
+    return (
+        selector("addr(bytes32,uint256)")
+        + node.hex()
+        + coin_type.to_bytes(32, "big").hex()
+    )
+
+
+def addr_multicoin(resolver: str, node: bytes, coin_type: int):
+    """Read ENSIP-9 raw bytes for `coinType`, then encode to that chain's
+    canonical presentation form. Falls back to `0x`-prefixed hex if the
+    payload doesn't match any recognised on-chain shape. Returns None when
+    the record is unset."""
+    try:
+        raw = decode_bytes(eth_call(resolver, encode_addr_multicoin_call(node, coin_type)))
+    except RuntimeError:
+        return None
+    if not raw:
+        return None
+    # An all-zero payload is the ENS convention for "unset" — many tools
+    # write 20 zero bytes for coinType=60 instead of clearing the slot.
+    # Treat it as null so the response doesn't surface a zero address.
+    if raw == b"\x00" * len(raw):
+        return None
+    encoder = COIN_ENCODERS.get(coin_type)
+    if encoder is None:
+        return "0x" + raw.hex()
+    try:
+        return encoder(raw) or ("0x" + raw.hex())
+    except Exception:
+        return "0x" + raw.hex()
+
+
+# ---------- Coin-specific address encoders ----------
+# Each takes raw bytes as stored under ENSIP-9 and returns the canonical
+# user-facing string for that chain (EIP-55 for ETH, bech32/base58check
+# for BTC, SS58 for DOT, Monero-base58 for XMR). All stdlib + eth_hash.
+
+
+B58_ALPHA = "123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz"
+
+
+def _b58_encode(b: bytes) -> str:
+    n = int.from_bytes(b, "big")
+    out = ""
+    while n:
+        n, r = divmod(n, 58)
+        out = B58_ALPHA[r] + out
+    # leading zero bytes → leading '1's
+    pad = len(b) - len(b.lstrip(b"\x00"))
+    return "1" * pad + out
+
+
+def _b58check_encode(payload: bytes) -> str:
+    """Base58Check used by BTC legacy/P2SH: payload + dSHA256(payload)[:4]."""
+    chk = hashlib.sha256(hashlib.sha256(payload).digest()).digest()[:4]
+    return _b58_encode(payload + chk)
+
+
+# ---- Bech32 / Bech32m (BIP-173 / BIP-350) ----
+
+_BECH32_CHARSET = "qpzry9x8gf2tvdw0s3jn54khce6mua7l"
+_BECH32_GEN = [0x3B6A57B2, 0x26508E6D, 0x1EA119FA, 0x3D4233DD, 0x2A1462B3]
+
+
+def _bech32_polymod(values):
+    chk = 1
+    for v in values:
+        b = chk >> 25
+        chk = ((chk & 0x1FFFFFF) << 5) ^ v
+        for i in range(5):
+            if (b >> i) & 1:
+                chk ^= _BECH32_GEN[i]
+    return chk
+
+
+def _bech32_hrp_expand(hrp):
+    return [ord(c) >> 5 for c in hrp] + [0] + [ord(c) & 31 for c in hrp]
+
+
+def _bech32_create_checksum(hrp, data, spec):
+    const = 1 if spec == "bech32" else 0x2BC830A3  # bech32m
+    values = _bech32_hrp_expand(hrp) + data + [0] * 6
+    polymod = _bech32_polymod(values) ^ const
+    return [(polymod >> 5 * (5 - i)) & 31 for i in range(6)]
+
+
+def _bech32_encode(hrp, data, spec):
+    combined = data + _bech32_create_checksum(hrp, data, spec)
+    return hrp + "1" + "".join(_BECH32_CHARSET[d] for d in combined)
+
+
+def _convertbits(data, frombits, tobits, pad=True):
+    acc = 0
+    bits = 0
+    ret = []
+    maxv = (1 << tobits) - 1
+    max_acc = (1 << (frombits + tobits - 1)) - 1
+    for value in data:
+        if value < 0 or (value >> frombits):
+            return None
+        acc = ((acc << frombits) | value) & max_acc
+        bits += frombits
+        while bits >= tobits:
+            bits -= tobits
+            ret.append((acc >> bits) & maxv)
+    if pad and bits:
+        ret.append((acc << (tobits - bits)) & maxv)
+    elif not pad and (bits >= frombits or ((acc << (tobits - bits)) & maxv)):
+        return None
+    return ret
+
+
+def _segwit_encode(hrp: str, witver: int, witprog: bytes) -> str:
+    spec = "bech32" if witver == 0 else "bech32m"
+    data = [witver] + _convertbits(list(witprog), 8, 5)
+    return _bech32_encode(hrp, data, spec)
+
+
+# ---- BTC scriptPubKey → address ----
+# ENSIP-9 stores the raw output script. Dispatch by length + opcode prefix.
+
+def _btc_encode(raw: bytes) -> str | None:
+    hrp = "bc"  # mainnet
+    if len(raw) == 25 and raw[:3] == b"\x76\xa9\x14" and raw[23:25] == b"\x88\xac":
+        return _b58check_encode(b"\x00" + raw[3:23])  # P2PKH
+    if len(raw) == 23 and raw[:2] == b"\xa9\x14" and raw[22:23] == b"\x87":
+        return _b58check_encode(b"\x05" + raw[2:22])  # P2SH
+    if len(raw) == 22 and raw[:2] == b"\x00\x14":
+        return _segwit_encode(hrp, 0, raw[2:22])  # P2WPKH
+    if len(raw) == 34 and raw[:2] == b"\x00\x20":
+        return _segwit_encode(hrp, 0, raw[2:34])  # P2WSH
+    if len(raw) == 34 and raw[:2] == b"\x51\x20":
+        return _segwit_encode(hrp, 1, raw[2:34])  # P2TR
+    return None
+
+
+# ---- Polkadot SS58 ----
+# Per SS58 spec: base58( prefix_byte + pubkey + blake2b-512("SS58PRE" + body)[:2] )
+# Polkadot mainnet uses network prefix 0 (single byte); Kusama uses 2.
+
+_SS58_PRE = b"SS58PRE"
+
+
+def _ss58_encode(pubkey: bytes, network_prefix: int = 0) -> str:
+    if len(pubkey) != 32:
+        return None
+    body = bytes([network_prefix]) + pubkey
+    checksum = hashlib.blake2b(_SS58_PRE + body, digest_size=64).digest()[:2]
+    return _b58_encode(body + checksum)
+
+
+def _dot_encode(raw: bytes) -> str | None:
+    return _ss58_encode(raw, network_prefix=0)
+
+
+# ---- Monero base58 ----
+# Monero base58 encodes in 8-byte blocks; each full block → 11 chars, partial
+# block sizes per fixed table. Alphabet is identical to Bitcoin's.
+
+_XMR_BLOCK_SIZES = [0, 2, 3, 5, 6, 7, 9, 10, 11]
+
+
+def _xmr_encode(raw: bytes) -> str:
+    out = []
+    for i in range(0, len(raw), 8):
+        chunk = raw[i:i + 8]
+        n = int.from_bytes(chunk, "big")
+        width = 11 if len(chunk) == 8 else _XMR_BLOCK_SIZES[len(chunk)]
+        block = []
+        for _ in range(width):
+            n, r = divmod(n, 58)
+            block.append(B58_ALPHA[r])
+        out.append("".join(reversed(block)))
+    return "".join(out)
+
+
+# ---- ETH EIP-55 mixed-case checksum ----
+
+def _eth_encode(raw: bytes) -> str | None:
+    if len(raw) != 20:
+        return None
+    hex_addr = raw.hex()
+    hash_hex = keccak(hex_addr.encode()).hex()
+    return "0x" + "".join(
+        c.upper() if c.isalpha() and int(hash_hex[i], 16) >= 8 else c
+        for i, c in enumerate(hex_addr)
+    )
+
+
+COIN_ENCODERS = {
+    COIN_ETH: _eth_encode,
+    COIN_BTC: _btc_encode,
+    COIN_XMR: _xmr_encode,
+    COIN_DOT: _dot_encode,
+}
+
+
+# ---------- Resolution logic ----------
+
+# Text-record keys we read from the resolver. Surfaced under the response
+# field names listed in the docstring above. `name` and `description` are
+# common ENS fallbacks for a human-readable nickname.
+TEXT_KEYS = [
+    "name",
+    "nickname",
+    "description",
+    "url",
+    "location",
+    "simplex.contact",
+    "simplex.channel",
+]
+
+
+# Separator that joins the SMP-server URL list inside a simplex.contact /
+# simplex.channel text record. MUST match SIMPLEX_LINK_SEPARATOR in the dApp
+# (ens-app-v3 src/constants/simplex.ts) — the two sides decode the same record.
+LINK_SEPARATOR = ";"
+
+
+def split_links(value: str) -> list:
+    """Split a separator-joined text record into an ordered list of entries.
+
+    Trims whitespace around each element and drops empties so trailing
+    separators, doubled separators, and all-whitespace inputs all yield clean
+    output. Single-value records yield a 1-element list; empty inputs
+    yield `[]`. Used for `simplex.contact` / `simplex.channel`, which
+    store one-or-more SMP-server URLs as a single `LINK_SEPARATOR`-joined string.
+    """
+    return [item.strip() for item in value.split(LINK_SEPARATOR) if item.strip()]
+
+
+def resolve(name: str):
+    tld = name.rsplit(".", 1)[-1]
+    registry = REGISTRIES.get(tld)
+    if not registry:
+        configured = [k for k, v in REGISTRIES.items() if v]
+        return 400, {
+            "name": name,
+            "error": f"TLD '{tld}' is not configured on this resolver",
+            "configured_tlds": configured,
+        }
+
+    node = namehash(name)
+    node_hex = node.hex()
+
+    resolver_raw = eth_call(registry, selector("resolver(bytes32)") + node_hex)
+    resolver_addr = decode_address(resolver_raw)
+    if resolver_addr == ZERO_ADDR:
+        return 404, {"name": name, "error": "no resolver set for this name"}
+
+    owner_raw = eth_call(registry, selector("owner(bytes32)") + node_hex)
+    owner = decode_address(owner_raw)
+
+    texts = {}
+    for k in TEXT_KEYS:
+        try:
+            v = text(resolver_addr, node, k)
+        except RuntimeError:
+            v = ""
+        if v:
+            texts[k] = v
+
+    # The user-facing "nickname" prefers an explicit `nickname` record,
+    # falls back to `name`, then `description` (ENSIP-5 convention).
+    nickname = texts.get("nickname") or texts.get("name") or texts.get("description") or ""
+
+    # Keys chosen to be valid Haskell record-field identifiers (lowercase
+    # initial, no dots) so consumers can derive aeson FromJSON instances
+    # without a key-rewriting layer. On-chain text-record names still
+    # use the ENSIP-5 dot convention (e.g. "simplex.contact") — only the
+    # resolver's JSON surface camelCases them.
+    return 200, {
+        "name": name,
+        "nickname": nickname,
+        "website": texts.get("url", ""),
+        "location": texts.get("location", ""),
+        "simplexContact": split_links(texts.get("simplex.contact", "")),
+        "simplexChannel": split_links(texts.get("simplex.channel", "")),
+        "eth": addr_multicoin(resolver_addr, node, COIN_ETH),
+        "btc": addr_multicoin(resolver_addr, node, COIN_BTC),
+        "xmr": addr_multicoin(resolver_addr, node, COIN_XMR),
+        "dot": addr_multicoin(resolver_addr, node, COIN_DOT),
+        "owner": owner,
+        "resolver": resolver_addr,
+    }
+
+
+# ---------- HTTP layer ----------
+
+class Handler(BaseHTTPRequestHandler):
+    def do_GET(self):  # noqa: N802 - http.server contract
+        path = urlparse(self.path).path
+        parts = [unquote(p) for p in path.split("/") if p]
+
+        if parts == ["health"]:
+            self._respond(
+                200,
+                {"ok": True, "rpc": RPC, "registries": REGISTRIES},
+            )
+            return
+
+        if len(parts) == 2 and parts[0] == "resolve":
+            name = parts[1].strip().lower()
+            if not name or "." not in name:
+                self._respond(
+                    400,
+                    {
+                        "error": "expected fully-qualified name, e.g. /resolve/alice.testing",
+                        "got": name,
+                    },
+                )
+                return
+            try:
+                status, body = resolve(name)
+            except Exception as e:  # surface upstream errors as 502
+                status, body = 502, {"name": name, "error": f"{type(e).__name__}: {e}"}
+            self._respond(status, body)
+            return
+
+        self._respond(
+            404,
+            {"error": "not found", "routes": ["/health", "/resolve/<name>"]},
+        )
+
+    def _respond(self, status: int, body: dict):
+        data = json.dumps(body, indent=2).encode()
+        self.send_response(status)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(data)))
+        self.end_headers()
+        self.wfile.write(data)
+
+    def log_message(self, fmt, *args):
+        # Quiet the default per-request access log; route to stderr in one line.
+        sys.stderr.write(f"{self.address_string()} - {fmt % args}\n")
+
+
+def main():
+    server = ThreadingHTTPServer((BIND, PORT), Handler)
+    sys.stderr.write(
+        f"snrc-resolve listening on {BIND}:{PORT}\n"
+        f"  RPC = {RPC}\n"
+        f"  Registries:\n"
+    )
+    for tld, addr in REGISTRIES.items():
+        sys.stderr.write(f"    .{tld:<8s} = {addr or '(not configured)'}\n")
+    sys.stderr.write("  GET /resolve/<name>   GET /health\n")
+    try:
+        server.serve_forever()
+    except KeyboardInterrupt:
+        sys.stderr.write("\nshutting down\n")
+        server.server_close()
+
+
+if __name__ == "__main__":
+    main()

scripts/resolver/service/test_snrc_resolve.py

@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+"""Unit tests for snrc-resolve helpers.
+
+Run with `python3 -m unittest scripts/resolver/service/test_snrc_resolve.py`.
+"""
+
+import importlib.util
+import os
+import unittest
+
+# snrc-resolve.py has a hyphen, so import it via importlib instead of `import`.
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_SPEC = importlib.util.spec_from_file_location(
+    "snrc_resolve", os.path.join(_HERE, "snrc-resolve.py")
+)
+snrc = importlib.util.module_from_spec(_SPEC)
+_SPEC.loader.exec_module(snrc)
+
+
+class SplitLinksTests(unittest.TestCase):
+    """`split_links` decodes the multi-URL convention for simplex.contact /
+    simplex.channel text records. Reuses the same rule the dApp's
+    `parseSimplexUrls` uses (separator `;`), so the two sides round-trip
+    cleanly."""
+
+    def test_empty_string_yields_empty_list(self):
+        self.assertEqual(snrc.split_links(""), [])
+
+    def test_whitespace_only_yields_empty_list(self):
+        self.assertEqual(snrc.split_links("   "), [])
+        self.assertEqual(snrc.split_links(" ; ; "), [])
+
+    def test_single_url_yields_singleton_list(self):
+        self.assertEqual(
+            snrc.split_links("https://smp16.simplex.im/a#H1"),
+            ["https://smp16.simplex.im/a#H1"],
+        )
+
+    def test_two_urls_split_on_separator(self):
+        self.assertEqual(
+            snrc.split_links(
+                "https://smp16.simplex.im/a#H1;https://smp19.simplex.im/a#H1"
+            ),
+            [
+                "https://smp16.simplex.im/a#H1",
+                "https://smp19.simplex.im/a#H1",
+            ],
+        )
+
+    def test_whitespace_around_separators_is_trimmed(self):
+        self.assertEqual(
+            snrc.split_links(
+                "  https://smp16.simplex.im/a#H1 ;\thttps://smp19.simplex.im/a#H1 "
+            ),
+            [
+                "https://smp16.simplex.im/a#H1",
+                "https://smp19.simplex.im/a#H1",
+            ],
+        )
+
+    def test_trailing_separator_does_not_produce_empty_entry(self):
+        self.assertEqual(
+            snrc.split_links("https://smp16.simplex.im/a#H1;"),
+            ["https://smp16.simplex.im/a#H1"],
+        )
+
+    def test_doubled_separator_does_not_produce_empty_entry(self):
+        self.assertEqual(
+            snrc.split_links(
+                "https://smp16.simplex.im/a#H1;;https://smp19.simplex.im/a#H1"
+            ),
+            [
+                "https://smp16.simplex.im/a#H1",
+                "https://smp19.simplex.im/a#H1",
+            ],
+        )
+
+    def test_order_is_preserved(self):
+        self.assertEqual(
+            snrc.split_links("c;a;b"),
+            ["c", "a", "b"],
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()

scripts/resolver/tools/ens-lookup.py

@@ -0,0 +1,168 @@
+#!/usr/bin/env python3
+"""Resolve an ENS name via local Reth (the same shape SNRC will use).
+
+Usage:
+  ./ens-lookup.py                     # defaults to simplexchat.eth
+  ./ens-lookup.py vitalik.eth
+  ./ens-lookup.py corevo.eth
+
+Requires:  pip install --break-system-packages 'eth-hash[pycryptodome]'
+"""
+
+import base64
+import json
+import sys
+from urllib.request import Request, urlopen
+
+from eth_hash.auto import keccak
+
+RPC = "http://127.0.0.1:8545"
+# ENS Registry (current, post-2020 migration)
+ENS_REGISTRY = "0x00000000000C2E074eC69A0dFb2997BA6C7d2e1e"
+
+
+def rpc(method, params):
+    body = json.dumps({"jsonrpc": "2.0", "method": method, "params": params, "id": 1}).encode()
+    req = Request(RPC, data=body, headers={"Content-Type": "application/json"})
+    res = json.loads(urlopen(req, timeout=15).read())
+    if "error" in res:
+        raise RuntimeError(res["error"])
+    return res["result"]
+
+
+def namehash(name: str) -> bytes:
+    """ENS namehash — recursive keccak256 over reversed labels."""
+    node = b"\x00" * 32
+    if name:
+        for label in reversed(name.split(".")):
+            node = keccak(node + keccak(label.encode()))
+    return node
+
+
+def selector(signature: str) -> str:
+    return "0x" + keccak(signature.encode())[:4].hex()
+
+
+def eth_call(to: str, data: str) -> str:
+    return rpc("eth_call", [{"to": to, "data": data}, "latest"])
+
+
+def decode_address(hex_data: str) -> str:
+    return "0x" + hex_data[-40:]
+
+
+def decode_bytes(hex_data: str) -> bytes:
+    raw = bytes.fromhex(hex_data[2:] if hex_data.startswith("0x") else hex_data)
+    if len(raw) < 64:
+        return b""
+    length = int.from_bytes(raw[32:64], "big")
+    return raw[64:64 + length]
+
+
+def encode_text_call(node: bytes, key: str) -> str:
+    """ABI-encode text(bytes32 node, string key). String arg is dynamic:
+    offset (=0x40) + length + right-padded data."""
+    sel = selector("text(bytes32,string)")
+    head = node.hex() + (0x40).to_bytes(32, "big").hex()
+    key_bytes = key.encode()
+    body = len(key_bytes).to_bytes(32, "big").hex() + key_bytes.hex()
+    # right-pad to 32-byte boundary
+    pad = (-len(key_bytes)) % 32
+    body += "00" * pad
+    return sel + head + body
+
+
+def text(resolver: str, node: bytes, key: str) -> str:
+    raw = decode_bytes(eth_call(resolver, encode_text_call(node, key)))
+    return raw.decode("utf-8", errors="replace") if raw else ""
+
+
+# Common ENS text keys (ENSIP-5). Resolvers may return empty for any of these.
+TEXT_KEYS = [
+    "url",
+    "avatar",
+    "description",
+    "email",
+    "notice",
+    "keywords",
+    "com.twitter",
+    "com.github",
+    "com.discord",
+    "org.telegram",
+    "io.keybase",
+    "xyz.farcaster",
+]
+
+
+def decode_contenthash(raw: bytes) -> str:
+    """ENS contenthash → human-readable URI (best-effort)."""
+    if not raw:
+        return "(empty)"
+    # Multicodec prefixes:
+    #   0xe301 = ipfs-ns + dag-pb (CIDv0/v1)
+    #   0xe501 = ipns-ns
+    #   0xe40101701b... = swarm
+    if raw[:2] == b"\xe3\x01":
+        cid_bytes = raw[2:]
+        # Base32 lowercase + 'b' prefix per CIDv1 spec
+        b32 = base64.b32encode(cid_bytes).decode().lower().rstrip("=")
+        return f"ipfs://b{b32}"
+    if raw[:2] == b"\xe5\x01":
+        cid_bytes = raw[2:]
+        b32 = base64.b32encode(cid_bytes).decode().lower().rstrip("=")
+        return f"ipns://b{b32}"
+    return "0x" + raw.hex()
+
+
+def main():
+    name = sys.argv[1] if len(sys.argv) > 1 else "simplexchat.eth"
+
+    print(f"  name:       {name}")
+    node = namehash(name)
+    print(f"  namehash:   0x{node.hex()}")
+
+    # 1. Ask the registry which resolver is responsible for this name
+    resolver_data = selector("resolver(bytes32)") + node.hex()
+    resolver_raw = eth_call(ENS_REGISTRY, resolver_data)
+    resolver = decode_address(resolver_raw)
+    print(f"  resolver:   {resolver}")
+    if resolver == "0x0000000000000000000000000000000000000000":
+        print("  → no resolver set for this name")
+        return
+
+    node_hex = node.hex()
+
+    # 2. Ask the resolver for the address
+    try:
+        addr = decode_address(eth_call(resolver, selector("addr(bytes32)") + node_hex))
+        print(f"  address:    {addr}")
+    except Exception as e:
+        print(f"  address:    (error: {e})")
+
+    # 3. Ask the resolver for the content hash (IPFS pointer)
+    try:
+        ch = decode_bytes(eth_call(resolver, selector("contenthash(bytes32)") + node_hex))
+        print(f"  contenthash: {decode_contenthash(ch)}")
+    except Exception as e:
+        print(f"  contenthash: (not supported: {e})")
+
+    # 4. Owner from the registry
+    try:
+        owner = decode_address(eth_call(ENS_REGISTRY, selector("owner(bytes32)") + node_hex))
+        print(f"  owner:      {owner}")
+    except Exception as e:
+        print(f"  owner:      (error: {e})")
+
+    # 5. Text records (EIP-634). Print only the non-empty ones.
+    print("  text records:")
+    for key in TEXT_KEYS:
+        try:
+            v = text(resolver, node, key)
+            if v:
+                print(f"    {key:<16s} {v}")
+        except Exception as e:
+            print(f"    {key:<16s} (error: {e})")
+
+
+if __name__ == "__main__":
+    main()

scripts/resolver/tools/progress.py

@@ -0,0 +1,246 @@
+#!/usr/bin/env python3
+"""Sync progress for the Reth + Nimbus stack.
+
+Usage:
+  ./progress.py           # continuous (Ctrl-C to exit, auto-exits when synced)
+  ./progress.py --once    # single snapshot
+
+Requires Nimbus REST port exposed at 127.0.0.1:5052 (add --rest flag in compose).
+"""
+
+import json
+import sys
+import time
+from collections import deque
+from datetime import timedelta
+from urllib.error import URLError
+from urllib.request import Request, urlopen
+
+RETH = "http://127.0.0.1:8545"
+NIMBUS = "http://127.0.0.1:5052"
+INTERVAL = 5
+WINDOW = 60
+BAR_W = 40
+
+# ANSI helpers
+def c(s, code): return f"\033[{code}m{s}\033[0m"
+GREEN, YELLOW, RED, DIM, BOLD = "32", "33", "31", "2;37", "1"
+
+
+def rpc(method):
+    body = json.dumps({"jsonrpc": "2.0", "method": method, "params": [], "id": 1}).encode()
+    req = Request(RETH, data=body, headers={"Content-Type": "application/json"})
+    return json.loads(urlopen(req, timeout=5).read())["result"]
+
+
+def get_reth():
+    try:
+        r = rpc("eth_syncing")
+        try:
+            peers = int(rpc("net_peerCount"), 16)
+        except Exception:
+            peers = -1            # net namespace not exposed
+        if r is False:
+            head = int(rpc("eth_blockNumber"), 16)
+            return {"state": "synced", "current": head, "target": head, "peers": peers,
+                    "stage": None, "stages": {}, "err": None}
+        current = int(r["currentBlock"], 16)
+        highest = int(r["highestBlock"], 16)
+        # Build stage map (name -> block).
+        stages = {s["name"]: int(s["block"], 16) for s in r.get("stages", [])}
+        active_stages = {k: v for k, v in stages.items() if v > 0}
+        # Headers download phase: nothing has progressed yet.
+        if current == 0 and highest == 0 and not active_stages:
+            return {"state": "headers", "current": 0, "target": 0, "peers": peers,
+                    "stage": "Headers", "stages": stages, "err": None}
+        # Derive progress from the stages pipeline.
+        # Bottleneck (rate-limiting stage) = stage with lowest non-zero block.
+        # Target = leading stage block (typically Headers = chain tip).
+        # Reth's top-level currentBlock/highestBlock are unreliable during initial
+        # sync (often 0 until execution stage runs), so prefer stages-derived values.
+        if active_stages:
+            bottleneck = min(active_stages, key=active_stages.get)
+            stage_current = active_stages[bottleneck]
+            stage_target = max(stages.values()) if stages else 0
+            # Trust the stages-derived values if highest is unset or stages tip is higher.
+            if highest <= 0 or stage_target > highest:
+                current = stage_current
+                highest = stage_target
+            elif current <= 0:
+                current = stage_current
+        else:
+            bottleneck = None
+        return {"state": "syncing", "current": current, "target": highest,
+                "peers": peers, "stage": bottleneck, "stages": stages, "err": None}
+    except URLError as e:
+        return {"state": "down", "current": 0, "target": 0, "peers": 0,
+                "stage": None, "stages": {}, "err": str(e.reason)}
+    except Exception as e:
+        return {"state": "error", "current": 0, "target": 0, "peers": 0,
+                "stage": None, "stages": {}, "err": str(e)}
+
+
+def get_nimbus():
+    try:
+        d = json.loads(urlopen(f"{NIMBUS}/eth/v1/node/syncing", timeout=5).read())["data"]
+        peers_d = json.loads(urlopen(f"{NIMBUS}/eth/v1/node/peer_count", timeout=5).read())["data"]
+        head = int(d["head_slot"])
+        dist = int(d["sync_distance"])
+        peers = int(peers_d.get("connected", "0"))
+        return {"state": "synced" if not d["is_syncing"] else "syncing",
+                "current": head, "target": head + dist, "peers": peers,
+                "optimistic": bool(d.get("is_optimistic", False)),
+                "el_offline": bool(d.get("el_offline", False)),
+                "err": None}
+    except URLError as e:
+        return {"state": "down", "current": 0, "target": 0, "peers": 0,
+                "optimistic": False, "el_offline": False, "err": str(e.reason)}
+    except Exception as e:
+        return {"state": "error", "current": 0, "target": 0, "peers": 0,
+                "optimistic": False, "el_offline": False, "err": str(e)}
+
+
+def format_num(n): return f"{n:,}"
+
+
+def format_eta(seconds):
+    if seconds is None: return "?"
+    if seconds < 0: return "?"
+    if seconds < 60: return f"{int(seconds)}s"
+    if seconds < 3600:
+        return f"{int(seconds // 60)}m {int(seconds % 60)}s"
+    if seconds < 86400:
+        return f"{int(seconds // 3600)}h {int((seconds % 3600) // 60)}m"
+    return f"{int(seconds // 86400)}d {int((seconds % 86400) // 3600)}h"
+
+
+def rate_per_sec(history):
+    if len(history) < 2: return None
+    t0, c0 = history[0]
+    t1, c1 = history[-1]
+    if t1 <= t0: return None
+    return (c1 - c0) / (t1 - t0)
+
+
+def eta_seconds(history, target):
+    r = rate_per_sec(history)
+    if r is None or r <= 0: return None
+    remaining = target - history[-1][1]
+    if remaining <= 0: return 0
+    return remaining / r
+
+
+def progress_bar(pct):
+    pct = max(0.0, min(100.0, pct))
+    filled = int(pct / 100 * BAR_W)
+    return c("█" * filled, GREEN) + c("░" * (BAR_W - filled), DIM)
+
+
+def peers_label(peers):
+    if peers < 0:
+        return c("· peers unknown (enable net namespace)", DIM)
+    return c(f"· {peers} peers", DIM)
+
+
+def stages_summary(stages):
+    """One-line view: stages that have progressed, with their block numbers."""
+    if not stages:
+        return ""
+    advanced = [(n, b) for n, b in stages.items() if b > 0]
+    if not advanced:
+        return c("  stages: all 0 (headers downloading)", DIM)
+    advanced.sort(key=lambda kv: kv[1], reverse=True)
+    parts = [f"{n}={format_num(b)}" for n, b in advanced[:4]]
+    return c("  stages: " + ", ".join(parts), DIM)
+
+
+def render_one(name, x, hist):
+    state = x["state"]
+    peers = x.get("peers", 0)
+    extras = []
+    if name == "Nimbus":
+        if x.get("optimistic"):
+            extras.append(c("(optimistic head — Reth not yet verifying)", YELLOW))
+        if x.get("el_offline"):
+            extras.append(c("⚠ EL OFFLINE", RED))
+    if state == "synced":
+        out = [f"  {c(name, BOLD):<14s} {c('✓ synced', GREEN)}      {c(format_num(x['current']), BOLD)}  {peers_label(peers)}"]
+    elif state == "headers":
+        out = [
+            f"  {c(name, BOLD):<14s} {c('⧗ headers', YELLOW)}    {c('downloading initial chain', DIM)}  {peers_label(peers)}",
+            f"                 {c('(per-block progress unavailable until headers validated — see docker logs)', DIM)}",
+        ]
+    elif state == "syncing" and x["target"] <= 0:
+        out = [f"  {c(name, BOLD):<14s} {c('⧗ syncing', YELLOW)}    {c('waiting for fork-choice', DIM)}  {peers_label(peers)}"]
+    elif state == "syncing":
+        pct = x["current"] / x["target"] * 100
+        r = rate_per_sec(hist)
+        eta = eta_seconds(hist, x["target"])
+        rate_s = f"{format_num(int(r))} /s" if r and r > 0 else c("stalled", RED)
+        eta_s = format_eta(eta) if eta is not None else "?"
+        stage = x.get("stage")
+        stage_s = c(f"[{stage}]", DIM) if stage else ""
+        out = [
+            f"  {c(name, BOLD):<14s} {c('⧗ syncing', YELLOW)}    {format_num(x['current'])} / {format_num(x['target'])}  {stage_s}  {peers_label(peers)}",
+            f"                 {progress_bar(pct)} {c(f'{pct:6.2f}%', BOLD)}",
+            f"                 {c(rate_s, DIM)}   ETA {c(eta_s, BOLD)}",
+        ]
+    else:
+        out = [
+            f"  {c(name, BOLD):<14s} {c('✗ ' + state, RED)}",
+            f"                 {c(x.get('err') or '', DIM)}",
+        ]
+    # Reth-only: stages summary
+    if name == "Reth" and x.get("stages"):
+        out.append(f"               {stages_summary(x['stages'])}")
+    for e in extras:
+        out.append(f"                 {e}")
+    return out
+
+
+def render(reth, nimbus, reth_hist, nim_hist):
+    print("\033[2J\033[H", end="")
+    width = 64
+    title = f"Reth + Nimbus sync"
+    ts = time.strftime("%H:%M:%S")
+    print()
+    print(f"  {c(title, BOLD)}   {c(ts, DIM)}")
+    print(f"  {c('─' * width, DIM)}")
+    print()
+    for line in render_one("Reth", reth, reth_hist):
+        print(line)
+    print()
+    for line in render_one("Nimbus", nimbus, nim_hist):
+        print(line)
+    print()
+    win_s = (len(reth_hist) - 1) * INTERVAL if len(reth_hist) > 1 else 0
+    print(f"  {c(f'window {win_s}s · refresh {INTERVAL}s · Ctrl-C to exit', DIM)}")
+    print()
+
+
+def main():
+    once = "--once" in sys.argv
+    reth_hist = deque(maxlen=WINDOW)
+    nim_hist = deque(maxlen=WINDOW)
+    try:
+        while True:
+            r = get_reth()
+            n = get_nimbus()
+            now = time.time()
+            if r["target"] > 0 or r["state"] == "syncing":
+                reth_hist.append((now, r["current"]))
+            if n["target"] > 0 or n["state"] == "syncing":
+                nim_hist.append((now, n["current"]))
+            render(r, n, reth_hist, nim_hist)
+            if once:
+                break
+            if r["state"] == "synced" and n["state"] == "synced":
+                print(f"  {c('✓ all synced.', GREEN)}\n")
+                break
+            time.sleep(INTERVAL)
+    except KeyboardInterrupt:
+        print()
+
+
+if __name__ == "__main__":
+    main()

scripts/smp-server-digitalocean-droplet/files/opt/simplex/initialize_server.sh

@@ -22,7 +22,7 @@ smp-server --version
 
 # Initialize server
 ip_address=$(curl ifconfig.me)
-smp-server init -l --ip $ip_address
+smp-server init -l --disable-web --ip $ip_address
 
 # Server fingerprint
 fingerprint=$(cat /etc/opt/simplex/fingerprint)

scripts/smp-server-digitalocean-droplet/files/opt/simplex/on_login.sh

@@ -12,6 +12,11 @@ Check SMP server status with: systemctl status smp-server
 To keep this server secure, the UFW firewall is enabled.
 All ports are BLOCKED except 22 (SSH), 443 (HTTPS), 5223 (SMP server).
 
+Embedded HTTPS web is disabled because this image does not provision
+/etc/opt/simplex/web.crt or /etc/opt/simplex/web.key. To enable it, provision
+those files, uncomment WEB https/cert/key in /etc/opt/simplex/smp-server.ini,
+and restart smp-server.
+
 ********************************************************************************
 To stop seeing this message delete line - bash /opt/simplex/on_login.sh - from /root/.bashrc
 EOF

scripts/smp-server-linode.sh

@@ -75,6 +75,9 @@ init_opts=()
 
 [[ $ENABLE_STORE_LOG == "on" ]] && init_opts+=(-l)
 
+# This script does not provision /etc/opt/simplex/web.crt or web.key.
+init_opts+=(--disable-web)
+
 ip_address=$(curl ifconfig.me)
 init_opts+=(--ip $ip_address)
 
@@ -111,6 +114,11 @@ Check SMP server status with: systemctl status smp-server
 To keep this server secure, the UFW firewall is enabled.
 All ports are BLOCKED except 22 (SSH), 443 (HTTPS), 5223 (SMP server).
 
+Embedded HTTPS web is disabled because this script does not provision
+/etc/opt/simplex/web.crt or /etc/opt/simplex/web.key. To enable it, provision
+those files, uncomment WEB https/cert/key in /etc/opt/simplex/smp-server.ini,
+and restart smp-server.
+
 ********************************************************************************
 To stop seeing this message delete line - bash /opt/simplex/on_login.sh - from /root/.bashrc
 EOF2

simplexmq.cabal

@@ -1,7 +1,7 @@
-cabal-version: 1.12
+cabal-version: 3.0
 
 name:           simplexmq
-version:        6.5.0.11
+version:        7.0.1.0
 synopsis:       SimpleXMQ message broker
 description:    This package includes <./docs/Simplex-Messaging-Server.html server>,
                 <./docs/Simplex-Messaging-Client.html client> and
@@ -16,7 +16,7 @@ homepage:       https://github.com/simplex-chat/simplexmq#readme
 author:         simplex.chat
 maintainer:     chat@simplex.chat
 copyright:      2020-2022 simplex.chat
-license:        AGPL-3
+license:        AGPL-3.0-only
 license-file:   LICENSE
 build-type:     Simple
 extra-source-files:
@@ -24,6 +24,13 @@ extra-source-files:
     CHANGELOG.md
     cbits/sha512.h
     cbits/sntrup761.h
+    cbits/blst/**/*.c
+    cbits/blst/**/*.h
+    cbits/blst/**/*.s
+    cbits/blst/**/*.S
+    cbits/blst/**/*.asm
+    cbits/libbbs/**/*.c
+    cbits/libbbs/**/*.h
     apps/common/Web/static/index.html
     apps/common/Web/static/link.html
     apps/common/Web/static/media/apk_icon.png
@@ -82,6 +89,11 @@ flag server_postgres
   manual: True
   default: False
 
+flag commoncrypto
+  description: On Apple platforms, use SecRandomCopyBytes (Security.framework) for libbbs randomness. getentropy is a non-public symbol on iOS and triggers App Store rejection (ITMS-90338).
+  manual: True
+  default: False
+
 library
   exposed-modules:
       Simplex.FileTransfer.Agent
@@ -122,6 +134,7 @@ library
       Simplex.Messaging.Crypto.File
       Simplex.Messaging.Crypto.Lazy
       Simplex.Messaging.Crypto.Ratchet
+      Simplex.Messaging.Crypto.BBS
       Simplex.Messaging.Crypto.SNTRUP761
       Simplex.Messaging.Crypto.SNTRUP761.Bindings
       Simplex.Messaging.Crypto.SNTRUP761.Bindings.Defines
@@ -130,6 +143,7 @@ library
       Simplex.Messaging.Crypto.ShortLink
       Simplex.Messaging.Encoding
       Simplex.Messaging.Encoding.String
+      Simplex.Messaging.Names.Record
       Simplex.Messaging.Notifications.Client
       Simplex.Messaging.Notifications.Protocol
       Simplex.Messaging.Notifications.Transport
@@ -141,6 +155,7 @@ library
       Simplex.Messaging.Server.QueueStore.Postgres.Config
       Simplex.Messaging.Server.QueueStore.QueueInfo
       Simplex.Messaging.ServiceScheme
+      Simplex.Messaging.SimplexName
       Simplex.Messaging.Session
       Simplex.Messaging.SystemTime
       Simplex.Messaging.TMap
@@ -173,7 +188,8 @@ library
           Simplex.Messaging.Agent.Store.Postgres.Migrations.M20251009_queue_to_subscribe
           Simplex.Messaging.Agent.Store.Postgres.Migrations.M20251010_client_notices
           Simplex.Messaging.Agent.Store.Postgres.Migrations.M20251230_strict_tables
-          Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260115_service_certs
+          Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260410_receive_attempts
+          Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260411_service_certs
   else
       exposed-modules:
           Simplex.Messaging.Agent.Store.SQLite
@@ -224,7 +240,8 @@ library
           Simplex.Messaging.Agent.Store.SQLite.Migrations.M20251009_queue_to_subscribe
           Simplex.Messaging.Agent.Store.SQLite.Migrations.M20251010_client_notices
           Simplex.Messaging.Agent.Store.SQLite.Migrations.M20251230_strict_tables
-          Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260115_service_certs
+          Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260410_receive_attempts
+          Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260411_service_certs
           Simplex.Messaging.Agent.Store.SQLite.Util
   if flag(client_postgres) || flag(server_postgres)
       exposed-modules:
@@ -259,6 +276,8 @@ library
           Simplex.Messaging.Server.MsgStore.Journal.SharedLock
           Simplex.Messaging.Server.MsgStore.STM
           Simplex.Messaging.Server.MsgStore.Types
+          Simplex.Messaging.Server.Names
+          Simplex.Messaging.Server.Names.HttpResolver
           Simplex.Messaging.Server.NtfStore
           Simplex.Messaging.Server.Prometheus
           Simplex.Messaging.Server.QueueStore
@@ -283,6 +302,9 @@ library
               Simplex.Messaging.Notifications.Server.Store.Migrations
               Simplex.Messaging.Notifications.Server.Store.Postgres
               Simplex.Messaging.Notifications.Server.Store.Types
+              Simplex.FileTransfer.Server.Store.Postgres
+              Simplex.FileTransfer.Server.Store.Postgres.Config
+              Simplex.FileTransfer.Server.Store.Postgres.Migrations
               Simplex.Messaging.Server.MsgStore.Postgres
               Simplex.Messaging.Server.QueueStore.Postgres
               Simplex.Messaging.Server.QueueStore.Postgres.Migrations
@@ -295,11 +317,33 @@ library
   ghc-options: -Weverything -Wno-missing-exported-signatures -Wno-missing-import-lists -Wno-missed-specialisations -Wno-all-missed-specialisations -Wno-unsafe -Wno-safe -Wno-missing-local-signatures -Wno-missing-kind-signatures -Wno-missing-deriving-strategies -Wno-monomorphism-restriction -Wno-prepositive-qualified-module -Wno-implicit-prelude -Wno-missing-safe-haskell-mode -Wno-missing-export-lists -Wno-partial-fields -Wcompat -Werror=incomplete-record-updates -Werror=incomplete-patterns -Werror=incomplete-uni-patterns -Werror=missing-home-modules -Werror=missing-methods -Werror=tabs -Wredundant-constraints -Wincomplete-record-updates -Wunused-type-patterns -O2
   include-dirs:
       cbits
+      cbits/blst/bindings
+      cbits/blst/src
+      cbits/libbbs/include
+      cbits/libbbs/src
+  cc-options: -D__BLST_PORTABLE__
+  if flag(commoncrypto)
+    cc-options: -DBBS_CRYPTO_CC
+    frameworks: Security
   c-sources:
       cbits/sha512.c
       cbits/sntrup761.c
+      cbits/blst/src/server.c
+      cbits/libbbs/src/bbs.c
+      cbits/libbbs/src/bbs_ciphersuites.c
+      cbits/libbbs/src/bbs_util.c
+      cbits/libbbs/src/compat-string.c
+      cbits/libbbs/src/sha256.c
+      cbits/libbbs/src/shake256.c
+  asm-sources:
+      cbits/blst/build/assembly.S
   extra-libraries:
       crypto
+  if os(windows)
+    c-sources:
+        cbits/getentropy_win.c
+    extra-libraries:
+        bcrypt
   build-depends:
       aeson ==2.2.*
     , asn1-encoding ==0.9.*
@@ -350,7 +394,10 @@ library
     build-depends:
         case-insensitive ==1.2.*
       , hashable ==1.4.*
+      , http-client >=0.7 && <0.8
+      , http-client-tls >=0.3 && <0.4
       , ini ==0.4.1
+      , network-uri >=2.6 && <2.7
       , optparse-applicative >=0.15 && <0.17
       , process ==1.6.*
       , temporary ==1.3.*
@@ -432,36 +479,6 @@ executable smp-server
     , text
   default-language: Haskell2010
 
-executable smp-server-bench
-  if flag(client_library)
-      buildable: False
-  if flag(server_postgres)
-    cpp-options: -DdbServerPostgres
-  main-is: Main.hs
-  other-modules:
-      ClientSim
-      Report
-  hs-source-dirs:
-      bench
-  default-extensions:
-      StrictData
-  ghc-options: -O2 -threaded -rtsopts
-  build-depends:
-      base
-    , async
-    , bytestring
-    , containers
-    , crypton
-    , mtl
-    , network
-    , simple-logger
-    , simplexmq
-    , stm
-    , text
-    , time
-    , unliftio
-  default-language: Haskell2010
-
 executable xftp
   if flag(client_library)
       buildable: False
@@ -514,6 +531,7 @@ test-suite simplexmq-test
       AgentTests.EqInstances
       AgentTests.FunctionalAPITests
       AgentTests.MigrationTests
+      AgentTests.ResolveNameTests
       AgentTests.ServerChoice
       AgentTests.ShortLinkTests
       CLITests
@@ -530,9 +548,12 @@ test-suite simplexmq-test
       CoreTests.VersionRangeTests
       FileDescriptionTests
       RemoteControl
+      NamesResolverServer
+      RSLVTests
       ServerTests
       SMPAgentClient
       SMPClient
+      SMPNamesTests
       SMPProxyTests
       Util
       XFTPAgent
@@ -555,6 +576,7 @@ test-suite simplexmq-test
   if flag(server_postgres)
       other-modules:
           AgentTests.NotificationTests
+          CoreTests.XFTPStoreTests
           NtfClient
           NtfServerTests
   if flag(client_postgres) || flag(server_postgres)
@@ -612,6 +634,8 @@ test-suite simplexmq-test
     , unliftio
     , unliftio-core
     , unordered-containers
+    , wai
+    , warp
     , yaml
   default-language: Haskell2010
   if flag(server_postgres)

src/Simplex/FileTransfer/Client/Main.hs

@@ -14,6 +14,7 @@ module Simplex.FileTransfer.Client.Main
   ( SendOptions (..),
     CLIError (..),
     xftpClientCLI,
+    xftpClientDeprecationNotice,
     cliSendFile,
     cliSendFileOpts,
     encodeWebURI,
@@ -69,7 +70,6 @@ import Simplex.Messaging.Encoding
 import Simplex.Messaging.Encoding.String (StrEncoding (..))
 import Simplex.Messaging.Parsers (parseAll)
 import Simplex.Messaging.Protocol (ProtoServerWithAuth (..), ProtocolServer (..), SenderId, SndPrivateAuthKey, XFTPServer, XFTPServerWithAuth)
-import Simplex.Messaging.Server.CLI (getCliCommand')
 import Simplex.Messaging.Util (groupAllOn, ifM, tshow, whenM)
 import System.Exit (exitFailure)
 import System.FilePath (splitFileName, (</>))
@@ -81,6 +81,10 @@ import UnliftIO.Directory
 xftpClientVersion :: String
 xftpClientVersion = "1.0.1"
 
+xftpClientDeprecationNotice :: String
+xftpClientDeprecationNotice =
+  "WARNING: the standalone xftp CLI is experimental and deprecated."
+
 newtype CLIError = CLIError String
   deriving (Eq, Show, Exception)
 
@@ -223,7 +227,13 @@ logCfg = LogConfig {lc_file = Nothing, lc_stderr = True}
 
 xftpClientCLI :: IO ()
 xftpClientCLI =
-  getCliCommand' cliCommandP clientVersion >>= \case
+  customExecParser
+    (prefs showHelpOnEmpty)
+    ( info
+        (helper <*> versionOption <*> cliCommandP)
+        (header (clientVersion <> "\n" <> xftpClientDeprecationNotice) <> fullDesc)
+    )
+    >>= \case
     SendFile opts -> runLogE opts $ cliSendFile opts
     ReceiveFile opts -> runLogE opts $ cliReceiveFile opts
     DeleteFile opts -> runLogE opts $ cliDeleteFile opts
@@ -231,6 +241,7 @@ xftpClientCLI =
     RandomFile opts -> cliRandomFile opts
   where
     clientVersion = "SimpleX XFTP client v" <> xftpClientVersion
+    versionOption = infoOption clientVersion (long "version" <> short 'v' <> help "Show version")
 
 runLogE :: HasField "verbose" a Bool => a -> ExceptT CLIError IO () -> IO ()
 runLogE opts a

src/Simplex/FileTransfer/Server.hs

@@ -31,7 +31,6 @@ import qualified Data.ByteString.Char8 as B
 import Data.Int (Int64)
 import Data.List.NonEmpty (NonEmpty)
 import qualified Data.List.NonEmpty as L
-import qualified Data.Map.Strict as M
 import Data.Maybe (fromMaybe, isJust)
 import qualified Data.Text as T
 import qualified Data.Text.IO as T
@@ -88,7 +87,7 @@ import UnliftIO.Concurrent (threadDelay)
 import UnliftIO.Directory (canonicalizePath, doesFileExist, removeFile, renameFile)
 import qualified UnliftIO.Exception as E
 
-type M a = ReaderT XFTPEnv IO a
+type M s a = ReaderT (XFTPEnv s) IO a
 
 data XFTPTransportRequest = XFTPTransportRequest
   { thParams :: THandleParamsXFTP 'TServer,
@@ -112,19 +111,19 @@ corsPreflightHeaders =
     ("Access-Control-Max-Age", "86400")
   ]
 
-runXFTPServer :: XFTPServerConfig -> IO ()
+runXFTPServer :: FileStoreClass s => XFTPServerConfig s -> IO ()
 runXFTPServer cfg = do
   started <- newEmptyTMVarIO
   runXFTPServerBlocking started cfg
 
-runXFTPServerBlocking :: TMVar Bool -> XFTPServerConfig -> IO ()
+runXFTPServerBlocking :: FileStoreClass s => TMVar Bool -> XFTPServerConfig s -> IO ()
 runXFTPServerBlocking started cfg = newXFTPServerEnv cfg >>= runReaderT (xftpServer cfg started)
 
 data Handshake
   = HandshakeSent C.PrivateKeyX25519
   | HandshakeAccepted (THandleParams XFTPVersion 'TServer)
 
-xftpServer :: XFTPServerConfig -> TMVar Bool -> M ()
+xftpServer :: forall s. FileStoreClass s => XFTPServerConfig s -> TMVar Bool -> M s ()
 xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpiration, fileExpiration, xftpServerVRange} started = do
   mapM_ (expireServerFiles Nothing) fileExpiration
   restoreServerStats
@@ -137,7 +136,7 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
     )
     `finally` stopServer
   where
-    runServer :: M ()
+    runServer :: M s ()
     runServer = do
       srvCreds@(chain, pk) <- asks tlsServerCreds
       httpCreds_ <- asks httpServerCreds
@@ -168,7 +167,7 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
                       Nothing -> pure ()
                       Just thParams -> processRequest req0 {thParams}
                 | otherwise -> liftIO . sendResponse $ H.responseNoBody N.ok200 (corsHeaders addCORS')
-    xftpServerHandshakeV1 :: X.CertificateChain -> C.APrivateSignKey -> TMap SessionId Handshake -> XFTPTransportRequest -> M (Maybe (THandleParams XFTPVersion 'TServer))
+    xftpServerHandshakeV1 :: X.CertificateChain -> C.APrivateSignKey -> TMap SessionId Handshake -> XFTPTransportRequest -> M s (Maybe (THandleParams XFTPVersion 'TServer))
     xftpServerHandshakeV1 chain serverSignKey sessions XFTPTransportRequest {thParams = thParams0@THandleParams {sessionId}, request, reqBody = HTTP2Body {bodyHead}, sendResponse, sniUsed, addCORS} = do
       s <- atomically $ TM.lookup sessionId sessions
       r <- runExceptT $ case s of
@@ -227,39 +226,40 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
               liftIO . sendResponse $ H.responseNoBody N.ok200 (corsHeaders addCORS)
               pure Nothing
             Nothing -> throwE HANDSHAKE
-        sendError :: XFTPErrorType -> M (Maybe (THandleParams XFTPVersion 'TServer))
+        sendError :: XFTPErrorType -> M s (Maybe (THandleParams XFTPVersion 'TServer))
         sendError err = do
           runExceptT (encodeXftp err) >>= \case
             Right bs -> liftIO . sendResponse $ H.responseBuilder N.ok200 (corsHeaders addCORS) bs
             Left _ -> logError $ "Error encoding handshake error: " <> tshow err
           pure Nothing
-        encodeXftp :: Encoding a => a -> ExceptT XFTPErrorType (ReaderT XFTPEnv IO) Builder
+        encodeXftp :: Encoding a => a -> ExceptT XFTPErrorType (ReaderT (XFTPEnv s) IO) Builder
         encodeXftp a = byteString <$> liftHS (C.pad (smpEncode a) xftpBlockSize)
         liftHS = liftEitherWith (const HANDSHAKE)
 
-    stopServer :: M ()
+    stopServer :: M s ()
     stopServer = do
-      withFileLog closeStoreLog
+      st <- asks fileStore
+      liftIO $ closeFileStore st
       saveServerStats
       logNote "Server stopped"
 
-    expireFilesThread_ :: XFTPServerConfig -> [M ()]
+    expireFilesThread_ :: XFTPServerConfig s -> [M s ()]
     expireFilesThread_ XFTPServerConfig {fileExpiration = Just fileExp} = [expireFiles fileExp]
     expireFilesThread_ _ = []
 
-    expireFiles :: ExpirationConfig -> M ()
+    expireFiles :: ExpirationConfig -> M s ()
     expireFiles expCfg = do
       let interval = checkInterval expCfg * 1000000
       forever $ do
         liftIO $ threadDelay' interval
         expireServerFiles (Just 100000) expCfg
 
-    serverStatsThread_ :: XFTPServerConfig -> [M ()]
+    serverStatsThread_ :: XFTPServerConfig s -> [M s ()]
     serverStatsThread_ XFTPServerConfig {logStatsInterval = Just interval, logStatsStartTime, serverStatsLogFile} =
       [logServerStats logStatsStartTime interval serverStatsLogFile]
     serverStatsThread_ _ = []
 
-    logServerStats :: Int64 -> Int64 -> FilePath -> M ()
+    logServerStats :: Int64 -> Int64 -> FilePath -> M s ()
     logServerStats startAt logInterval statsFilePath = do
       initialDelay <- (startAt -) . fromIntegral . (`div` 1000000_000000) . diffTimeToPicoseconds . utctDayTime <$> liftIO getCurrentTime
       liftIO $ putStrLn $ "server stats log enabled: " <> statsFilePath
@@ -300,12 +300,12 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
               ]
         liftIO $ threadDelay' interval
 
-    prometheusMetricsThread_ :: XFTPServerConfig -> [M ()]
+    prometheusMetricsThread_ :: XFTPServerConfig s -> [M s ()]
     prometheusMetricsThread_ XFTPServerConfig {prometheusInterval = Just interval, prometheusMetricsFile} =
       [savePrometheusMetrics interval prometheusMetricsFile]
     prometheusMetricsThread_ _ = []
 
-    savePrometheusMetrics :: Int -> FilePath -> M ()
+    savePrometheusMetrics :: Int -> FilePath -> M s ()
     savePrometheusMetrics saveInterval metricsFile = do
       labelMyThread "savePrometheusMetrics"
       liftIO $ putStrLn $ "Prometheus metrics saved every " <> show saveInterval <> " seconds to " <> metricsFile
@@ -324,11 +324,11 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
       let fd = periodStatDataCounts $ _filesDownloaded d
       pure FileServerMetrics {statsData = d, filesDownloadedPeriods = fd, rtsOptions}
 
-    controlPortThread_ :: XFTPServerConfig -> [M ()]
+    controlPortThread_ :: XFTPServerConfig s -> [M s ()]
     controlPortThread_ XFTPServerConfig {controlPort = Just port} = [runCPServer port]
     controlPortThread_ _ = []
 
-    runCPServer :: ServiceName -> M ()
+    runCPServer :: ServiceName -> M s ()
     runCPServer port = do
       cpStarted <- newEmptyTMVarIO
       u <- askUnliftIO
@@ -336,7 +336,7 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
         labelMyThread "control port server"
         runLocalTCPServer cpStarted port $ runCPClient u
       where
-        runCPClient :: UnliftIO (ReaderT XFTPEnv IO) -> Socket -> IO ()
+        runCPClient :: UnliftIO (ReaderT (XFTPEnv s) IO) -> Socket -> IO ()
         runCPClient u sock = do
           labelMyThread "control port client"
           h <- socketToHandle sock ReadWriteMode
@@ -366,15 +366,15 @@ xftpServer cfg@XFTPServerConfig {xftpPort, transportConfig, inactiveClientExpira
                   XFTPServerConfig {controlPortUserAuth = user, controlPortAdminAuth = admin} = cfg
               CPStatsRTS -> E.tryAny getRTSStats >>= either (hPrint h) (hPrint h)
               CPDelete fileId -> withUserRole $ unliftIO u $ do
-                fs <- asks store
+                fs <- asks fileStore
                 r <- runExceptT $ do
-                  (fr, _) <- ExceptT $ atomically $ getFile fs SFRecipient fileId
+                  (fr, _) <- ExceptT $ liftIO $ getFile fs SFRecipient fileId
                   ExceptT $ deleteServerFile_ fr
                 liftIO . hPutStrLn h $ either (\e -> "error: " <> show e) (\() -> "ok") r
               CPBlock fileId info -> withUserRole $ unliftIO u $ do
-                fs <- asks store
+                fs <- asks fileStore
                 r <- runExceptT $ do
-                  (fr, _) <- ExceptT $ atomically $ getFile fs SFRecipient fileId
+                  (fr, _) <- ExceptT $ liftIO $ getFile fs SFRecipient fileId
                   ExceptT $ blockServerFile fr info
                 liftIO . hPutStrLn h $ either (\e -> "error: " <> show e) (\() -> "ok") r
               CPHelp -> hPutStrLn h "commands: stats-rts, delete, help, quit"
@@ -395,7 +395,7 @@ data ServerFile = ServerFile
     sbState :: LC.SbState
   }
 
-processRequest :: XFTPTransportRequest -> M ()
+processRequest :: FileStoreClass s => XFTPTransportRequest -> M s ()
 processRequest XFTPTransportRequest {thParams, reqBody = body@HTTP2Body {bodyHead}, sendResponse, addCORS}
   | B.length bodyHead /= xftpBlockSize = sendXFTPResponse ("", NoEntity, FRErr BLOCK) Nothing
   | otherwise =
@@ -430,7 +430,7 @@ processRequest XFTPTransportRequest {thParams, reqBody = body@HTTP2Body {bodyHea
           done
 
 #ifdef slow_servers
-randomDelay :: M ()
+randomDelay :: M s ()
 randomDelay = do
   d <- asks $ responseDelay . config
   when (d > 0) $ do
@@ -440,20 +440,20 @@ randomDelay = do
 
 data VerificationResult = VRVerified XFTPRequest | VRFailed XFTPErrorType
 
-verifyXFTPTransmission :: Maybe (THandleAuth 'TServer) -> SignedTransmission FileCmd -> M VerificationResult
+verifyXFTPTransmission :: forall s. FileStoreClass s => Maybe (THandleAuth 'TServer) -> SignedTransmission FileCmd -> M s VerificationResult
 verifyXFTPTransmission thAuth (tAuth, authorized, (corrId, fId, cmd)) =
   case cmd of
     FileCmd SFSender (FNEW file rcps auth') -> pure $ XFTPReqNew file rcps auth' `verifyWith` sndKey file
     FileCmd SFRecipient PING -> pure $ VRVerified XFTPReqPing
     FileCmd party _ -> verifyCmd party
   where
-    verifyCmd :: SFileParty p -> M VerificationResult
+    verifyCmd :: SFileParty p -> M s VerificationResult
     verifyCmd party = do
-      st <- asks store
-      atomically $ verify =<< getFile st party fId
+      st <- asks fileStore
+      liftIO $ verify =<< getFile st party fId
       where
         verify = \case
-          Right (fr, k) -> result <$> readTVar (fileStatus fr)
+          Right (fr, k) -> result <$> readTVarIO (fileStatus fr)
             where
               result = \case
                 EntityActive -> XFTPReqCmd fId fr cmd `verifyWith` k
@@ -464,7 +464,7 @@ verifyXFTPTransmission thAuth (tAuth, authorized, (corrId, fId, cmd)) =
     -- TODO verify with DH authorization
     req `verifyWith` k = if verifyCmdAuthorization thAuth tAuth authorized corrId k then VRVerified req else VRFailed AUTH
 
-processXFTPRequest :: HTTP2Body -> XFTPRequest -> M (FileResponse, Maybe ServerFile)
+processXFTPRequest :: forall s. FileStoreClass s => HTTP2Body -> XFTPRequest -> M s (FileResponse, Maybe ServerFile)
 processXFTPRequest HTTP2Body {bodyPart} = \case
   XFTPReqNew file rks auth -> noFile =<< ifM allowNew (createFile file rks) (pure $ FRErr AUTH)
     where
@@ -483,9 +483,9 @@ processXFTPRequest HTTP2Body {bodyPart} = \case
   XFTPReqPing -> noFile FRPong
   where
     noFile resp = pure (resp, Nothing)
-    createFile :: FileInfo -> NonEmpty RcvPublicAuthKey -> M FileResponse
+    createFile :: FileInfo -> NonEmpty RcvPublicAuthKey -> M s FileResponse
     createFile file rks = do
-      st <- asks store
+      st <- asks fileStore
       r <- runExceptT $ do
         sizes <- asks $ allowedChunkSizes . config
         unless (size file `elem` sizes) $ throwE SIZE
@@ -502,27 +502,27 @@ processXFTPRequest HTTP2Body {bodyPart} = \case
         let rIds = L.map (\(FileRecipient rId _) -> rId) rcps
         pure $ FRSndIds sId rIds
       pure $ either FRErr id r
-    addFileRetry :: FileStore -> FileInfo -> Int -> RoundedFileTime -> M (Either XFTPErrorType XFTPFileId)
+    addFileRetry :: s -> FileInfo -> Int -> RoundedFileTime -> M s (Either XFTPErrorType XFTPFileId)
     addFileRetry st file n ts =
       retryAdd n $ \sId -> runExceptT $ do
         ExceptT $ addFile st sId file ts EntityActive
         pure sId
-    addRecipientRetry :: FileStore -> Int -> XFTPFileId -> RcvPublicAuthKey -> M (Either XFTPErrorType FileRecipient)
+    addRecipientRetry :: s -> Int -> XFTPFileId -> RcvPublicAuthKey -> M s (Either XFTPErrorType FileRecipient)
     addRecipientRetry st n sId rpk =
       retryAdd n $ \rId -> runExceptT $ do
         let rcp = FileRecipient rId rpk
         ExceptT $ addRecipient st sId rcp
         pure rcp
-    retryAdd :: Int -> (XFTPFileId -> STM (Either XFTPErrorType a)) -> M (Either XFTPErrorType a)
+    retryAdd :: Int -> (XFTPFileId -> IO (Either XFTPErrorType a)) -> M s (Either XFTPErrorType a)
     retryAdd 0 _ = pure $ Left INTERNAL
     retryAdd n add = do
       fId <- getFileId
-      atomically (add fId) >>= \case
+      liftIO (add fId) >>= \case
         Left DUPLICATE_ -> retryAdd (n - 1) add
         r -> pure r
-    addRecipients :: XFTPFileId -> NonEmpty RcvPublicAuthKey -> M FileResponse
+    addRecipients :: XFTPFileId -> NonEmpty RcvPublicAuthKey -> M s FileResponse
     addRecipients sId rks = do
-      st <- asks store
+      st <- asks fileStore
       r <- runExceptT $ do
         rcps <- mapM (ExceptT . addRecipientRetry st 3 sId) rks
         lift $ withFileLog $ \sl -> logAddRecipients sl sId rcps
@@ -531,7 +531,7 @@ processXFTPRequest HTTP2Body {bodyPart} = \case
         let rIds = L.map (\(FileRecipient rId _) -> rId) rcps
         pure $ FRRcvIds rIds
       pure $ either FRErr id r
-    receiveServerFile :: FileRec -> M FileResponse
+    receiveServerFile :: FileRec -> M s FileResponse
     receiveServerFile FileRec {senderId, fileInfo = FileInfo {size, digest}, filePath} = case bodyPart of
       Nothing -> pure $ FRErr SIZE
       -- TODO validate body size from request before downloading, once it's populated
@@ -549,7 +549,7 @@ processXFTPRequest HTTP2Body {bodyPart} = \case
                   | bs == 0 || bs > s -> pure $ FRErr SIZE
                   | otherwise -> drain (s - bs)
           reserve = do
-            us <- asks $ usedStorage . store
+            us <- asks usedStorage
             quota <- asks $ fromMaybe maxBound . fileSizeQuota . config
             atomically . stateTVar us $
               \used -> let used' = used + fromIntegral size in if used' <= quota then (True, used') else (False, used)
@@ -559,21 +559,28 @@ processXFTPRequest HTTP2Body {bodyPart} = \case
             receiveChunk (XFTPRcvChunkSpec fPath size digest) >>= \case
               Right () -> do
                 stats <- asks serverStats
-                withFileLog $ \sl -> logPutFile sl senderId fPath
-                atomically $ writeTVar filePath (Just fPath)
-                incFileStat filesUploaded
-                incFileStat filesCount
-                liftIO $ atomicModifyIORef'_ (filesSize stats) (+ fromIntegral size)
-                pure FROk
+                st <- asks fileStore
+                liftIO (setFilePath st senderId fPath) >>= \case
+                  Right () -> do
+                    withFileLog $ \sl -> logPutFile sl senderId fPath
+                    incFileStat filesUploaded
+                    incFileStat filesCount
+                    liftIO $ atomicModifyIORef'_ (filesSize stats) (+ fromIntegral size)
+                    pure FROk
+                  Left _e -> do
+                    us <- asks usedStorage
+                    atomically $ modifyTVar' us $ subtract (fromIntegral size)
+                    liftIO $ whenM (doesFileExist fPath) (removeFile fPath) `catch` logFileError
+                    pure $ FRErr AUTH
               Left e -> do
-                us <- asks $ usedStorage . store
+                us <- asks usedStorage
                 atomically $ modifyTVar' us $ subtract (fromIntegral size)
                 liftIO $ whenM (doesFileExist fPath) (removeFile fPath) `catch` logFileError
                 pure $ FRErr e
           receiveChunk spec = do
             t <- asks $ fileTimeout . config
             liftIO $ fromMaybe (Left TIMEOUT) <$> timeout t (runExceptT $ receiveFile getBody spec)
-    sendServerFile :: FileRec -> RcvPublicDhKey -> M (FileResponse, Maybe ServerFile)
+    sendServerFile :: FileRec -> RcvPublicDhKey -> M s (FileResponse, Maybe ServerFile)
     sendServerFile FileRec {senderId, filePath, fileInfo = FileInfo {size}} rDhKey = do
       readTVarIO filePath >>= \case
         Just path -> ifM (doesFileExist path) sendFile (pure (FRErr AUTH, Nothing))
@@ -592,38 +599,41 @@ processXFTPRequest HTTP2Body {bodyPart} = \case
                 _ -> pure (FRErr INTERNAL, Nothing)
         _ -> pure (FRErr NO_FILE, Nothing)
 
-    deleteServerFile :: FileRec -> M FileResponse
+    deleteServerFile :: FileRec -> M s FileResponse
     deleteServerFile fr = either FRErr (\() -> FROk) <$> deleteServerFile_ fr
 
     logFileError :: SomeException -> IO ()
     logFileError e = logError $ "Error deleting file: " <> tshow e
 
-    ackFileReception :: RecipientId -> FileRec -> M FileResponse
+    ackFileReception :: RecipientId -> FileRec -> M s FileResponse
     ackFileReception rId fr = do
       withFileLog (`logAckFile` rId)
-      st <- asks store
-      atomically $ deleteRecipient st rId fr
+      st <- asks fileStore
+      liftIO $ deleteRecipient st rId fr
       incFileStat fileDownloadAcks
       pure FROk
 
-deleteServerFile_ :: FileRec -> M (Either XFTPErrorType ())
+deleteServerFile_ :: FileStoreClass s => FileRec -> M s (Either XFTPErrorType ())
 deleteServerFile_ fr@FileRec {senderId} = do
   withFileLog (`logDeleteFile` senderId)
   deleteOrBlockServerFile_ fr filesDeleted (`deleteFile` senderId)
 
 -- this also deletes the file from storage, but doesn't include it in delete statistics
-blockServerFile :: FileRec -> BlockingInfo -> M (Either XFTPErrorType ())
+blockServerFile :: FileStoreClass s => FileRec -> BlockingInfo -> M s (Either XFTPErrorType ())
 blockServerFile fr@FileRec {senderId} info = do
   withFileLog $ \sl -> logBlockFile sl senderId info
   deleteOrBlockServerFile_ fr filesBlocked $ \st -> blockFile st senderId info True
 
-deleteOrBlockServerFile_ :: FileRec -> (FileServerStats -> IORef Int) -> (FileStore -> STM (Either XFTPErrorType ())) -> M (Either XFTPErrorType ())
+deleteOrBlockServerFile_ :: FileStoreClass s => FileRec -> (FileServerStats -> IORef Int) -> (s -> IO (Either XFTPErrorType ())) -> M s (Either XFTPErrorType ())
 deleteOrBlockServerFile_ FileRec {filePath, fileInfo} stat storeAction = runExceptT $ do
   path <- readTVarIO filePath
   stats <- asks serverStats
   ExceptT $ first (\(_ :: SomeException) -> FILE_IO) <$> try (forM_ path $ \p -> whenM (doesFileExist p) (removeFile p >> deletedStats stats))
-  st <- asks store
-  void $ atomically $ storeAction st
+  st <- asks fileStore
+  ExceptT $ liftIO $ storeAction st
+  forM_ path $ \_ -> do
+    us <- asks usedStorage
+    atomically $ modifyTVar' us $ subtract (fromIntegral $ size fileInfo)
   lift $ incFileStat stat
   where
     deletedStats stats = do
@@ -633,47 +643,50 @@ deleteOrBlockServerFile_ FileRec {filePath, fileInfo} stat storeAction = runExce
 getFileTime :: IO RoundedFileTime
 getFileTime = getRoundedSystemTime
 
-expireServerFiles :: Maybe Int -> ExpirationConfig -> M ()
+expireServerFiles :: FileStoreClass s => Maybe Int -> ExpirationConfig -> M s ()
 expireServerFiles itemDelay expCfg = do
-  st <- asks store
-  usedStart <- readTVarIO $ usedStorage st
+  st <- asks fileStore
+  us <- asks usedStorage
+  usedStart <- readTVarIO us
   old <- liftIO $ expireBeforeEpoch expCfg
-  files' <- readTVarIO (files st)
-  logNote $ "Expiration check: " <> tshow (M.size files') <> " files"
-  forM_ (M.keys files') $ \sId -> do
-    mapM_ threadDelay itemDelay
-    atomically (expiredFilePath st sId old)
-      >>= mapM_ (maybeRemove $ delete st sId)
-  usedEnd <- readTVarIO $ usedStorage st
+  filesCount <- liftIO $ getFileCount st
+  logNote $ "Expiration check: " <> tshow filesCount <> " files"
+  expireLoop st us old
+  usedEnd <- readTVarIO us
   logNote $ "Used " <> mbs usedStart <> " -> " <> mbs usedEnd <> ", " <> mbs (usedStart - usedEnd) <> " reclaimed."
   where
     mbs bs = tshow (bs `div` 1048576) <> "mb"
-    maybeRemove del = maybe del (remove del)
-    remove del filePath =
-      ifM
-        (doesFileExist filePath)
-        ((removeFile filePath >> del) `catch` \(e :: SomeException) -> logError $ "failed to remove expired file " <> tshow filePath <> ": " <> tshow e)
-        del
-    delete st sId = do
-      withFileLog (`logDeleteFile` sId)
-      void . atomically $ deleteFile st sId -- will not update usedStorage if sId isn't in store
-      incFileStat filesExpired
+    expireLoop st us old = do
+      expired <- liftIO $ expiredFiles st old 10000
+      forM_ expired $ \(sId, filePath_, fileSize) -> do
+        mapM_ threadDelay itemDelay
+        forM_ filePath_ $ \fp ->
+          whenM (doesFileExist fp) $
+            removeFile fp `catch` \(e :: SomeException) -> logError $ "failed to remove expired file " <> tshow fp <> ": " <> tshow e
+        forM_ filePath_ $ \_ ->
+          atomically $ modifyTVar' us $ subtract (fromIntegral fileSize)
+        incFileStat filesExpired
+      let sIds = map (\(sId, _, _) -> sId) expired
+      unless (null sIds) $ do
+        withFileLog $ \sl -> mapM_ (logDeleteFile sl) sIds
+        liftIO $ deleteFiles st sIds
+        expireLoop st us old
 
-randomId :: Int -> M ByteString
+randomId :: Int -> M s ByteString
 randomId n = atomically . C.randomBytes n =<< asks random
 
-getFileId :: M XFTPFileId
+getFileId :: M s XFTPFileId
 getFileId = fmap EntityId . randomId =<< asks (fileIdSize . config)
 
-withFileLog :: (StoreLog 'WriteMode -> IO a) -> M ()
+withFileLog :: (StoreLog 'WriteMode -> IO a) -> M s ()
 withFileLog action = liftIO . mapM_ action =<< asks storeLog
 
-incFileStat :: (FileServerStats -> IORef Int) -> M ()
+incFileStat :: (FileServerStats -> IORef Int) -> M s ()
 incFileStat statSel = do
   stats <- asks serverStats
   liftIO $ atomicModifyIORef'_ (statSel stats) (+ 1)
 
-saveServerStats :: M ()
+saveServerStats :: M s ()
 saveServerStats =
   asks (serverStatsBackupFile . config)
     >>= mapM_ (\f -> asks serverStats >>= liftIO . getFileServerStatsData >>= liftIO . saveStats f)
@@ -683,7 +696,7 @@ saveServerStats =
       B.writeFile f $ strEncode stats
       logNote "server stats saved"
 
-restoreServerStats :: M ()
+restoreServerStats :: FileStoreClass s => M s ()
 restoreServerStats = asks (serverStatsBackupFile . config) >>= mapM_ restoreStats
   where
     restoreStats f = whenM (doesFileExist f) $ do
@@ -691,9 +704,9 @@ restoreServerStats = asks (serverStatsBackupFile . config) >>= mapM_ restoreStat
       liftIO (strDecode <$> B.readFile f) >>= \case
         Right d@FileServerStatsData {_filesCount = statsFilesCount, _filesSize = statsFilesSize} -> do
           s <- asks serverStats
-          FileStore {files, usedStorage} <- asks store
-          _filesCount <- M.size <$> readTVarIO files
-          _filesSize <- readTVarIO usedStorage
+          st <- asks fileStore
+          _filesCount <- liftIO $ getFileCount st
+          _filesSize <- readTVarIO =<< asks usedStorage
           liftIO $ setFileServerStats s d {_filesCount, _filesSize}
           renameFile f $ f <> ".bak"
           logNote "server stats restored"

src/Simplex/FileTransfer/Server/Env.hs

@@ -1,21 +1,35 @@
+{-# LANGUAGE CPP #-}
 {-# LANGUAGE DataKinds #-}
 {-# LANGUAGE DuplicateRecordFields #-}
+{-# LANGUAGE FlexibleContexts #-}
 {-# LANGUAGE GADTs #-}
 {-# LANGUAGE KindSignatures #-}
+{-# LANGUAGE RankNTypes #-}
 {-# LANGUAGE LambdaCase #-}
 {-# LANGUAGE NamedFieldPuns #-}
 {-# LANGUAGE OverloadedStrings #-}
 {-# LANGUAGE StrictData #-}
+{-# LANGUAGE TypeFamilies #-}
 
 module Simplex.FileTransfer.Server.Env
   ( XFTPServerConfig (..),
+    XFTPStoreConfig (..),
     XFTPEnv (..),
     XFTPRequest (..),
+    XFTPStoreType,
+    FileStore (..),
+    AFStoreType (..),
+    fileStore,
+    fromFileStore,
     defaultInactiveClientExpiration,
     defFileExpirationHours,
     defaultFileExpiration,
     newXFTPServerEnv,
-    countUsedStorage,
+    readFileStoreType,
+    runWithStoreConfig,
+    checkFileStoreMode,
+    importToDatabase,
+    exportFromDatabase,
   ) where
 
 import Control.Logger.Simple
@@ -23,7 +37,6 @@ import Control.Monad
 import Crypto.Random
 import Data.Int (Int64)
 import Data.List.NonEmpty (NonEmpty)
-import qualified Data.Map.Strict as M
 import Data.Time.Clock (getCurrentTime)
 import Data.Word (Word32)
 import Data.X509.Validation (Fingerprint (..))
@@ -31,7 +44,21 @@ import Network.Socket
 import qualified Network.TLS as T
 import Simplex.FileTransfer.Protocol (FileCmd, FileInfo (..), XFTPFileId)
 import Simplex.FileTransfer.Server.Stats
+import Data.Either (fromRight)
+import Data.Ini (Ini, lookupValue)
+import qualified Data.Text as T
 import Simplex.FileTransfer.Server.Store
+import Simplex.Messaging.Agent.Store.Shared (MigrationConfirmation)
+import Data.Functor (($>))
+import Simplex.Messaging.Server.CLI (settingIsOn)
+import System.Exit (exitFailure)
+#if defined(dbServerPostgres)
+import Data.Maybe (isNothing)
+import Simplex.FileTransfer.Server.Store.Postgres (PostgresFileStore, importFileStore, exportFileStore)
+import Simplex.FileTransfer.Server.Store.Postgres.Config (PostgresFileStoreCfg (..), defaultXFTPDBOpts)
+import Simplex.Messaging.Server.CLI (iniDBOptions)
+import System.Directory (doesFileExist)
+#endif
 import Simplex.FileTransfer.Server.StoreLog
 import Simplex.FileTransfer.Transport (VersionRangeXFTP)
 import qualified Simplex.Messaging.Crypto as C
@@ -42,10 +69,11 @@ import Simplex.Messaging.Util (tshow)
 import System.IO (IOMode (..))
 import UnliftIO.STM
 
-data XFTPServerConfig = XFTPServerConfig
+data XFTPServerConfig s = XFTPServerConfig
   { xftpPort :: ServiceName,
     controlPort :: Maybe ServiceName,
     fileIdSize :: Int,
+    serverStoreCfg :: XFTPStoreConfig s,
     storeLogFile :: Maybe FilePath,
     filesPath :: FilePath,
     -- | server storage quota
@@ -88,9 +116,10 @@ defaultInactiveClientExpiration =
       checkInterval = 3600 -- seconds, 1 hours
     }
 
-data XFTPEnv = XFTPEnv
-  { config :: XFTPServerConfig,
-    store :: FileStore,
+data XFTPEnv s = XFTPEnv
+  { config :: XFTPServerConfig s,
+    store :: FileStore s,
+    usedStorage :: TVar Int64,
     storeLog :: Maybe (StoreLog 'WriteMode),
     random :: TVar ChaChaDRG,
     serverIdentity :: C.KeyHash,
@@ -99,6 +128,38 @@ data XFTPEnv = XFTPEnv
     serverStats :: FileServerStats
   }
 
+fileStore :: XFTPEnv s -> s
+fileStore = fromFileStore . store
+{-# INLINE fileStore #-}
+
+data XFTPStoreConfig s where
+  XSCMemory :: Maybe FilePath -> XFTPStoreConfig STMFileStore
+#if defined(dbServerPostgres)
+  XSCDatabase :: PostgresFileStoreCfg -> XFTPStoreConfig PostgresFileStore
+#endif
+
+type family XFTPStoreType (fs :: FSType) where
+  XFTPStoreType 'FSMemory = STMFileStore
+#if defined(dbServerPostgres)
+  XFTPStoreType 'FSPostgres = PostgresFileStore
+#endif
+
+data FileStore s where
+  StoreMemory :: STMFileStore -> FileStore STMFileStore
+#if defined(dbServerPostgres)
+  StoreDatabase :: PostgresFileStore -> FileStore PostgresFileStore
+#endif
+
+data AFStoreType = forall fs. AFSType (SFSType fs)
+
+fromFileStore :: FileStore s -> s
+fromFileStore = \case
+  StoreMemory s -> s
+#if defined(dbServerPostgres)
+  StoreDatabase s -> s
+#endif
+{-# INLINE fromFileStore #-}
+
 defFileExpirationHours :: Int64
 defFileExpirationHours = 48
 
@@ -109,13 +170,22 @@ defaultFileExpiration =
       checkInterval = 2 * 3600 -- seconds, 2 hours
     }
 
-newXFTPServerEnv :: XFTPServerConfig -> IO XFTPEnv
-newXFTPServerEnv config@XFTPServerConfig {storeLogFile, fileSizeQuota, xftpCredentials, httpCredentials} = do
+newXFTPServerEnv :: FileStoreClass s => XFTPServerConfig s -> IO (XFTPEnv s)
+newXFTPServerEnv config@XFTPServerConfig {serverStoreCfg, fileSizeQuota, xftpCredentials, httpCredentials} = do
   random <- C.newRandom
-  store <- newFileStore
-  storeLog <- mapM (`readWriteFileStore` store) storeLogFile
-  used <- countUsedStorage <$> readTVarIO (files store)
-  atomically $ writeTVar (usedStorage store) used
+  (store, storeLog) <- case serverStoreCfg of
+    XSCMemory storeLogPath -> do
+      st <- newFileStore ()
+      sl <- mapM (`readWriteFileStore` st) storeLogPath
+      atomically $ writeTVar (stmStoreLog st) sl
+      pure (StoreMemory st, sl)
+#if defined(dbServerPostgres)
+    XSCDatabase dbCfg -> do
+      st <- newFileStore dbCfg
+      pure (StoreDatabase st, Nothing)
+#endif
+  used <- getUsedStorage (fromFileStore store)
+  usedStorage <- newTVarIO used
   forM_ fileSizeQuota $ \quota -> do
     logNote $ "Total / available storage: " <> tshow quota <> " / " <> tshow (quota - used)
     when (quota < used) $ logWarn "WARNING: storage quota is less than used storage, no files can be uploaded!"
@@ -123,12 +193,76 @@ newXFTPServerEnv config@XFTPServerConfig {storeLogFile, fileSizeQuota, xftpCrede
   httpServerCreds <- mapM loadServerCredential httpCredentials
   Fingerprint fp <- loadFingerprint xftpCredentials
   serverStats <- newFileServerStats =<< getCurrentTime
-  pure XFTPEnv {config, store, storeLog, random, tlsServerCreds, httpServerCreds, serverIdentity = C.KeyHash fp, serverStats}
-
-countUsedStorage :: M.Map k FileRec -> Int64
-countUsedStorage = M.foldl' (\acc FileRec {fileInfo = FileInfo {size}} -> acc + fromIntegral size) 0
+  pure XFTPEnv {config, store, usedStorage, storeLog, random, tlsServerCreds, httpServerCreds, serverIdentity = C.KeyHash fp, serverStats}
 
 data XFTPRequest
   = XFTPReqNew FileInfo (NonEmpty RcvPublicAuthKey) (Maybe BasicAuth)
   | XFTPReqCmd XFTPFileId FileRec FileCmd
   | XFTPReqPing
+
+readFileStoreType :: Ini -> Either String AFStoreType
+readFileStoreType ini = case fromRight "memory" $ T.unpack <$> lookupValue "STORE_LOG" "store_files" ini of
+  "memory" -> Right $ AFSType SFSMemory
+  "database" -> Right $ AFSType SFSPostgres
+  other -> Left $ "Invalid store_files value: " <> other
+
+-- | Dispatch store config from AFStoreType singleton and run the callback.
+-- CPP guards for Postgres are handled here so Main.hs stays CPP-free.
+runWithStoreConfig ::
+  AFStoreType ->
+  Ini ->
+  FilePath ->
+  MigrationConfirmation ->
+  (forall s. FileStoreClass s => XFTPStoreConfig s -> IO ()) ->
+  IO ()
+runWithStoreConfig (AFSType SFSMemory) ini storeLogFilePath _confirmMigrations run =
+  run $ XSCMemory (enableStoreLog' $> storeLogFilePath)
+  where
+    enableStoreLog' = settingIsOn "STORE_LOG" "enable" ini
+runWithStoreConfig (AFSType SFSPostgres) ini storeLogFilePath confirmMigrations run =
+#if defined(dbServerPostgres)
+  run $ XSCDatabase dbCfg
+  where
+    enableDbStoreLog' = settingIsOn "STORE_LOG" "db_store_log" ini
+    dbStoreLogPath = enableDbStoreLog' $> storeLogFilePath
+    dbCfg = PostgresFileStoreCfg {dbOpts = iniDBOptions ini defaultXFTPDBOpts, dbStoreLogPath, confirmMigrations}
+#else
+  error "server binary is compiled without support for PostgreSQL database"
+#endif
+
+-- | Validate startup config when store_files=database.
+checkFileStoreMode :: Ini -> AFStoreType -> FilePath -> IO ()
+checkFileStoreMode ini (AFSType SFSPostgres) storeLogFilePath = do
+#if defined(dbServerPostgres)
+  storeLogExists <- doesFileExist storeLogFilePath
+  let dbStoreLogOn = settingIsOn "STORE_LOG" "db_store_log" ini
+  when (storeLogExists && isNothing dbStoreLogOn) $ do
+    putStrLn $ "Error: store log file " <> storeLogFilePath <> " exists but store_files is `database`."
+    putStrLn "Use `file-server database import` to migrate, or set `db_store_log: on`."
+    exitFailure
+#else
+  putStrLn "Error: server binary is compiled without support for PostgreSQL database."
+  putStrLn "Please re-compile with `cabal build -fserver_postgres`."
+  exitFailure
+#endif
+checkFileStoreMode _ (AFSType SFSMemory) _ = pure ()
+
+-- | Import StoreLog to PostgreSQL database.
+importToDatabase :: FilePath -> Ini -> MigrationConfirmation -> IO ()
+#if defined(dbServerPostgres)
+importToDatabase storeLogFilePath ini _confirmMigrations = do
+  let dbCfg = PostgresFileStoreCfg {dbOpts = iniDBOptions ini defaultXFTPDBOpts, dbStoreLogPath = Nothing, confirmMigrations = _confirmMigrations}
+  importFileStore storeLogFilePath dbCfg
+#else
+importToDatabase _ _ _ = error "Error: server binary is compiled without support for PostgreSQL database.\nPlease re-compile with `cabal build -fserver_postgres`."
+#endif
+
+-- | Export PostgreSQL database to StoreLog.
+exportFromDatabase :: FilePath -> Ini -> MigrationConfirmation -> IO ()
+#if defined(dbServerPostgres)
+exportFromDatabase storeLogFilePath ini _confirmMigrations = do
+  let dbCfg = PostgresFileStoreCfg {dbOpts = iniDBOptions ini defaultXFTPDBOpts, dbStoreLogPath = Nothing, confirmMigrations = _confirmMigrations}
+  exportFileStore storeLogFilePath dbCfg
+#else
+exportFromDatabase _ _ _ = error "Error: server binary is compiled without support for PostgreSQL database.\nPlease re-compile with `cabal build -fserver_postgres`."
+#endif

src/Simplex/FileTransfer/Server/Main.hs

@@ -5,6 +5,7 @@
 {-# LANGUAGE OverloadedLists #-}
 {-# LANGUAGE OverloadedStrings #-}
 {-# LANGUAGE PatternSynonyms #-}
+{-# LANGUAGE RankNTypes #-}
 {-# LANGUAGE TypeApplications #-}
 
 module Simplex.FileTransfer.Server.Main
@@ -12,7 +13,7 @@ module Simplex.FileTransfer.Server.Main
     xftpServerCLI_,
   ) where
 
-import Control.Monad (when)
+import Control.Monad (unless, when)
 import Data.Either (fromRight)
 import Data.Functor (($>))
 import Data.Ini (lookupValue, readIniFile)
@@ -28,11 +29,12 @@ import Options.Applicative
 import Simplex.FileTransfer.Chunks
 import Simplex.FileTransfer.Description (FileSize (..))
 import Simplex.FileTransfer.Server (runXFTPServer)
-import Simplex.FileTransfer.Server.Env (XFTPServerConfig (..), defFileExpirationHours, defaultFileExpiration, defaultInactiveClientExpiration)
+import Simplex.FileTransfer.Server.Env (XFTPServerConfig (..), XFTPStoreConfig, AFStoreType (..), defFileExpirationHours, defaultFileExpiration, defaultInactiveClientExpiration, readFileStoreType, runWithStoreConfig, checkFileStoreMode, importToDatabase, exportFromDatabase)
 import Simplex.FileTransfer.Transport (alpnSupportedXFTPhandshakes, supportedFileServerVRange)
 import qualified Simplex.Messaging.Crypto as C
 import Simplex.Messaging.Encoding.String
 import Simplex.Messaging.Protocol (ProtoServerWithAuth (..), pattern XFTPServer)
+import Simplex.Messaging.Agent.Store.Shared (MigrationConfirmation (..))
 import Simplex.Messaging.Server.CLI
 import Simplex.Messaging.Server.Expiration
 import Simplex.Messaging.Server.Information (ServerPublicInfo (..))
@@ -51,7 +53,7 @@ xftpServerCLI :: FilePath -> FilePath -> IO ()
 xftpServerCLI = xftpServerCLI_ (\_ _ _ _ -> pure ()) (\_ -> pure ())
 
 xftpServerCLI_ ::
-  (XFTPServerConfig -> Maybe ServerPublicInfo -> Maybe TransportHost -> FilePath -> IO ()) ->
+  (forall s. XFTPServerConfig s -> Maybe ServerPublicInfo -> Maybe TransportHost -> FilePath -> IO ()) ->
   (EmbeddedWebParams -> IO ()) ->
   FilePath ->
   FilePath ->
@@ -66,9 +68,13 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
       doesFileExist iniFile >>= \case
         True -> genOnline cfgPath certOpts
         _ -> exitError $ "Error: server is not initialized (" <> iniFile <> " does not exist).\nRun `" <> executableName <> " init`."
-    Start ->
+    Start opts ->
       doesFileExist iniFile >>= \case
-        True -> readIniFile iniFile >>= either exitError runServer
+        True -> readIniFile iniFile >>= either exitError (runServer opts)
+        _ -> exitError $ "Error: server is not initialized (" <> iniFile <> " does not exist).\nRun `" <> executableName <> " init`."
+    Database cmd ->
+      doesFileExist iniFile >>= \case
+        True -> readIniFile iniFile >>= either exitError (runDatabaseCmd cmd)
         _ -> exitError $ "Error: server is not initialized (" <> iniFile <> " does not exist).\nRun `" <> executableName <> " init`."
     Delete -> do
       confirmOrExit
@@ -84,6 +90,21 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
     executableName = "file-server"
     storeLogFilePath = combine logPath "file-server-store.log"
     defaultStaticPath = combine logPath "www"
+    runDatabaseCmd cmd ini = case cmd of
+      SCImport -> do
+        storeLogExists <- doesFileExist storeLogFilePath
+        unless storeLogExists $ exitError $ "Error: store log file " <> storeLogFilePath <> " does not exist."
+        confirmOrExit
+          ("Import store log " <> storeLogFilePath <> " to PostgreSQL database?")
+          "Import cancelled."
+        importToDatabase storeLogFilePath ini MCYesUp
+      SCExport -> do
+        storeLogExists <- doesFileExist storeLogFilePath
+        when storeLogExists $ exitError $ "Error: store log file " <> storeLogFilePath <> " already exists."
+        confirmOrExit
+          ("Export PostgreSQL database to store log " <> storeLogFilePath <> "?")
+          "Export cancelled."
+        exportFromDatabase storeLogFilePath ini MCConsole
     initializeServer InitOptions {enableStoreLog, signAlgorithm, ip, fqdn, filesPath, fileSizeQuota, webStaticPath = webStaticPath_} = do
       clearDirIfExists cfgPath
       clearDirIfExists logPath
@@ -104,20 +125,20 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
           \# available to the end users of the server.\n\
           \# LICENSE: https://github.com/simplex-chat/simplexmq/blob/stable/LICENSE\n\
           \# Include correct source code URI in case the server source code is modified in any way.\n\
-          \# source_code: https://github.com/simplex-chat/simplexmq\n\
+          \# source_code = https://github.com/simplex-chat/simplexmq\n\
           \\n\
           \# Declaring all below information is optional, any of these fields can be omitted.\n\
-          \# server_country: ISO-3166 2-letter code\n\
-          \# operator: entity (organization or person name)\n\
-          \# operator_country: ISO-3166 2-letter code\n\
-          \# website:\n\
-          \# admin_simplex: SimpleX address\n\
-          \# admin_email:\n\
-          \# complaints_simplex: SimpleX address\n\
-          \# complaints_email:\n\
-          \# hosting: entity (organization or person name)\n\
-          \# hosting_country: ISO-3166 2-letter code\n\
-          \# hosting_type: virtual\n\
+          \# server_country = ISO-3166 2-letter code\n\
+          \# operator = entity (organization or person name)\n\
+          \# operator_country = ISO-3166 2-letter code\n\
+          \# website =\n\
+          \# admin_simplex = SimpleX address\n\
+          \# admin_email =\n\
+          \# complaints_simplex = SimpleX address\n\
+          \# complaints_email =\n\
+          \# hosting = entity (organization or person name)\n\
+          \# hosting_country = ISO-3166 2-letter code\n\
+          \# hosting_type = virtual\n\
           \\n\
           \[STORE_LOG]\n\
           \# The server uses STM memory for persistence,\n\
@@ -125,55 +146,63 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
           \# This option enables saving memory to append only log,\n\
           \# and restoring it when the server is started.\n\
           \# Log is compacted on start (deleted objects are removed).\n"
-            <> ("enable: " <> onOff enableStoreLog <> "\n\n")
+            <> ("enable = " <> onOff enableStoreLog <> "\n\n")
+            <> "# File storage mode: `memory` or `database` (PostgreSQL).\n\
+               \store_files = memory\n\n\
+               \# Database connection settings for PostgreSQL database (`store_files = database`).\n\
+               \# db_connection = postgresql://xftp@/xftp_server_store\n\
+               \# db_schema = xftp_server\n\
+               \# db_pool_size = 10\n\n\
+               \# Write database changes to store log file\n\
+               \# db_store_log = off\n\n"
             <> "# Expire files after the specified number of hours.\n"
-            <> ("expire_files_hours: " <> tshow defFileExpirationHours <> "\n\n")
-            <> "log_stats: off\n\
+            <> ("expire_files_hours = " <> tshow defFileExpirationHours <> "\n\n")
+            <> "log_stats = off\n\
                \\n\
                \# Log interval for real-time Prometheus metrics\n\
-               \# prometheus_interval: 60\n\
+               \# prometheus_interval = 60\n\
                \\n\
                \[AUTH]\n\
                \# Set new_files option to off to completely prohibit uploading new files.\n\
                \# This can be useful when you want to decommission the server, but still allow downloading the existing files.\n\
-               \new_files: on\n\
+               \new_files = on\n\
                \\n\
                \# Use create_password option to enable basic auth to upload new files.\n\
                \# The password should be used as part of server address in client configuration:\n\
                \# xftp://fingerprint:password@host1,host2\n\
                \# The password will not be shared with file recipients, you must share it only\n\
                \# with the users who you want to allow uploading files to your server.\n\
-               \# create_password: password to upload files (any printable ASCII characters without whitespace, '@', ':' and '/')\n\
+               \# create_password = password to upload files (any printable ASCII characters without whitespace, '@', ':' and '/')\n\
                \\n\
-               \# control_port_admin_password:\n\
-               \# control_port_user_password:\n\
+               \# control_port_admin_password =\n\
+               \# control_port_user_password =\n\
                \\n\
                \[TRANSPORT]\n\
                \# host is only used to print server address on start\n"
-            <> ("host: " <> T.pack host <> "\n")
-            <> ("port: " <> T.pack defaultServerPort <> "\n")
-            <> "log_tls_errors: off\n\
-               \# control_port: 5226\n\
+            <> ("host = " <> T.pack host <> "\n")
+            <> ("port = " <> T.pack defaultServerPort <> "\n")
+            <> "log_tls_errors = off\n\
+               \# control_port = 5226\n\
                \\n\
                \[FILES]\n"
-            <> ("path: " <> T.pack filesPath <> "\n")
-            <> ("storage_quota: " <> safeDecodeUtf8 (strEncode fileSizeQuota) <> "\n")
+            <> ("path = " <> T.pack filesPath <> "\n")
+            <> ("storage_quota = " <> safeDecodeUtf8 (strEncode fileSizeQuota) <> "\n")
             <> "\n\
                \[INACTIVE_CLIENTS]\n\
                \# TTL and interval to check inactive clients\n\
-               \disconnect: off\n"
-            <> ("# ttl: " <> tshow (ttl defaultInactiveClientExpiration) <> "\n")
-            <> ("# check_interval: " <> tshow (checkInterval defaultInactiveClientExpiration) <> "\n")
+               \disconnect = off\n"
+            <> ("# ttl = " <> tshow (ttl defaultInactiveClientExpiration) <> "\n")
+            <> ("# check_interval = " <> tshow (checkInterval defaultInactiveClientExpiration) <> "\n")
             <> "\n\
                \[WEB]\n\
                \# Set path to generate static mini-site for server information\n"
-            <> ("static_path: " <> T.pack (fromMaybe defaultStaticPath webStaticPath_) <> "\n\n")
+            <> ("static_path = " <> T.pack (fromMaybe defaultStaticPath webStaticPath_) <> "\n\n")
             <> "# Run an embedded HTTP server on this port.\n\
-               \# http: 8000\n\n\
+               \# http = 8000\n\n\
                \# TLS credentials for HTTPS web server on the same port as XFTP.\n\
-               \# cert: " <> T.pack (cfgPath `combine` "web.crt") <> "\n\
-               \# key: " <> T.pack (cfgPath `combine` "web.key") <> "\n"
-    runServer ini = do
+               \# cert = " <> T.pack (cfgPath `combine` "web.crt") <> "\n\
+               \# key = " <> T.pack (cfgPath `combine` "web.key") <> "\n"
+    runServer StartOptions {confirmMigrations} ini = do
       hSetBuffering stdout LineBuffering
       hSetBuffering stderr LineBuffering
       fp <- checkSavedFingerprint cfgPath defaultX509Config
@@ -183,18 +212,24 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
       printServiceInfo serverVersion srv
       let information = serverPublicInfo ini
       printSourceCode (sourceCode <$> information)
-      printXFTPConfig serverConfig
-      case webStaticPath' of
-        Just path -> do
-          let onionHost =
-                either (const Nothing) (find isOnion) $
-                  strDecode @(L.NonEmpty TransportHost) . encodeUtf8 =<< lookupValue "TRANSPORT" "host" ini
-              webHttpPort = eitherToMaybe (lookupValue "WEB" "http" ini) >>= readMaybe . T.unpack
-          generateSite serverConfig information onionHost path
-          when (isJust webHttpPort || isJust webHttpsParams') $
-            serveStaticFiles EmbeddedWebParams {webStaticPath = path, webHttpPort, webHttpsParams = webHttpsParams'}
-        Nothing -> pure ()
-      runXFTPServer serverConfig
+      case readFileStoreType ini of
+        Left err -> error err
+        Right fsType -> do
+          checkFileStoreMode ini fsType storeLogFilePath
+          runWithStoreConfig fsType ini storeLogFilePath confirmMigrations $ \storeCfg -> do
+            let cfg = serverConfig storeCfg
+            printXFTPConfig cfg
+            case webStaticPath' of
+              Just path -> do
+                let onionHost =
+                      either (const Nothing) (find isOnion) $
+                        strDecode @(L.NonEmpty TransportHost) . encodeUtf8 =<< lookupValue "TRANSPORT" "host" ini
+                    webHttpPort = eitherToMaybe (lookupValue "WEB" "http" ini) >>= readMaybe . T.unpack
+                generateSite cfg information onionHost path
+                when (isJust webHttpPort || isJust webHttpsParams') $
+                  serveStaticFiles EmbeddedWebParams {webStaticPath = path, webHttpPort, webHttpsParams = webHttpsParams'}
+              Nothing -> pure ()
+            runXFTPServer cfg
       where
         isOnion = \case THOnionHost _ -> True; _ -> False
         enableStoreLog = settingIsOn "STORE_LOG" "enable" ini
@@ -236,11 +271,13 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
 
         webStaticPath' = eitherToMaybe $ T.unpack <$> lookupValue "WEB" "static_path" ini
 
-        serverConfig =
+        serverConfig :: XFTPStoreConfig s -> XFTPServerConfig s
+        serverConfig serverStoreCfg =
           XFTPServerConfig
             { xftpPort = T.unpack $ strictIni "TRANSPORT" "port" ini,
               controlPort = either (const Nothing) (Just . T.unpack) $ lookupValue "TRANSPORT" "control_port" ini,
               fileIdSize = 16,
+              serverStoreCfg,
               storeLogFile = enableStoreLog $> storeLogFilePath,
               filesPath = T.unpack $ strictIni "FILES" "path" ini,
               fileSizeQuota = either error unFileSize <$> strDecodeIni "FILES" "storage_quota" ini,
@@ -289,9 +326,16 @@ xftpServerCLI_ generateSite serveStaticFiles cfgPath logPath = do
 data CliCommand
   = Init InitOptions
   | OnlineCert CertOptions
-  | Start
+  | Start StartOptions
+  | Database StoreCmd
   | Delete
 
+data StoreCmd = SCImport | SCExport
+
+newtype StartOptions = StartOptions
+  { confirmMigrations :: MigrationConfirmation
+  }
+
 data InitOptions = InitOptions
   { enableStoreLog :: Bool,
     signAlgorithm :: SignAlgorithm,
@@ -308,7 +352,8 @@ cliCommandP cfgPath logPath iniFile =
   hsubparser
     ( command "init" (info (Init <$> initP) (progDesc $ "Initialize server - creates " <> cfgPath <> " and " <> logPath <> " directories and configuration files"))
         <> command "cert" (info (OnlineCert <$> certOptionsP) (progDesc $ "Generate new online TLS server credentials (configuration: " <> iniFile <> ")"))
-        <> command "start" (info (pure Start) (progDesc $ "Start server (configuration: " <> iniFile <> ")"))
+        <> command "start" (info (Start <$> startOptsP) (progDesc $ "Start server (configuration: " <> iniFile <> ")"))
+        <> command "database" (info (Database <$> storeCmdP) (progDesc "Import/export file store to/from PostgreSQL database"))
         <> command "delete" (info (pure Delete) (progDesc "Delete configuration and log files"))
     )
   where
@@ -375,3 +420,20 @@ cliCommandP cfgPath logPath iniFile =
               <> metavar "PATH"
           )
       pure InitOptions {enableStoreLog, signAlgorithm, ip, fqdn, filesPath, fileSizeQuota, webStaticPath}
+    startOptsP :: Parser StartOptions
+    startOptsP = do
+      confirmMigrations <-
+        option
+          parseConfirmMigrations
+          ( long "confirm-migrations"
+              <> metavar "CONFIRM_MIGRATIONS"
+              <> help "Confirm PostgreSQL database migration: up, down (default is manual confirmation)"
+              <> value MCConsole
+          )
+      pure StartOptions {confirmMigrations}
+    storeCmdP :: Parser StoreCmd
+    storeCmdP =
+      hsubparser
+        ( command "import" (info (pure SCImport) (progDesc "Import store log file into PostgreSQL database"))
+            <> command "export" (info (pure SCExport) (progDesc "Export PostgreSQL database to store log file"))
+        )

src/Simplex/FileTransfer/Server/Store.hs

@@ -1,51 +1,53 @@
 {-# LANGUAGE DataKinds #-}
 {-# LANGUAGE GADTs #-}
+{-# LANGUAGE KindSignatures #-}
 {-# LANGUAGE LambdaCase #-}
 {-# LANGUAGE NamedFieldPuns #-}
 {-# LANGUAGE OverloadedStrings #-}
 {-# LANGUAGE TupleSections #-}
+{-# LANGUAGE TypeFamilies #-}
 
 module Simplex.FileTransfer.Server.Store
-  ( FileStore (..),
+  ( FSType (..),
+    SFSType (..),
+    FileStoreClass (..),
     FileRec (..),
     FileRecipient (..),
+    STMFileStore (..),
     RoundedFileTime,
-    newFileStore,
-    addFile,
-    setFilePath,
-    addRecipient,
-    deleteFile,
-    blockFile,
-    deleteRecipient,
-    expiredFilePath,
-    getFile,
-    ackFile,
     fileTimePrecision,
   )
 where
 
+import Data.Kind (Type)
+
 import Control.Concurrent.STM
 import Control.Monad
 import qualified Data.Attoparsec.ByteString.Char8 as A
 import Data.Int (Int64)
+import qualified Data.Map.Strict as M
+import Data.Maybe (catMaybes, isJust)
 import Data.Set (Set)
 import qualified Data.Set as S
+import Data.Word (Word32)
 import Simplex.FileTransfer.Protocol (FileInfo (..), SFileParty (..), XFTPFileId)
 import Simplex.FileTransfer.Transport (XFTPErrorType (..))
 import qualified Simplex.Messaging.Crypto as C
 import Simplex.Messaging.Encoding.String
 import Simplex.Messaging.Protocol (BlockingInfo, RcvPublicAuthKey, RecipientId, SenderId)
 import Simplex.Messaging.Server.QueueStore (ServerEntityStatus (..))
+import Simplex.Messaging.Server.StoreLog (StoreLog, closeStoreLog)
+import System.IO (IOMode (..))
 import Simplex.Messaging.SystemTime
 import Simplex.Messaging.TMap (TMap)
 import qualified Simplex.Messaging.TMap as TM
-import Simplex.Messaging.Util (ifM, ($>>=))
+import Simplex.Messaging.Util (ifM)
 
-data FileStore = FileStore
-  { files :: TMap SenderId FileRec,
-    recipients :: TMap RecipientId (SenderId, RcvPublicAuthKey),
-    usedStorage :: TVar Int64
-  }
+data FSType = FSMemory | FSPostgres
+
+data SFSType :: FSType -> Type where
+  SFSMemory :: SFSType 'FSMemory
+  SFSPostgres :: SFSType 'FSPostgres
 
 data FileRec = FileRec
   { senderId :: SenderId,
@@ -59,28 +61,128 @@ data FileRec = FileRec
 type RoundedFileTime = RoundedSystemTime 3600
 
 fileTimePrecision :: Int64
-fileTimePrecision = 3600 -- truncate creation time to 1 hour
+fileTimePrecision = 3600
 
-data FileRecipient = FileRecipient RecipientId RcvPublicAuthKey
+data FileRecipient = FileRecipient RecipientId C.APublicAuthKey
   deriving (Show)
 
 instance StrEncoding FileRecipient where
   strEncode (FileRecipient rId rKey) = strEncode rId <> ":" <> strEncode rKey
   strP = FileRecipient <$> strP <* A.char ':' <*> strP
 
-newFileStore :: IO FileStore
-newFileStore = do
-  files <- TM.emptyIO
-  recipients <- TM.emptyIO
-  usedStorage <- newTVarIO 0
-  pure FileStore {files, recipients, usedStorage}
+class FileStoreClass s where
+  type FileStoreConfig s
+  newFileStore :: FileStoreConfig s -> IO s
+  closeFileStore :: s -> IO ()
+  addFile :: s -> SenderId -> FileInfo -> RoundedFileTime -> ServerEntityStatus -> IO (Either XFTPErrorType ())
+  setFilePath :: s -> SenderId -> FilePath -> IO (Either XFTPErrorType ())
+  addRecipient :: s -> SenderId -> FileRecipient -> IO (Either XFTPErrorType ())
+  deleteFile :: s -> SenderId -> IO (Either XFTPErrorType ())
+  deleteFiles :: s -> [SenderId] -> IO ()
+  deleteFiles s = mapM_ (void . deleteFile s)
+  blockFile :: s -> SenderId -> BlockingInfo -> Bool -> IO (Either XFTPErrorType ())
+  deleteRecipient :: s -> RecipientId -> FileRec -> IO ()
+  getFile :: s -> SFileParty p -> XFTPFileId -> IO (Either XFTPErrorType (FileRec, C.APublicAuthKey))
+  ackFile :: s -> RecipientId -> IO (Either XFTPErrorType ())
+  expiredFiles :: s -> Int64 -> Int -> IO [(SenderId, Maybe FilePath, Word32)]
+  getUsedStorage :: s -> IO Int64
+  getFileCount :: s -> IO Int
 
-addFile :: FileStore -> SenderId -> FileInfo -> RoundedFileTime -> ServerEntityStatus -> STM (Either XFTPErrorType ())
-addFile FileStore {files} sId fileInfo createdAt status =
-  ifM (TM.member sId files) (pure $ Left DUPLICATE_) $ do
-    f <- newFileRec sId fileInfo createdAt status
-    TM.insert sId f files
-    pure $ Right ()
+-- STM in-memory store
+
+data STMFileStore = STMFileStore
+  { files :: TMap SenderId FileRec,
+    recipients :: TMap RecipientId (SenderId, RcvPublicAuthKey),
+    stmStoreLog :: TVar (Maybe (StoreLog 'WriteMode))
+  }
+
+instance FileStoreClass STMFileStore where
+  type FileStoreConfig STMFileStore = ()
+
+  newFileStore () = do
+    files <- TM.emptyIO
+    recipients <- TM.emptyIO
+    stmStoreLog <- newTVarIO Nothing
+    pure STMFileStore {files, recipients, stmStoreLog}
+
+  closeFileStore STMFileStore {stmStoreLog} = readTVarIO stmStoreLog >>= mapM_ closeStoreLog
+
+  addFile STMFileStore {files} sId fileInfo createdAt status = atomically $
+    ifM (TM.member sId files) (pure $ Left DUPLICATE_) $ do
+      f <- newFileRec sId fileInfo createdAt status
+      TM.insert sId f files
+      pure $ Right ()
+
+  setFilePath st sId fPath = atomically $
+    withFile st sId $ \FileRec {filePath, fileStatus} -> do
+      readTVar filePath >>= \case
+        Just _ -> pure $ Left AUTH
+        Nothing ->
+          readTVar fileStatus >>= \case
+            EntityActive -> do
+              writeTVar filePath (Just fPath)
+              pure $ Right ()
+            _ -> pure $ Left AUTH
+
+  addRecipient st@STMFileStore {recipients} senderId (FileRecipient rId rKey) = atomically $
+    withFile st senderId $ \FileRec {recipientIds} -> do
+      rIds <- readTVar recipientIds
+      mem <- TM.member rId recipients
+      if rId `S.member` rIds || mem
+        then pure $ Left DUPLICATE_
+        else do
+          writeTVar recipientIds $! S.insert rId rIds
+          TM.insert rId (senderId, rKey) recipients
+          pure $ Right ()
+
+  deleteFile STMFileStore {files, recipients} senderId = atomically $ do
+    TM.lookupDelete senderId files >>= \case
+      Just FileRec {recipientIds} -> do
+        readTVar recipientIds >>= mapM_ (`TM.delete` recipients)
+        pure $ Right ()
+      _ -> pure $ Left AUTH
+
+  blockFile st senderId info _deleted = atomically $
+    withFile st senderId $ \FileRec {fileStatus} -> do
+      writeTVar fileStatus $! EntityBlocked info
+      pure $ Right ()
+
+  deleteRecipient STMFileStore {recipients} rId FileRec {recipientIds} = atomically $ do
+    TM.delete rId recipients
+    modifyTVar' recipientIds $ S.delete rId
+
+  getFile st party fId = atomically $ case party of
+    SFSender -> withFile st fId $ pure . Right . (\f -> (f, sndKey $ fileInfo f))
+    SFRecipient ->
+      TM.lookup fId (recipients st) >>= \case
+        Just (sId, rKey) -> withFile st sId $ pure . Right . (,rKey)
+        _ -> pure $ Left AUTH
+
+  ackFile st@STMFileStore {recipients} recipientId = atomically $ do
+    TM.lookupDelete recipientId recipients >>= \case
+      Just (sId, _) ->
+        withFile st sId $ \FileRec {recipientIds} -> do
+          modifyTVar' recipientIds $ S.delete recipientId
+          pure $ Right ()
+      _ -> pure $ Left AUTH
+
+  expiredFiles STMFileStore {files} old _limit = do
+    fs <- readTVarIO files
+    fmap catMaybes . forM (M.toList fs) $ \(sId, FileRec {fileInfo = FileInfo {size}, filePath, createdAt = RoundedSystemTime createdAt}) ->
+      if createdAt + fileTimePrecision < old
+        then do
+          path <- readTVarIO filePath
+          pure $ Just (sId, path, size)
+        else pure Nothing
+
+  getUsedStorage STMFileStore {files} = foldM addSize 0 =<< readTVarIO files
+    where
+      addSize acc FileRec {fileInfo = FileInfo {size}, filePath} =
+        ifM (isJust <$> readTVarIO filePath) (pure $! acc + fromIntegral size) (pure acc)
+
+  getFileCount STMFileStore {files} = M.size <$> readTVarIO files
+
+-- Internal STM helpers
 
 newFileRec :: SenderId -> FileInfo -> RoundedFileTime -> ServerEntityStatus -> STM FileRec
 newFileRec senderId fileInfo createdAt status = do
@@ -89,75 +191,8 @@ newFileRec senderId fileInfo createdAt status = do
   fileStatus <- newTVar status
   pure FileRec {senderId, fileInfo, filePath, recipientIds, createdAt, fileStatus}
 
-setFilePath :: FileStore -> SenderId -> FilePath -> STM (Either XFTPErrorType ())
-setFilePath st sId fPath =
-  withFile st sId $ \FileRec {fileInfo, filePath} -> do
-    writeTVar filePath (Just fPath)
-    modifyTVar' (usedStorage st) (+ fromIntegral (size fileInfo))
-    pure $ Right ()
-
-addRecipient :: FileStore -> SenderId -> FileRecipient -> STM (Either XFTPErrorType ())
-addRecipient st@FileStore {recipients} senderId (FileRecipient rId rKey) =
-  withFile st senderId $ \FileRec {recipientIds} -> do
-    rIds <- readTVar recipientIds
-    mem <- TM.member rId recipients
-    if rId `S.member` rIds || mem
-      then pure $ Left DUPLICATE_
-      else do
-        writeTVar recipientIds $! S.insert rId rIds
-        TM.insert rId (senderId, rKey) recipients
-        pure $ Right ()
-
--- this function must be called after the file is deleted from the file system
-deleteFile :: FileStore -> SenderId -> STM (Either XFTPErrorType ())
-deleteFile FileStore {files, recipients, usedStorage} senderId = do
-  TM.lookupDelete senderId files >>= \case
-    Just FileRec {fileInfo, recipientIds} -> do
-      readTVar recipientIds >>= mapM_ (`TM.delete` recipients)
-      modifyTVar' usedStorage $ subtract (fromIntegral $ size fileInfo)
-      pure $ Right ()
-    _ -> pure $ Left AUTH
-
--- this function must be called after the file is deleted from the file system
-blockFile :: FileStore -> SenderId -> BlockingInfo -> Bool -> STM (Either XFTPErrorType ())
-blockFile st@FileStore {usedStorage} senderId info deleted =
-  withFile st senderId $ \FileRec {fileInfo, fileStatus} -> do
-    when deleted $ modifyTVar' usedStorage $ subtract (fromIntegral $ size fileInfo)
-    writeTVar fileStatus $! EntityBlocked info
-    pure $ Right ()
-
-deleteRecipient :: FileStore -> RecipientId -> FileRec -> STM ()
-deleteRecipient FileStore {recipients} rId FileRec {recipientIds} = do
-  TM.delete rId recipients
-  modifyTVar' recipientIds $ S.delete rId
-
-getFile :: FileStore -> SFileParty p -> XFTPFileId -> STM (Either XFTPErrorType (FileRec, C.APublicAuthKey))
-getFile st party fId = case party of
-  SFSender -> withFile st fId $ pure . Right . (\f -> (f, sndKey $ fileInfo f))
-  SFRecipient ->
-    TM.lookup fId (recipients st) >>= \case
-      Just (sId, rKey) -> withFile st sId $ pure . Right . (,rKey)
-      _ -> pure $ Left AUTH
-
-expiredFilePath :: FileStore -> XFTPFileId -> Int64 -> STM (Maybe (Maybe FilePath))
-expiredFilePath FileStore {files} sId old =
-  TM.lookup sId files
-    $>>= \FileRec {filePath, createdAt = RoundedSystemTime createdAt} ->
-      if createdAt + fileTimePrecision < old
-        then Just <$> readTVar filePath
-        else pure Nothing
-
-ackFile :: FileStore -> RecipientId -> STM (Either XFTPErrorType ())
-ackFile st@FileStore {recipients} recipientId = do
-  TM.lookupDelete recipientId recipients >>= \case
-    Just (sId, _) ->
-      withFile st sId $ \FileRec {recipientIds} -> do
-        modifyTVar' recipientIds $ S.delete recipientId
-        pure $ Right ()
-    _ -> pure $ Left AUTH
-
-withFile :: FileStore -> SenderId -> (FileRec -> STM (Either XFTPErrorType a)) -> STM (Either XFTPErrorType a)
-withFile FileStore {files} sId a =
+withFile :: STMFileStore -> SenderId -> (FileRec -> STM (Either XFTPErrorType a)) -> STM (Either XFTPErrorType a)
+withFile STMFileStore {files} sId a =
   TM.lookup sId files >>= \case
     Just f -> a f
     _ -> pure $ Left AUTH

src/Simplex/FileTransfer/Server/Store/Postgres.hs

@@ -0,0 +1,370 @@
+{-# LANGUAGE BangPatterns #-}
+{-# LANGUAGE DataKinds #-}
+{-# LANGUAGE GADTs #-}
+{-# LANGUAGE LambdaCase #-}
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE ScopedTypeVariables #-}
+{-# LANGUAGE TypeFamilies #-}
+
+module Simplex.FileTransfer.Server.Store.Postgres
+  ( PostgresFileStore (..),
+    importFileStore,
+    exportFileStore,
+  )
+where
+
+import qualified Control.Exception as E
+import Control.Logger.Simple
+import Control.Monad
+import Control.Monad.Except
+import Control.Monad.IO.Class
+import Control.Monad.Trans.Except (throwE)
+import Data.ByteString (ByteString)
+import qualified Data.ByteString.Char8 as B
+import Data.ByteString.Builder (Builder)
+import qualified Data.ByteString.Builder as BB
+import qualified Data.ByteString.Lazy as LB
+import Data.Functor (($>))
+import Data.Int (Int32, Int64)
+import Data.List (intersperse)
+import qualified Data.List.NonEmpty as L
+import qualified Data.Map.Strict as M
+import qualified Data.Set as S
+import Data.Text (Text)
+import Data.Word (Word32)
+import Database.PostgreSQL.Simple (Binary (..), In (..), Only (..), SqlError, (:.) (..))
+import qualified Database.PostgreSQL.Simple as DB
+import qualified Database.PostgreSQL.Simple.Copy as DB
+import Database.PostgreSQL.Simple.Errors (ConstraintViolation (..), constraintViolation)
+import Database.PostgreSQL.Simple.ToField (Action (..), ToField (..))
+import GHC.IO (catchAny)
+import Simplex.FileTransfer.Protocol (FileInfo (..), SFileParty (..))
+import Simplex.FileTransfer.Server.Store
+import Simplex.FileTransfer.Server.Store.Postgres.Config
+import Simplex.FileTransfer.Server.Store.Postgres.Migrations (xftpServerMigrations)
+import Simplex.FileTransfer.Server.StoreLog
+import Simplex.FileTransfer.Transport (XFTPErrorType (..))
+import Simplex.Messaging.Agent.Store.Postgres (closeDBStore, createDBStore)
+import Simplex.Messaging.Agent.Store.Postgres.Common (DBStore, withTransaction)
+import Simplex.Messaging.Agent.Store.Postgres.Options (DBOpts (..))
+import Simplex.Messaging.Agent.Store.Shared (MigrationConfig (..), MigrationConfirmation (..))
+import qualified Simplex.Messaging.Crypto as C
+import Simplex.Messaging.Protocol (RcvPublicAuthKey, RecipientId, SenderId)
+import Simplex.Messaging.Transport (EntityId (..))
+import Simplex.Messaging.Server.QueueStore (ServerEntityStatus (..))
+import Simplex.Messaging.Server.QueueStore.Postgres ()
+import Simplex.Messaging.Server.StoreLog (openWriteStoreLog)
+import Simplex.Messaging.Util (firstRow, tshow)
+import System.Directory (renameFile)
+import System.Exit (exitFailure)
+import System.IO (IOMode (..), hFlush, stdout)
+import UnliftIO.STM
+
+data PostgresFileStore = PostgresFileStore
+  { dbStore :: DBStore,
+    dbStoreLog :: Maybe (StoreLog 'WriteMode)
+  }
+
+instance FileStoreClass PostgresFileStore where
+  type FileStoreConfig PostgresFileStore = PostgresFileStoreCfg
+
+  newFileStore PostgresFileStoreCfg {dbOpts, dbStoreLogPath, confirmMigrations} = do
+    dbStore <- either err pure =<< createDBStore dbOpts xftpServerMigrations (MigrationConfig confirmMigrations Nothing)
+    dbStoreLog <- mapM (openWriteStoreLog True) dbStoreLogPath
+    pure PostgresFileStore {dbStore, dbStoreLog}
+    where
+      err e = do
+        logError $ "STORE: newFileStore, error opening PostgreSQL database, " <> tshow e
+        exitFailure
+
+  closeFileStore PostgresFileStore {dbStore, dbStoreLog} = do
+    closeDBStore dbStore
+    mapM_ closeStoreLog dbStoreLog
+
+  addFile st sId fileInfo@FileInfo {sndKey, size, digest} createdAt status =
+    E.uninterruptibleMask_ $ runExceptT $ do
+      void $ withDB "addFile" st $ \db ->
+        E.try
+          ( DB.execute
+              db
+              "INSERT INTO files (sender_id, file_size, file_digest, sender_key, created_at, status) VALUES (?,?,?,?,?,?)"
+              (sId, (fromIntegral size :: Int32), Binary digest, Binary (C.encodePubKey sndKey), createdAt, status)
+          )
+          >>= either handleDuplicate (pure . Right)
+      withLog "addFile" st $ \s -> logAddFile s sId fileInfo createdAt status
+
+  setFilePath st sId fPath = E.uninterruptibleMask_ $ runExceptT $ do
+    assertUpdated $ withDB' "setFilePath" st $ \db ->
+      DB.execute db "UPDATE files SET file_path = ? WHERE sender_id = ? AND file_path IS NULL AND status = 'active'" (fPath, sId)
+    withLog "setFilePath" st $ \s -> logPutFile s sId fPath
+
+  addRecipient st senderId (FileRecipient rId rKey) = E.uninterruptibleMask_ $ runExceptT $ do
+    void $ withDB "addRecipient" st $ \db ->
+      E.try
+        ( DB.execute
+            db
+            "INSERT INTO recipients (recipient_id, sender_id, recipient_key) VALUES (?,?,?)"
+            (rId, senderId, Binary (C.encodePubKey rKey))
+        )
+        >>= either handleDuplicate (pure . Right)
+    withLog "addRecipient" st $ \s -> logAddRecipients s senderId (pure $ FileRecipient rId rKey)
+
+  deleteFile st sId = E.uninterruptibleMask_ $ runExceptT $ do
+    assertUpdated $ withDB' "deleteFile" st $ \db ->
+      DB.execute db "DELETE FROM files WHERE sender_id = ?" (Only sId)
+    withLog "deleteFile" st $ \s -> logDeleteFile s sId
+
+  deleteFiles st sIds = E.uninterruptibleMask_ $ do
+    withTransaction (dbStore st) $ \db ->
+      DB.execute db "DELETE FROM files WHERE sender_id IN ?" (Only (In sIds))
+    withLog "deleteFiles" st $ \s -> mapM_ (logDeleteFile s) sIds
+
+  blockFile st sId info _deleted = E.uninterruptibleMask_ $ runExceptT $ do
+    assertUpdated $ withDB' "blockFile" st $ \db ->
+      DB.execute db "UPDATE files SET status = ? WHERE sender_id = ?" (EntityBlocked info, sId)
+    withLog "blockFile" st $ \s -> logBlockFile s sId info
+
+  deleteRecipient st rId _fr =
+    void $ runExceptT $ withDB' "deleteRecipient" st $ \db ->
+      DB.execute db "DELETE FROM recipients WHERE recipient_id = ?" (Only rId)
+
+  getFile st party fId = runExceptT $ case party of
+    SFSender -> do
+      row <- loadFileRow "SELECT sender_id, file_size, file_digest, sender_key, file_path, created_at, status FROM files WHERE sender_id = ?"
+      fr <- ExceptT $ rowToFileRec row
+      pure (fr, sndKey (fileInfo fr))
+    SFRecipient -> do
+      row :. Only rcpKeyBs <-
+        loadFileRow
+          "SELECT f.sender_id, f.file_size, f.file_digest, f.sender_key, f.file_path, f.created_at, f.status, r.recipient_key FROM files f JOIN recipients r ON r.sender_id = f.sender_id WHERE r.recipient_id = ?"
+      fr <- ExceptT $ rowToFileRec row
+      rcpKey <- either (const $ throwE INTERNAL) pure $ C.decodePubKey rcpKeyBs
+      pure (fr, rcpKey)
+    where
+      loadFileRow :: DB.FromRow r => DB.Query -> ExceptT XFTPErrorType IO r
+      loadFileRow q =
+        withDB "getFile" st $ \db ->
+          firstRow id AUTH $ DB.query db q (Only fId)
+
+  ackFile st rId = E.uninterruptibleMask_ $ runExceptT $ do
+    assertUpdated $ withDB' "ackFile" st $ \db ->
+      DB.execute db "DELETE FROM recipients WHERE recipient_id = ?" (Only rId)
+    withLog "ackFile" st $ \s -> logAckFile s rId
+
+  expiredFiles st old limit =
+    fmap toResult $ withTransaction (dbStore st) $ \db ->
+      DB.query
+        db
+        "SELECT sender_id, file_path, file_size FROM files WHERE created_at + ? < ? ORDER BY created_at LIMIT ?"
+        (fileTimePrecision, old, limit)
+    where
+      toResult :: [(SenderId, Maybe FilePath, Int32)] -> [(SenderId, Maybe FilePath, Word32)]
+      toResult = map (\(sId, path, size) -> (sId, path, fromIntegral size))
+
+  getUsedStorage st =
+    withTransaction (dbStore st) $ \db -> do
+      [Only total] <- DB.query_ db "SELECT COALESCE(SUM(file_size::BIGINT), 0)::BIGINT FROM files WHERE file_path IS NOT NULL"
+      pure total
+
+  getFileCount st =
+    withTransaction (dbStore st) $ \db -> do
+      [Only count] <- DB.query_ db "SELECT COUNT(*) FROM files"
+      pure (fromIntegral (count :: Int64))
+
+-- Internal helpers
+
+mkFileRec :: SenderId -> FileInfo -> Maybe FilePath -> RoundedFileTime -> ServerEntityStatus -> IO FileRec
+mkFileRec senderId fileInfo path createdAt status = do
+  filePath <- newTVarIO path
+  recipientIds <- newTVarIO S.empty
+  fileStatus <- newTVarIO status
+  pure FileRec {senderId, fileInfo, filePath, recipientIds, createdAt, fileStatus}
+
+type FileRecRow = (SenderId, Int32, ByteString, ByteString, Maybe FilePath, RoundedFileTime, ServerEntityStatus)
+
+rowToFileRec :: FileRecRow -> IO (Either XFTPErrorType FileRec)
+rowToFileRec (sId, size, digest, sndKeyBs, path, createdAt, status) =
+  case C.decodePubKey sndKeyBs of
+    Right sndKey -> do
+      let fileInfo = FileInfo {sndKey, size = fromIntegral size, digest}
+      Right <$> mkFileRec sId fileInfo path createdAt status
+    Left _ -> pure $ Left INTERNAL
+
+-- DB helpers
+
+withDB :: forall a. Text -> PostgresFileStore -> (DB.Connection -> IO (Either XFTPErrorType a)) -> ExceptT XFTPErrorType IO a
+withDB op st action =
+  ExceptT $ E.try (withTransaction (dbStore st) action) >>= either logErr pure
+  where
+    logErr :: E.SomeException -> IO (Either XFTPErrorType a)
+    logErr e = logError ("STORE: " <> err) $> Left INTERNAL
+      where
+        err = op <> ", withDB, " <> tshow e
+
+withDB' :: Text -> PostgresFileStore -> (DB.Connection -> IO a) -> ExceptT XFTPErrorType IO a
+withDB' op st action = withDB op st $ fmap Right . action
+
+assertUpdated :: ExceptT XFTPErrorType IO Int64 -> ExceptT XFTPErrorType IO ()
+assertUpdated = (>>= \n -> when (n == 0) (throwE AUTH))
+
+handleDuplicate :: SqlError -> IO (Either XFTPErrorType a)
+handleDuplicate e = case constraintViolation e of
+  Just (UniqueViolation _) -> pure $ Left DUPLICATE_
+  Just (ForeignKeyViolation _ _) -> pure $ Left AUTH
+  _ -> E.throwIO e
+
+withLog :: MonadIO m => Text -> PostgresFileStore -> (StoreLog 'WriteMode -> IO ()) -> m ()
+withLog op PostgresFileStore {dbStoreLog} action =
+  forM_ dbStoreLog $ \sl -> liftIO $ action sl `catchAny` \e ->
+    logWarn $ "STORE: " <> op <> ", withLog, " <> tshow e
+
+-- Import: StoreLog -> PostgreSQL
+
+importFileStore :: FilePath -> PostgresFileStoreCfg -> IO ()
+importFileStore storeLogFilePath dbCfg = do
+  putStrLn $ "Reading store log: " <> storeLogFilePath
+  stmStore <- newFileStore () :: IO STMFileStore
+  sl <- readWriteFileStore storeLogFilePath stmStore
+  closeStoreLog sl
+  allFiles <- readTVarIO (files stmStore)
+  allRcps <- readTVarIO (recipients stmStore)
+  let fileCount = M.size allFiles
+      rcpCount = M.size allRcps
+  putStrLn $ "Loaded " <> show fileCount <> " files, " <> show rcpCount <> " recipients."
+  let dbCfg' = dbCfg {dbOpts = (dbOpts dbCfg) {createSchema = True}, confirmMigrations = MCYesUp}
+  pgStore <- newFileStore dbCfg' :: IO PostgresFileStore
+  existingCount <- getFileCount pgStore
+  when (existingCount > 0) $ do
+    putStrLn $ "WARNING: database already contains " <> show existingCount <> " files. Import will fail on duplicate keys."
+    putStrLn "Drop the existing schema first or use a fresh database."
+    exitFailure
+  putStrLn "Importing files..."
+  fCnt <- withTransaction (dbStore pgStore) $ \db -> do
+    DB.copy_
+      db
+      "COPY files (sender_id, file_size, file_digest, sender_key, file_path, created_at, status) FROM STDIN WITH (FORMAT csv)"
+    iforM_ (M.toList allFiles) $ \i (sId, fr) -> do
+      DB.putCopyData db =<< fileRecToCSV sId fr
+      when (i > 0 && i `mod` 10000 == 0) $ putStr ("  " <> show i <> " files\r") >> hFlush stdout
+    DB.putCopyEnd db
+    [Only cnt] <- DB.query_ db "SELECT COUNT(*) FROM files"
+    pure (cnt :: Int64)
+  putStrLn $ "Imported " <> show fCnt <> " files."
+  putStrLn "Importing recipients..."
+  rCnt <- withTransaction (dbStore pgStore) $ \db -> do
+    DB.copy_
+      db
+      "COPY recipients (recipient_id, sender_id, recipient_key) FROM STDIN WITH (FORMAT csv)"
+    iforM_ (M.toList allRcps) $ \i (rId, (sId, rKey)) -> do
+      DB.putCopyData db $ recipientToCSV rId sId rKey
+      when (i > 0 && i `mod` 10000 == 0) $ putStr ("  " <> show i <> " recipients\r") >> hFlush stdout
+    DB.putCopyEnd db
+    [Only cnt] <- DB.query_ db "SELECT COUNT(*) FROM recipients"
+    pure (cnt :: Int64)
+  putStrLn $ "Imported " <> show rCnt <> " recipients."
+  when (fromIntegral fileCount /= fCnt) $
+    putStrLn $ "WARNING: expected " <> show fileCount <> " files, got " <> show fCnt
+  when (fromIntegral rcpCount /= rCnt) $
+    putStrLn $ "WARNING: expected " <> show rcpCount <> " recipients, got " <> show rCnt
+  closeFileStore pgStore
+  renameFile storeLogFilePath (storeLogFilePath <> ".bak")
+  putStrLn $ "Store log renamed to " <> storeLogFilePath <> ".bak"
+
+-- Export: PostgreSQL -> StoreLog
+
+exportFileStore :: FilePath -> PostgresFileStoreCfg -> IO ()
+exportFileStore storeLogFilePath dbCfg = do
+  pgStore <- newFileStore dbCfg :: IO PostgresFileStore
+  sl <- openWriteStoreLog False storeLogFilePath
+  -- Fold 1: stream files, write FNEW + FPUT per file
+  putStrLn "Exporting files..."
+  !fCnt <- withTransaction (dbStore pgStore) $ \db ->
+    DB.fold_
+      db
+      "SELECT sender_id, file_size, file_digest, sender_key, file_path, created_at, status FROM files ORDER BY created_at"
+      (0 :: Int)
+      ( \(!fc) (sId, size :: Int32, digest :: ByteString, sndKeyBs :: ByteString, path :: Maybe String, createdAt, status) ->
+          case C.decodePubKey sndKeyBs of
+            Right sndKey -> do
+              let fileInfo = FileInfo {sndKey, size = fromIntegral size, digest}
+              logAddFile sl sId fileInfo createdAt status
+              forM_ path $ logPutFile sl sId
+              pure (fc + 1)
+            Left _ -> do
+              putStrLn $ "WARNING: invalid sender key for " <> show sId
+              pure fc
+      )
+  -- Fold 2: stream recipients ordered by sender_id, flush FADD on sender change
+  putStrLn "Exporting recipients..."
+  !rCnt <- withTransaction (dbStore pgStore) $ \db ->
+    DB.fold_
+      db
+      "SELECT sender_id, recipient_id, recipient_key FROM recipients ORDER BY sender_id"
+      (Nothing :: Maybe SenderId, [] :: [FileRecipient], 0 :: Int)
+      ( \(!prevSId, !buf, !rc) (sId, rId, rKeyBs :: ByteString) ->
+          case C.decodePubKey rKeyBs of
+            Right rKey -> do
+              let rcp = FileRecipient rId rKey
+              case prevSId of
+                Just prev | prev /= sId -> do
+                  forM_ (L.nonEmpty buf) $ logAddRecipients sl prev
+                  pure (Just sId, [rcp], rc + length buf)
+                _ -> pure (Just sId, rcp : buf, rc)
+            Left _ -> putStrLn ("WARNING: invalid recipient key for " <> show rId) $> (prevSId, buf, rc)
+      )
+      >>= \(lastSId, buf, rc) -> do
+        forM_ lastSId $ \sId -> forM_ (L.nonEmpty buf) $ logAddRecipients sl sId
+        pure (rc + length buf)
+  closeStoreLog sl
+  closeFileStore pgStore
+  putStrLn $ "Exported " <> show fCnt <> " files, " <> show rCnt <> " recipients to " <> storeLogFilePath
+
+-- CSV helpers for COPY protocol
+
+iforM_ :: Monad m => [a] -> (Int -> a -> m ()) -> m ()
+iforM_ xs f = zipWithM_ f [0 ..] xs
+
+fileRecToCSV :: SenderId -> FileRec -> IO ByteString
+fileRecToCSV sId FileRec {fileInfo = FileInfo {sndKey, size, digest}, filePath, createdAt, fileStatus} = do
+  path <- readTVarIO filePath
+  status <- readTVarIO fileStatus
+  pure $ LB.toStrict $ BB.toLazyByteString $ mconcat (BB.char7 ',' `intersperse` fields path status) <> BB.char7 '\n'
+  where
+    fields path status =
+      [ renderField (toField (Binary (unEntityId sId))),
+        renderField (toField (fromIntegral size :: Int32)),
+        renderField (toField (Binary digest)),
+        renderField (toField (Binary (C.encodePubKey sndKey))),
+        nullable (toField <$> path),
+        renderField (toField createdAt),
+        quotedField (toField status)
+      ]
+
+recipientToCSV :: RecipientId -> SenderId -> RcvPublicAuthKey -> ByteString
+recipientToCSV rId sId rKey =
+  LB.toStrict $ BB.toLazyByteString $ mconcat (BB.char7 ',' `intersperse` fields) <> BB.char7 '\n'
+  where
+    fields =
+      [ renderField (toField (Binary (unEntityId rId))),
+        renderField (toField (Binary (unEntityId sId))),
+        renderField (toField (Binary (C.encodePubKey rKey)))
+      ]
+
+renderField :: Action -> Builder
+renderField = \case
+  Plain bld -> bld
+  Escape s -> BB.byteString s
+  EscapeByteA s -> BB.string7 "\\x" <> BB.byteStringHex s
+  EscapeIdentifier s -> BB.byteString s
+  Many as -> mconcat (map renderField as)
+
+nullable :: Maybe Action -> Builder
+nullable = maybe mempty renderField
+
+quotedField :: Action -> Builder
+quotedField a = BB.char7 '"' <> escapeQuotes (renderField a) <> BB.char7 '"'
+  where
+    escapeQuotes bld =
+      let bs = LB.toStrict $ BB.toLazyByteString bld
+       in BB.byteString $ B.concatMap (\c -> if c == '"' then "\"\"" else B.singleton c) bs

src/Simplex/FileTransfer/Server/Store/Postgres/Config.hs

@@ -0,0 +1,25 @@
+{-# LANGUAGE OverloadedStrings #-}
+
+module Simplex.FileTransfer.Server.Store.Postgres.Config
+  ( PostgresFileStoreCfg (..),
+    defaultXFTPDBOpts,
+  )
+where
+
+import Simplex.Messaging.Agent.Store.Postgres.Options (DBOpts (..))
+import Simplex.Messaging.Agent.Store.Shared (MigrationConfirmation)
+
+data PostgresFileStoreCfg = PostgresFileStoreCfg
+  { dbOpts :: DBOpts,
+    dbStoreLogPath :: Maybe FilePath,
+    confirmMigrations :: MigrationConfirmation
+  }
+
+defaultXFTPDBOpts :: DBOpts
+defaultXFTPDBOpts =
+  DBOpts
+    { connstr = "postgresql://xftp@/xftp_server_store",
+      schema = "xftp_server",
+      poolSize = 10,
+      createSchema = False
+    }

src/Simplex/FileTransfer/Server/Store/Postgres/Migrations.hs

@@ -0,0 +1,47 @@
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE QuasiQuotes #-}
+
+module Simplex.FileTransfer.Server.Store.Postgres.Migrations
+  ( xftpServerMigrations,
+  )
+where
+
+import Data.List (sortOn)
+import Data.Text (Text)
+import Simplex.Messaging.Agent.Store.Shared
+import Text.RawString.QQ (r)
+
+xftpSchemaMigrations :: [(String, Text, Maybe Text)]
+xftpSchemaMigrations =
+  [ ("20260325_initial", m20260325_initial, Nothing)
+  ]
+
+-- | The list of migrations in ascending order by date
+xftpServerMigrations :: [Migration]
+xftpServerMigrations = sortOn name $ map migration xftpSchemaMigrations
+  where
+    migration (name, up, down) = Migration {name, up, down = down}
+
+m20260325_initial :: Text
+m20260325_initial =
+  [r|
+CREATE TABLE files (
+  sender_id BYTEA NOT NULL PRIMARY KEY,
+  file_size INTEGER NOT NULL,
+  file_digest BYTEA NOT NULL,
+  sender_key BYTEA NOT NULL,
+  file_path TEXT,
+  created_at BIGINT NOT NULL,
+  status TEXT NOT NULL DEFAULT 'active'
+);
+
+CREATE TABLE recipients (
+  recipient_id BYTEA NOT NULL PRIMARY KEY,
+  sender_id BYTEA NOT NULL REFERENCES files ON DELETE CASCADE,
+  recipient_key BYTEA NOT NULL
+);
+
+CREATE INDEX idx_recipients_sender_id ON recipients (sender_id);
+CREATE INDEX idx_files_created_at ON files (created_at);
+|]

src/Simplex/FileTransfer/Server/StoreLog.hs

@@ -10,6 +10,7 @@ module Simplex.FileTransfer.Server.StoreLog
     FileStoreLogRecord (..),
     closeStoreLog,
     readWriteFileStore,
+    writeFileStore,
     logAddFile,
     logPutFile,
     logAddRecipients,
@@ -32,6 +33,7 @@ import Data.Map.Strict (Map)
 import qualified Data.Map.Strict as M
 import Simplex.FileTransfer.Protocol (FileInfo (..))
 import Simplex.FileTransfer.Server.Store
+import Simplex.FileTransfer.Transport (XFTPErrorType (..))
 import Simplex.Messaging.Encoding.String
 import Simplex.Messaging.Protocol (BlockingInfo, RcvPublicAuthKey, RecipientId, SenderId)
 import Simplex.Messaging.Server.QueueStore (ServerEntityStatus (..))
@@ -87,20 +89,22 @@ logBlockFile s fId = logFileStoreRecord s . BlockFile fId
 logAckFile :: StoreLog 'WriteMode -> RecipientId -> IO ()
 logAckFile s = logFileStoreRecord s . AckFile
 
-readWriteFileStore :: FilePath -> FileStore -> IO (StoreLog 'WriteMode)
+readWriteFileStore :: FilePath -> STMFileStore -> IO (StoreLog 'WriteMode)
 readWriteFileStore = readWriteStoreLog readFileStore writeFileStore
 
-readFileStore :: FilePath -> FileStore -> IO ()
+readFileStore :: FilePath -> STMFileStore -> IO ()
 readFileStore f st = mapM_ (addFileLogRecord . LB.toStrict) . LB.lines =<< LB.readFile f
   where
     addFileLogRecord s = case strDecode s of
       Left e -> B.putStrLn $ "Log parsing error (" <> B.pack e <> "): " <> B.take 100 s
       Right lr ->
-        atomically (addToStore lr) >>= \case
+        addToStore lr >>= \case
           Left e -> B.putStrLn $ "Log processing error (" <> bshow e <> "): " <> B.take 100 s
           _ -> pure ()
     addToStore = \case
-      AddFile sId file createdAt status -> addFile st sId file createdAt status
+      AddFile sId file createdAt status
+        | size file > 0 -> addFile st sId file createdAt status
+        | otherwise -> pure $ Left SIZE
       PutFile qId path -> setFilePath st qId path
       AddRecipients sId rcps -> runExceptT $ addRecipients sId rcps
       DeleteFile sId -> deleteFile st sId
@@ -108,8 +112,8 @@ readFileStore f st = mapM_ (addFileLogRecord . LB.toStrict) . LB.lines =<< LB.re
       AckFile rId -> ackFile st rId
     addRecipients sId rcps = mapM_ (ExceptT . addRecipient st sId) rcps
 
-writeFileStore :: StoreLog 'WriteMode -> FileStore -> IO ()
-writeFileStore s FileStore {files, recipients} = do
+writeFileStore :: StoreLog 'WriteMode -> STMFileStore -> IO ()
+writeFileStore s STMFileStore {files, recipients} = do
   allRcps <- readTVarIO recipients
   readTVarIO files >>= mapM_ (logFile allRcps)
   where

src/Simplex/FileTransfer/Types.hs

@@ -46,6 +46,7 @@ import Simplex.Messaging.Encoding
 import Simplex.Messaging.Encoding.String
 import Simplex.Messaging.Parsers
 import Simplex.Messaging.Protocol (XFTPServer)
+import Simplex.Messaging.Util (safeDecodeUtf8, (<$$>))
 import System.FilePath ((</>))
 
 type RcvFileId = ByteString -- Agent entity ID
@@ -65,7 +66,8 @@ data FileHeader = FileHeader
 instance Encoding FileHeader where
   smpEncode FileHeader {fileName, fileExtra} = smpEncode (fileName, fileExtra)
   smpP = do
-    (fileName, fileExtra) <- smpP
+    fileName <- safeDecodeUtf8 <$> smpP
+    fileExtra <- safeDecodeUtf8 <$$> smpP
     pure FileHeader {fileName, fileExtra}
 
 type DBRcvFileId = Int64

src/Simplex/Messaging/Agent.hs

@@ -49,6 +49,7 @@ module Simplex.Messaging.Agent
     deleteUser,
     setUserService,
     connRequestPQSupport,
+    prepareConnectionToCreate,
     createConnectionAsync,
     setConnShortLinkAsync,
     getConnShortLinkAsync,
@@ -65,6 +66,8 @@ module Simplex.Messaging.Agent
     setConnShortLink,
     deleteConnShortLink,
     getConnShortLink,
+    resolveSimplexName,
+    getConnLinkPrivKey,
     deleteLocalInvShortLink,
     changeConnectionUser,
     prepareConnectionToJoin,
@@ -215,6 +218,7 @@ import Simplex.Messaging.Protocol
     ErrorType (AUTH),
     MsgBody,
     MsgFlags (..),
+    NameRecord,
     NtfServer,
     ProtoServerWithAuth (..),
     ProtocolServer (..),
@@ -355,9 +359,14 @@ setUserService :: AgentClient -> UserId -> Bool -> AE ()
 setUserService c = withAgentEnv c .: setUserService' c
 {-# INLINE setUserService #-}
 
--- | Create SMP agent connection (NEW command) asynchronously, synchronous response is new connection id
-createConnectionAsync :: ConnectionModeI c => AgentClient -> UserId -> ACorrId -> Bool -> SConnectionMode c -> CR.InitialKeys -> SubscriptionMode -> AE ConnId
-createConnectionAsync c userId aCorrId enableNtfs = withAgentEnv c .:. newConnAsync c userId aCorrId enableNtfs
+-- | Create SMP agent connection without queue (to be used with createConnectionAsync).
+prepareConnectionToCreate :: AgentClient -> UserId -> Bool -> SConnectionMode c -> PQSupport -> AE ConnId
+prepareConnectionToCreate c userId enableNtfs = withAgentEnv c .: newConnNoQueues c userId enableNtfs
+{-# INLINE prepareConnectionToCreate #-}
+
+-- | Enqueue NEW command for a prepared connection.
+createConnectionAsync :: ConnectionModeI c => AgentClient -> ACorrId -> ConnId -> Bool -> SConnectionMode c -> CR.InitialKeys -> SubscriptionMode -> AE ()
+createConnectionAsync c aCorrId connId enableNtfs = withAgentEnv c .:. newConnAsync c aCorrId connId enableNtfs
 {-# INLINE createConnectionAsync #-}
 
 -- | Create or update user's contact connection short link (LSET command) asynchronously, no synchronous response
@@ -365,15 +374,14 @@ setConnShortLinkAsync :: AgentClient -> ACorrId -> ConnId -> UserConnLinkData 'C
 setConnShortLinkAsync c = withAgentEnv c .:: setConnShortLinkAsync' c
 {-# INLINE setConnShortLinkAsync #-}
 
--- | Get and verify data from short link (LGET/LKEY command) asynchronously, synchronous response is new connection id
-getConnShortLinkAsync :: AgentClient -> UserId -> ACorrId -> ConnShortLink 'CMContact -> AE ConnId
-getConnShortLinkAsync c = withAgentEnv c .:. getConnShortLinkAsync' c
+-- | Get and verify data from short link (LGET/LKEY command) asynchronously, synchronous response is new/passed connection id
+getConnShortLinkAsync :: AgentClient -> UserId -> ACorrId -> Maybe ConnId -> ConnShortLink 'CMContact -> AE ConnId
+getConnShortLinkAsync c = withAgentEnv c .:: getConnShortLinkAsync' c
 {-# INLINE getConnShortLinkAsync #-}
 
--- | Join SMP agent connection (JOIN command) asynchronously, synchronous response is new connection id.
--- If connId is provided (for contact URIs), it updates the existing connection record created by getConnShortLinkAsync.
-joinConnectionAsync :: AgentClient -> UserId -> ACorrId -> Maybe ConnId -> Bool -> ConnectionRequestUri c -> ConnInfo -> PQSupport -> SubscriptionMode -> AE ConnId
-joinConnectionAsync c userId aCorrId connId_ enableNtfs = withAgentEnv c .:: joinConnAsync c userId aCorrId connId_ enableNtfs
+-- | Enqueue JOIN command for a prepared connection.
+joinConnectionAsync :: AgentClient -> ACorrId -> Bool -> ConnId -> Bool -> ConnectionRequestUri c -> ConnInfo -> PQSupport -> SubscriptionMode -> AE ()
+joinConnectionAsync c aCorrId updateConn connId enableNtfs = withAgentEnv c .:: joinConnAsync c aCorrId updateConn connId enableNtfs
 {-# INLINE joinConnectionAsync #-}
 
 -- | Allow connection to continue after CONF notification (LET command), no synchronous response
@@ -381,9 +389,9 @@ allowConnectionAsync :: AgentClient -> ACorrId -> ConnId -> ConfirmationId -> Co
 allowConnectionAsync c = withAgentEnv c .:: allowConnectionAsync' c
 {-# INLINE allowConnectionAsync #-}
 
--- | Accept contact after REQ notification (ACPT command) asynchronously, synchronous response is new connection id
-acceptContactAsync :: AgentClient -> UserId -> ACorrId -> Bool -> ConfirmationId -> ConnInfo -> PQSupport -> SubscriptionMode -> AE ConnId
-acceptContactAsync c userId aCorrId enableNtfs = withAgentEnv c .:: acceptContactAsync' c userId aCorrId enableNtfs
+-- | Accept contact after REQ notification (ACPT command) asynchronously, for a prepared connection.
+acceptContactAsync :: AgentClient -> ACorrId -> ConnId -> Bool -> ConfirmationId -> ConnInfo -> PQSupport -> SubscriptionMode -> AE ()
+acceptContactAsync c aCorrId connId enableNtfs = withAgentEnv c .:: acceptContactAsync' c aCorrId connId enableNtfs
 {-# INLINE acceptContactAsync #-}
 
 -- | Acknowledge message (ACK command) asynchronously, no synchronous response
@@ -412,10 +420,12 @@ createConnection c nm userId enableNtfs checkNotices = withAgentEnv c .::. newCo
 {-# INLINE createConnection #-}
 
 -- | Prepare connection link for contact mode (no network call).
--- Returns root key pair (for signing OwnerAuth), the created link, and internal params.
+-- Caller provides root signing key pair and link entity ID.
+-- Returns the created link and internal params.
 -- The link address is fully determined at this point.
-prepareConnectionLink :: AgentClient -> UserId -> Maybe ByteString -> Bool -> Maybe CRClientData -> AE (C.KeyPairEd25519, CreatedConnLink 'CMContact, PreparedLinkParams)
-prepareConnectionLink c userId linkEntityId checkNotices = withAgentEnv c . prepareConnectionLink' c userId linkEntityId checkNotices
+prepareConnectionLink :: AgentClient -> UserId -> C.KeyPairEd25519 -> ByteString -> Bool -> Maybe CRClientData -> Maybe SMPServerWithAuth -> AE (CreatedConnLink 'CMContact, PreparedLinkParams)
+prepareConnectionLink c userId rootKey linkEntityId checkNotices clientData srv_ =
+  withAgentEnv c $ prepareConnectionLink' c userId rootKey linkEntityId checkNotices clientData srv_
 {-# INLINE prepareConnectionLink #-}
 
 -- | Create connection for prepared link (single network call).
@@ -438,6 +448,17 @@ getConnShortLink :: AgentClient -> NetworkRequestMode -> UserId -> ConnShortLink
 getConnShortLink c = withAgentEnv c .:. getConnShortLink' c
 {-# INLINE getConnShortLink #-}
 
+-- | Resolve a SimpleX name (PFWD RSLV). The agent owns server selection: it
+-- picks a names-capable server (ServerRoles.names) from the user's nameSrvs, so
+-- chat clients just pass the parsed domain.
+resolveSimplexName :: AgentClient -> NetworkRequestMode -> UserId -> SimplexDomain -> AE NameRecord
+resolveSimplexName c nm userId domain = withAgentEnv c $ resolveSimplexName' c nm userId domain
+{-# INLINE resolveSimplexName #-}
+
+getConnLinkPrivKey :: AgentClient -> ConnId -> AE (Maybe C.PrivateKeyEd25519)
+getConnLinkPrivKey c = withAgentEnv c . getConnLinkPrivKey' c
+{-# INLINE getConnLinkPrivKey #-}
+
 -- | This irreversibly deletes short link data, and it won't be retrievable again
 deleteLocalInvShortLink :: AgentClient -> ConnShortLink 'CMInvitation -> AE ()
 deleteLocalInvShortLink c = withAgentEnv c . deleteLocalInvShortLink' c
@@ -828,14 +849,13 @@ setUserService' c userId enable = do
         let changed = enable /= wasEnabled
         when changed $ TM.insert userId enable $ useClientServices c
         pure (True, changed)
-  unless ok $ throwE $ CMD PROHIBITED "setNetworkConfig"
+  unless ok $ throwE $ CMD PROHIBITED "setUserService"
   when (changed && not enable) $ withStore' c (`deleteClientServices` userId)
 
-newConnAsync :: ConnectionModeI c => AgentClient -> UserId -> ACorrId -> Bool -> SConnectionMode c -> CR.InitialKeys -> SubscriptionMode -> AM ConnId
-newConnAsync c userId corrId enableNtfs cMode pqInitKeys subMode = do
-  connId <- newConnNoQueues c userId enableNtfs cMode (CR.connPQEncryption pqInitKeys)
+newConnAsync :: ConnectionModeI c => AgentClient -> ACorrId -> ConnId -> Bool -> SConnectionMode c -> CR.InitialKeys -> SubscriptionMode -> AM ()
+newConnAsync c corrId connId enableNtfs cMode pqInitKeys subMode =
   enqueueCommand c corrId connId Nothing $ AClientCommand $ NEW enableNtfs (ACM cMode) pqInitKeys subMode
-  pure connId
+{-# INLINE newConnAsync #-}
 
 newConnNoQueues :: AgentClient -> UserId -> Bool -> SConnectionMode c -> PQSupport -> AM ConnId
 newConnNoQueues c userId enableNtfs cMode pqSupport = do
@@ -846,34 +866,21 @@ newConnNoQueues c userId enableNtfs cMode pqSupport = do
 
 -- TODO [short links] TBC, but probably we will need async join for contact addresses as the contact will be created after user confirming the connection,
 -- and join should retry, the same as 1-time invitation joins.
-joinConnAsync :: AgentClient -> UserId -> ACorrId -> Maybe ConnId -> Bool -> ConnectionRequestUri c -> ConnInfo -> PQSupport -> SubscriptionMode -> AM ConnId
-joinConnAsync c userId corrId connId_ enableNtfs cReqUri@CRInvitationUri {} cInfo pqSup subMode = do
-  when (isJust connId_) $ throwE $ CMD PROHIBITED "joinConnAsync: connId not allowed for invitation URI"
-  withInvLock c (strEncode cReqUri) "joinConnAsync" $ do
+joinConnAsync :: AgentClient -> ACorrId -> Bool -> ConnId -> Bool -> ConnectionRequestUri c -> ConnInfo -> PQSupport -> SubscriptionMode -> AM ()
+joinConnAsync c corrId updateConn connId enableNtfs cReqUri@CRInvitationUri {} cInfo pqSup subMode = do
+  when updateConn $ throwE $ CMD PROHIBITED "joinConnAsync: updateConn not allowed for invitation URI"
+  withInvLock c (strEncode cReqUri) "joinConnAsync" $
     lift (compatibleInvitationUri cReqUri) >>= \case
       Just (_, Compatible (CR.E2ERatchetParams v _ _ _), Compatible connAgentVersion) -> do
-        g <- asks random
         let pqSupport = pqSup `CR.pqSupportAnd` versionPQSupport_ connAgentVersion (Just v)
-            cData = ConnData {userId, connId = "", connAgentVersion, enableNtfs, lastExternalSndId = 0, deleted = False, ratchetSyncState = RSOk, pqSupport}
-        connId <- withStore c $ \db -> createNewConn db g cData SCMInvitation
         enqueueCommand c corrId connId Nothing $ AClientCommand $ JOIN enableNtfs (ACR sConnectionMode cReqUri) pqSupport subMode cInfo
-        pure connId
       Nothing -> throwE $ AGENT A_VERSION
-joinConnAsync c userId corrId connId_ enableNtfs cReqUri@(CRContactUri _) cInfo pqSup subMode = do
+joinConnAsync c corrId updateConn connId enableNtfs cReqUri@(CRContactUri _) cInfo pqSup subMode =
   lift (compatibleContactUri cReqUri) >>= \case
     Just (_, Compatible connAgentVersion) -> do
       let pqSupport = pqSup `CR.pqSupportAnd` versionPQSupport_ connAgentVersion Nothing
-      connId <- case connId_ of
-        Just cId -> do
-          -- update connection record created by getConnShortLinkAsync
-          withStore' c $ \db -> updateNewConnJoin db cId connAgentVersion pqSupport enableNtfs
-          pure cId
-        Nothing -> do
-          g <- asks random
-          let cData = ConnData {userId, connId = "", connAgentVersion, enableNtfs, lastExternalSndId = 0, deleted = False, ratchetSyncState = RSOk, pqSupport}
-          withStore c $ \db -> createNewConn db g cData SCMInvitation
+      when updateConn $ withStore' c $ \db -> updateNewConnJoin db connId connAgentVersion pqSupport enableNtfs
       enqueueCommand c corrId connId Nothing $ AClientCommand $ JOIN enableNtfs (ACR sConnectionMode cReqUri) pqSupport subMode cInfo
-      pure connId
     Nothing -> throwE $ AGENT A_VERSION
 
 allowConnectionAsync' :: AgentClient -> ACorrId -> ConnId -> ConfirmationId -> ConnInfo -> AM ()
@@ -889,11 +896,11 @@ allowConnectionAsync' c corrId connId confId ownConnInfo =
 -- and also it can't be triggered by user concurrently several times in a row. It could be improved similarly to
 -- `acceptContact` by creating a new map for invitation locks and taking lock here, and removing `unacceptInvitation`
 -- while marking invitation as accepted inside "lock level transaction" after successful `joinConnAsync`.
-acceptContactAsync' :: AgentClient -> UserId -> ACorrId -> Bool -> InvitationId -> ConnInfo -> PQSupport -> SubscriptionMode -> AM ConnId
-acceptContactAsync' c userId corrId enableNtfs invId ownConnInfo pqSupport subMode = do
+acceptContactAsync' :: AgentClient -> ACorrId -> ConnId -> Bool -> InvitationId -> ConnInfo -> PQSupport -> SubscriptionMode -> AM ()
+acceptContactAsync' c corrId connId enableNtfs invId ownConnInfo pqSupport subMode = do
   Invitation {connReq} <- withStore c $ \db -> getInvitation db "acceptContactAsync'" invId
   withStore' c $ \db -> acceptInvitation db invId ownConnInfo
-  joinConnAsync c userId corrId Nothing enableNtfs connReq ownConnInfo pqSupport subMode `catchAllErrors` \err -> do
+  joinConnAsync c corrId False connId enableNtfs connReq ownConnInfo pqSupport subMode `catchAllErrors` \err -> do
     withStore' c (`unacceptInvitation` invId)
     throwE err
 
@@ -958,23 +965,22 @@ newConn c nm userId enableNtfs checkNotices cMode linkData_ clientData pqInitKey
       `catchE` \e -> withStore' c (`deleteConnRecord` connId) >> throwE e
 
 -- | Prepare connection link for contact mode (no network, no database).
--- Generates all cryptographic material and returns the link that will be created.
-prepareConnectionLink' :: AgentClient -> UserId -> Maybe ByteString -> Bool -> Maybe CRClientData -> AM (C.KeyPairEd25519, CreatedConnLink 'CMContact, PreparedLinkParams)
-prepareConnectionLink' c userId linkEntityId checkNotices clientData = do
+-- Caller provides root signing key pair and link entity ID.
+prepareConnectionLink' :: AgentClient -> UserId -> C.KeyPairEd25519 -> ByteString -> Bool -> Maybe CRClientData -> Maybe SMPServerWithAuth -> AM (CreatedConnLink 'CMContact, PreparedLinkParams)
+prepareConnectionLink' c userId rootKey@(_, plpRootPrivKey) linkEntityId checkNotices clientData srv_ = do
   g <- asks random
-  plpSrvWithAuth@(ProtoServerWithAuth srv _) <- getSMPServer c userId
+  plpSrvWithAuth@(ProtoServerWithAuth srv _) <- maybe (getSMPServer c userId) pure srv_
   when checkNotices $ checkClientNotices c plpSrvWithAuth
   AgentConfig {smpClientVRange, smpAgentVRange} <- asks config
   plpNonce@(C.CbNonce corrId) <- atomically $ C.randomCbNonce g
-  sigKeys@(_, plpRootPrivKey) <- atomically $ C.generateKeyPair g
   plpQueueE2EKeys@(e2ePubKey, _) <- atomically $ C.generateKeyPair g
   let sndId = SMP.EntityId $ B.take 24 $ C.sha3_384 corrId
       qUri = SMPQueueUri smpClientVRange $ SMPQueueAddress srv sndId e2ePubKey (Just QMContact)
       connReq = CRContactUri $ ConnReqUriData SSSimplex smpAgentVRange [qUri] clientData
-      (plpLinkKey, plpSignedFixedData) = SL.encodeSignFixedData sigKeys smpAgentVRange connReq linkEntityId
+      (plpLinkKey, plpSignedFixedData) = SL.encodeSignFixedData rootKey smpAgentVRange connReq (Just linkEntityId)
       ccLink = CCLink connReq $ Just $ CSLContact SLSServer CCTContact srv plpLinkKey
       params = PreparedLinkParams {plpNonce, plpQueueE2EKeys, plpLinkKey, plpRootPrivKey, plpSignedFixedData, plpSrvWithAuth}
-  pure (sigKeys, ccLink, params)
+  pure (ccLink, params)
 
 -- | Create connection for prepared link (single network call).
 createConnectionForLink' :: AgentClient -> NetworkRequestMode -> UserId -> Bool -> CreatedConnLink 'CMContact -> PreparedLinkParams -> UserConnLinkData 'CMContact -> CR.InitialKeys -> SubscriptionMode -> AM ConnId
@@ -1041,14 +1047,22 @@ setConnShortLinkAsync' c corrId connId userLinkData clientData =
       _ -> throwE $ CMD PROHIBITED "setConnShortLinkAsync: invalid connection or mode"
     enqueueCommand c corrId connId (Just srv) $ AClientCommand $ LSET userLinkData clientData
 
-getConnShortLinkAsync' :: AgentClient -> UserId -> ACorrId -> ConnShortLink 'CMContact -> AM ConnId
-getConnShortLinkAsync' c userId corrId shortLink@(CSLContact _ _ srv _) = do
-  g <- asks random
-  connId <- withStore c $ \db -> do
-    -- server is created so the command is processed in server queue,
-    -- not blocking other "no server" commands
-    void $ createServer db srv
-    prepareNewConn db g
+getConnShortLinkAsync' :: AgentClient -> UserId -> ACorrId -> Maybe ConnId -> ConnShortLink 'CMContact -> AM ConnId
+getConnShortLinkAsync' c userId corrId connId_ shortLink@(CSLContact _ _ srv _) = do
+  connId <- case connId_ of
+    Just existingConnId -> do
+      -- connId and srv can be unrelated: connId is used as "mailbox" for LDATA delivery,
+      -- while srv is the short link's server for the LGET request.
+      -- E.g., owner's relay connection (connId, on server A) fetches relay's group link data (srv = server B).
+      -- This works because enqueueCommand stores (connId, srv) independently in the commands table,
+      -- the network request targets srv, and event delivery uses connId via corrId correlation.
+      withStore' c $ \db -> void $ createServer db srv
+      pure existingConnId
+    Nothing -> do
+      g <- asks random
+      withStore c $ \db -> do
+        void $ createServer db srv
+        prepareNewConn db g
   enqueueCommand c corrId connId (Just srv) $ AClientCommand $ LGET shortLink
   pure connId
   where
@@ -1119,6 +1133,14 @@ deleteConnShortLink' c nm connId cMode =
       (RcvConnection _ rq, SCMInvitation) -> deleteQueueLink c nm rq
       _ -> throwE $ CMD PROHIBITED "deleteConnShortLink: not contact address"
 
+getConnLinkPrivKey' :: AgentClient -> ConnId -> AM (Maybe C.PrivateKeyEd25519)
+getConnLinkPrivKey' c connId = do
+  SomeConn _ conn <- withStore c (`getConn` connId)
+  pure $ case conn of
+    ContactConnection _ rq -> linkPrivSigKey <$> shortLink rq
+    RcvConnection _ rq -> linkPrivSigKey <$> shortLink rq
+    _ -> Nothing
+
 -- TODO [short links] remove 1-time invitation data and link ID from the server after the message is sent.
 getConnShortLink' :: forall c. AgentClient -> NetworkRequestMode -> UserId -> ConnShortLink c -> AM (FixedLinkData c, ConnLinkData c)
 getConnShortLink' c nm userId = \case
@@ -1161,6 +1183,11 @@ getConnShortLink' c nm userId = \case
 deleteLocalInvShortLink' :: AgentClient -> ConnShortLink 'CMInvitation -> AM ()
 deleteLocalInvShortLink' c (CSLInvitation _ srv linkId _) = withStore' c $ \db -> deleteInvShortLink db srv linkId
 
+resolveSimplexName' :: AgentClient -> NetworkRequestMode -> UserId -> SimplexDomain -> AM NameRecord
+resolveSimplexName' c nm userId domain = do
+  resolverSrv <- getNextNameServer c userId
+  resolveName c nm userId resolverSrv domain
+
 changeConnectionUser' :: AgentClient -> UserId -> ConnId -> UserId -> AM ()
 changeConnectionUser' c oldUserId connId newUserId = do
   SomeConn _ conn <- withStore c (`getConn` connId)
@@ -1198,8 +1225,8 @@ newRcvConnSrv c nm userId connId enableNtfs cMode userLinkData_ clientData pqIni
         SCMInvitation -> do
           g <- asks random
           let pqEnc = CR.initialPQEncryption (isJust userLinkData_) pqInitKeys
-          (pk1, pk2, pKem, e2eRcvParams) <- liftIO $ CR.generateRcvE2EParams g (maxVersion e2eEncryptVRange) pqEnc
-          withStore' c $ \db -> createRatchetX3dhKeys db connId pk1 pk2 pKem
+          (pks, e2eRcvParams) <- liftIO $ CR.generateRcvE2EParams g (maxVersion e2eEncryptVRange) pqEnc
+          withStore' c $ \db -> createRatchetX3dhKeys db connId pks
           pure $ CRInvitationUri crData $ toVersionRangeT e2eRcvParams e2eEncryptVRange
     prepareLinkData :: UserConnLinkData c -> C.PublicKeyX25519 -> AM (C.CbNonce, SMPQueueUri, ConnectionRequestUri c, ClntQueueReqData)
     prepareLinkData userLinkData e2eDhKey = do
@@ -1320,9 +1347,9 @@ startJoinInvitation c userId connId sq_ enableNtfs cReqUri pqSup =
     Nothing -> throwE $ AGENT A_VERSION
   where
     createRatchet_ db g maxSupported pqSupport e2eRcvParams@(CR.E2ERatchetParams v _ rcDHRr kem_) = do
-      (pk1, pk2, pKem, e2eSndParams) <- liftIO $ CR.generateSndE2EParams g v (CR.replyKEM_ v kem_ pqSupport)
+      (pks, e2eSndParams) <- liftIO $ CR.generateSndE2EParams g v (CR.replyKEM_ v kem_ pqSupport)
       (_, rcDHRs) <- atomically $ C.generateKeyPair g
-      rcParams <- liftEitherWith (SEAgentError . cryptoError) $ CR.pqX3dhSnd pk1 pk2 pKem e2eRcvParams
+      rcParams <- liftEitherWith (SEAgentError . cryptoError) $ CR.pqX3dhSnd pks e2eRcvParams
       let rcVs = CR.RatchetVersions {current = v, maxSupported}
           rc = CR.initSndRatchet rcVs rcDHRr rcDHRs rcParams
       liftIO $ createSndRatchet db connId rc e2eSndParams
@@ -1399,8 +1426,8 @@ joinConnSrv c nm userId connId enableNtfs cReqUri@CRContactUri {} cInfo pqSup su
               Left e -> do
                 nonBlockingWriteTBQueue (subQ c) ("", connId, AEvt SAEConn (ERR $ INTERNAL $ "no rcv ratchet " <> show e))
                 let pqEnc = CR.initialPQEncryption False pqInitKeys
-                (pk1, pk2, pKem, e2eRcvParams) <- liftIO $ CR.generateRcvE2EParams g (maxVersion e2eVR) pqEnc
-                createRatchetX3dhKeys db connId pk1 pk2 pKem
+                (pks, e2eRcvParams) <- liftIO $ CR.generateRcvE2EParams g (maxVersion e2eVR) pqEnc
+                createRatchetX3dhKeys db connId pks
                 pure e2eRcvParams
           let cReq = CRInvitationUri crData $ toVersionRangeT e2eRcvParams e2eVR
           pure $ CCLink cReq Nothing
@@ -1589,8 +1616,7 @@ subscribeAllConnections' :: AgentClient -> Bool -> Maybe UserId -> AM ()
 subscribeAllConnections' c onlyNeeded activeUserId_ = handleErr $ do
   userSrvs <- withStore' c (`getSubscriptionServers` onlyNeeded)
   unless (null userSrvs) $ do
-    maxPending <- asks $ maxPendingSubscriptions . config
-    currPending <- newTVarIO 0
+    batchSize <- asks $ subsBatchSize . config
     let userSrvs' = case activeUserId_ of
           Just activeUserId -> sortOn (\(uId, _) -> if uId == activeUserId then 0 else 1 :: Int) userSrvs
           Nothing -> userSrvs
@@ -1602,7 +1628,7 @@ subscribeAllConnections' c onlyNeeded activeUserId_ = handleErr $ do
     -- On successful service subscription, only unassociated queues will be subscribed.
     userSrvs2 <- withStore' c $ \db -> mapM (getService db useServices) userSrvs'
     userSrvs3 <- lift $ mapConcurrently subscribeService userSrvs2
-    rs <- lift $ mapConcurrently (subscribeUserServer maxPending currPending) userSrvs3
+    rs <- lift $ mapConcurrently (subscribeUserServer batchSize) userSrvs3
     let (errs, oks) = partitionEithers rs
     logInfo $ "subscribed " <> tshow (sum oks) <> " queues"
     forM_ (L.nonEmpty errs) $ notifySub c . ERRS . L.map ("",)
@@ -1639,18 +1665,16 @@ subscribeAllConnections' c onlyNeeded activeUserId_ = handleErr $ do
               unassocQueues :: AM Bool
               unassocQueues = False <$ withStore' c (\db -> removeRcvServiceAssocs db userId srv)
           _ -> pure False
-    subscribeUserServer :: Int -> TVar Int -> ((UserId, SMPServer), ServiceAssoc) -> AM' (Either AgentErrorType Int)
-    subscribeUserServer maxPending currPending ((userId, srv), hasService) = do
-      atomically $ whenM ((maxPending <=) <$> readTVar currPending) retry
-      tryAllErrors' $ do
-        qs <- withStore' c $ \db -> do
-          qs <- getUserServerRcvQueueSubs db userId srv onlyNeeded hasService
-          unless (null qs) $ atomically $ modifyTVar' currPending (+ length qs) -- update before leaving transaction
-          pure qs
-        let n = length qs
-        unless (null qs) $ lift $ subscribe qs `E.finally` atomically (modifyTVar' currPending $ subtract n)
-        pure n
+    subscribeUserServer :: Int -> ((UserId, SMPServer), ServiceAssoc) -> AM' (Either AgentErrorType Int)
+    subscribeUserServer batchSize ((userId, srv), hasService) = tryAllErrors' $ loop 0 Nothing
       where
+        loop !n cursor_ = do
+          qs <- withStore' c $ \db -> getUserServerRcvQueueSubs db userId srv onlyNeeded hasService batchSize cursor_
+          if null qs then pure n else do
+            lift $ subscribe qs
+            let n' = n + length qs
+                lastRcvId = Just $ queueId $ last qs
+            if length qs < batchSize then pure n' else loop n' lastRcvId
         subscribe qs = do
           rs <- subscribeUserServerQueues c userId srv qs
           ns <- asks ntfSupervisor
@@ -2451,11 +2475,11 @@ synchronizeRatchet' c connId pqSupport' force = withConnLock c connId "synchroni
           let cData' = cData {pqSupport = pqSupport'} :: ConnData
           AgentConfig {e2eEncryptVRange} <- asks config
           g <- asks random
-          (pk1, pk2, pKem, e2eParams) <- liftIO $ CR.generateRcvE2EParams g (maxVersion e2eEncryptVRange) pqSupport'
+          (pks, e2eParams) <- liftIO $ CR.generateRcvE2EParams g (maxVersion e2eEncryptVRange) pqSupport'
           enqueueRatchetKeyMsgs c sqs e2eParams
           withStore' c $ \db -> do
             setConnRatchetSync db connId RSStarted
-            setRatchetX3dhKeys db connId pk1 pk2 pKem
+            setRatchetX3dhKeys db connId pks
           let cData'' = cData' {ratchetSyncState = RSStarted} :: ConnData
               conn' = DuplexConnection cData'' rqs sqs
           connectionStats c conn'
@@ -3088,7 +3112,7 @@ processSMPTransmissions c@AgentClient {subQ} (tSess@(userId, srv, _), THandlePar
   unless (null connIds) $ do
     notify' "" $ UP srv connIds
     atomically $ incSMPServerStat' c userId srv connSubscribed $ length connIds
-  readTVarIO serviceRQs >>= processRcvServiceAssocs c
+  readTVarIO serviceRQs >>= processRcvServiceAssocs c srv
   where
     withRcvConn :: SMP.RecipientId -> (forall c. RcvQueue -> Connection c -> AM ()) -> AM' ()
     withRcvConn rId a = do
@@ -3222,18 +3246,28 @@ processSMPTransmissions c@AgentClient {subQ} (tSess@(userId, srv, _), THandlePar
                                     pure conn''
                                 | otherwise = pure conn'
                           Right Nothing -> prohibited "msg: bad agent msg" >> ack
-                          Left e@(AGENT A_DUPLICATE) -> do
+                          Left e@(AGENT A_DUPLICATE {}) -> do
                             atomically $ incSMPServerStat c userId srv recvDuplicates
                             withStore' c (\db -> getLastMsg db connId srvMsgId) >>= \case
                               Just RcvMsg {internalId, msgMeta, msgBody = agentMsgBody, userAck}
                                 | userAck -> ackDel internalId
-                                | otherwise ->
-                                    liftEither (parse smpP (AGENT A_MESSAGE) agentMsgBody) >>= \case
-                                      AgentMessage _ (A_MSG body) -> do
-                                        logServer "<--" c srv rId $ "MSG <MSG>:" <> logSecret' srvMsgId
-                                        notify $ MSG msgMeta msgFlags body
-                                        pure ACKPending
-                                      _ -> ack
+                                | otherwise -> do
+                                    attempts <- withStore' c $ \db -> incMsgRcvAttempts db connId internalId
+                                    AgentConfig {rcvExpireCount, rcvExpireInterval} <- asks config
+                                    let firstTs = snd $ recipient msgMeta
+                                        brokerTs = snd $ broker msgMeta
+                                    now <- liftIO getCurrentTime
+                                    if attempts >= rcvExpireCount && diffUTCTime now firstTs >= rcvExpireInterval
+                                      then do
+                                        notify $ ERR (AGENT $ A_DUPLICATE $ Just DroppedMsg {brokerTs, attempts})
+                                        ackDel internalId
+                                      else
+                                        liftEither (parse smpP (AGENT A_MESSAGE) agentMsgBody) >>= \case
+                                          AgentMessage _ (A_MSG body) -> do
+                                            logServer "<--" c srv rId $ "MSG <MSG>:" <> logSecret' srvMsgId
+                                            notify $ MSG msgMeta msgFlags body
+                                            pure ACKPending
+                                          _ -> ack
                               _ -> checkDuplicateHash e encryptedMsgHash >> ack
                           Left (AGENT (A_CRYPTO e)) -> do
                             atomically $ incSMPServerStat c userId srv recvCryptoErrs
@@ -3376,8 +3410,8 @@ processSMPTransmissions c@AgentClient {subQ} (tSess@(userId, srv, _), THandlePar
                 -- party initiating connection
                 (RcvConnection _ _, Just (CR.AE2ERatchetParams _ e2eSndParams@(CR.E2ERatchetParams e2eVersion _ _ _))) -> do
                   unless (e2eVersion `isCompatible` e2eEncryptVRange) (throwE $ AGENT A_VERSION)
-                  (pk1, rcDHRs, pKem) <- withStore c (`getRatchetX3dhKeys` connId)
-                  rcParams <- liftError cryptoError $ CR.pqX3dhRcv pk1 rcDHRs pKem e2eSndParams
+                  pks@(_, rcDHRs, _) <- withStore c (`getRatchetX3dhKeys` connId)
+                  rcParams <- liftError cryptoError $ CR.pqX3dhRcv pks e2eSndParams
                   let rcVs = CR.RatchetVersions {current = e2eVersion, maxSupported = maxVersion e2eEncryptVRange}
                       pqSupport' = pqSupport `CR.pqSupportAnd` versionPQSupport_ agentVersion (Just e2eVersion)
                       rc = CR.initRcvRatchet rcVs rcDHRs rcParams pqSupport'
@@ -3618,7 +3652,7 @@ processSMPTransmissions c@AgentClient {subQ} (tSess@(userId, srv, _), THandlePar
                 exists <- checkRatchetKeyHashExists db connId rkHashRcv
                 unless exists $ addProcessedRatchetKeyHash db connId rkHashRcv
                 pure exists
-              getSendRatchetKeys :: AM (C.PrivateKeyX448, C.PrivateKeyX448, Maybe CR.RcvPrivRKEMParams)
+              getSendRatchetKeys :: AM (CR.RcvE2EPrivRatchetParams 'C.X448)
               getSendRatchetKeys = case rss of
                 RSOk -> sendReplyKey -- receiving client
                 RSAllowed -> sendReplyKey
@@ -3634,9 +3668,9 @@ processSMPTransmissions c@AgentClient {subQ} (tSess@(userId, srv, _), THandlePar
                 where
                   sendReplyKey = do
                     g <- asks random
-                    (pk1, pk2, pKem, e2eParams) <- liftIO $ CR.generateRcvE2EParams g e2eVersion pqSupport
+                    (pks, e2eParams) <- liftIO $ CR.generateRcvE2EParams g e2eVersion pqSupport
                     enqueueRatchetKeyMsgs c sqs e2eParams
-                    pure (pk1, pk2, pKem)
+                    pure pks
                   notifyRatchetSyncError = do
                     let cData'' = cData' {ratchetSyncState = RSRequired} :: ConnData
                         conn'' = updateConnection cData'' conn'
@@ -3655,14 +3689,14 @@ processSMPTransmissions c@AgentClient {subQ} (tSess@(userId, srv, _), THandlePar
                 createRatchet db connId rc
               -- compare public keys `k1` in AgentRatchetKey messages sent by self and other party
               -- to determine ratchet initilization ordering
-              initRatchet :: CR.RatchetVersions -> (C.PrivateKeyX448, C.PrivateKeyX448, Maybe CR.RcvPrivRKEMParams) -> AM ()
+              initRatchet :: CR.RatchetVersions -> CR.RcvE2EPrivRatchetParams 'C.X448 -> AM ()
               initRatchet rcVs (pk1, pk2, pKem)
                 | rkHash (C.publicKey pk1) (C.publicKey pk2) <= rkHashRcv = do
-                    rcParams <- liftError cryptoError $ CR.pqX3dhRcv pk1 pk2 pKem e2eOtherPartyParams
+                    rcParams <- liftError cryptoError $ CR.pqX3dhRcv (pk1, pk2, pKem) e2eOtherPartyParams
                     recreateRatchet $ CR.initRcvRatchet rcVs pk2 rcParams pqSupport
                 | otherwise = do
                     (_, rcDHRs) <- atomically . C.generateKeyPair =<< asks random
-                    rcParams <- liftEitherWith cryptoError $ CR.pqX3dhSnd pk1 pk2 (CR.APRKP CR.SRKSProposed <$> pKem) e2eOtherPartyParams
+                    rcParams <- liftEitherWith cryptoError $ CR.pqX3dhSnd (pk1, pk2, CR.APRKP CR.SRKSProposed <$> pKem) e2eOtherPartyParams
                     recreateRatchet $ CR.initSndRatchet rcVs k2Rcv rcDHRs rcParams
                     void . enqueueMessages' c cData' sqs SMP.MsgFlags {notification = True} $ EREADY lastExternalSndId
 

src/Simplex/Messaging/Agent/Client.hs

@@ -68,6 +68,8 @@ module Simplex.Messaging.Agent.Client
     deleteQueueLink,
     secureGetQueueLink,
     getQueueLink,
+    resolveName,
+    getNextNameServer,
     enableQueueNotifications,
     EnableQueueNtfReq (..),
     enableQueuesNtfs,
@@ -267,6 +269,7 @@ import Simplex.Messaging.Protocol
     NetworkError (..),
     MsgFlags (..),
     MsgId,
+    NameRecord,
     NtfServer,
     NtfServerWithAuth,
     ProtoServer,
@@ -625,9 +628,7 @@ getServiceCredentials c userId srv =
             Just service -> pure service
             Nothing -> do
               cred <- genCredentials g Nothing (25, 24 * 999999) "simplex"
-              let tlsCreds = tlsCredentials [cred]
-              createClientService db userId srv tlsCreds
-              pure (tlsCreds, Nothing)
+              createClientService db userId srv $ tlsCredentials [cred]
       serviceSignKey <- liftEitherWith INTERNAL $ C.x509ToPrivate' $ snd serviceCreds
       let creds = ServiceCredentials {serviceRole = SRMessaging, serviceCreds, serviceCertHash = XV.Fingerprint kh, serviceSignKey}
       pure (creds, serviceId_)
@@ -676,8 +677,7 @@ getSMPServerClient :: AgentClient -> NetworkRequestMode -> SMPTransportSession -
 getSMPServerClient c@AgentClient {active, smpClients, workerSeq} nm tSess = do
   unlessM (readTVarIO active) $ throwE INACTIVE
   ts <- liftIO getCurrentTime
-  atomically (getSessVar workerSeq tSess smpClients ts)
-    >>= either newClient (waitForProtocolClient c nm tSess smpClients)
+  withGetSessVar workerSeq tSess smpClients ts newClient (waitForProtocolClient c nm tSess smpClients)
   where
     newClient v = do
       prs <- liftIO TM.emptyIO
@@ -688,29 +688,25 @@ getSMPProxyClient c@AgentClient {active, smpClients, smpProxiedRelays, workerSeq
   unlessM (readTVarIO active) $ throwE INACTIVE
   proxySrv <- maybe (getNextServer c userId proxySrvs [destSrv]) pure proxySrv_
   ts <- liftIO getCurrentTime
-  atomically (getClientVar proxySrv ts) >>= \(tSess, auth, v) ->
-    either (newProxyClient tSess auth ts) (waitForProxyClient tSess auth) v
+  (tSess, auth) <- atomically $ proxiedTransportSession proxySrv
+  withGetSessVar workerSeq tSess smpClients ts (newProxyClient tSess auth ts) (waitForProxyClient tSess auth)
   where
-    getClientVar :: SMPServerWithAuth -> UTCTime -> STM (SMPTransportSession, Maybe SMP.BasicAuth, Either SMPClientVar SMPClientVar)
-    getClientVar proxySrv ts = do
+    proxiedTransportSession :: SMPServerWithAuth -> STM (SMPTransportSession, Maybe SMP.BasicAuth)
+    proxiedTransportSession proxySrv = do
       ProtoServerWithAuth srv auth <- TM.lookup destSess smpProxiedRelays >>= maybe (TM.insert destSess proxySrv smpProxiedRelays $> proxySrv) pure
-      let tSess = (userId, srv, qId)
-      (tSess,auth,) <$> getSessVar workerSeq tSess smpClients ts
+      pure ((userId, srv, qId), auth)
     newProxyClient :: SMPTransportSession -> Maybe SMP.BasicAuth -> UTCTime -> SMPClientVar -> AM (SMPConnectedClient, Either AgentErrorType ProxiedRelay)
     newProxyClient tSess auth ts v = do
       prs <- liftIO TM.emptyIO
-      -- we do not need to check if it is a new proxied relay session,
-      -- as the client is just created and there are no sessions yet
-      rv <- atomically $ either id id <$> getSessVar workerSeq destSrv prs ts
       clnt <- smpConnectClient c nm tSess prs v
-      (clnt,) <$> newProxiedRelay clnt auth rv
+      -- the relay var is always new (the client is just created and has no sessions yet)
+      sess <- withGetSessVar workerSeq destSrv prs ts (newProxiedRelay clnt auth) (waitForProxiedRelay tSess)
+      pure (clnt, sess)
     waitForProxyClient :: SMPTransportSession -> Maybe SMP.BasicAuth -> SMPClientVar -> AM (SMPConnectedClient, Either AgentErrorType ProxiedRelay)
     waitForProxyClient tSess auth v = do
       clnt@(SMPConnectedClient _ prs) <- waitForProtocolClient c nm tSess smpClients v
       ts <- liftIO getCurrentTime
-      sess <-
-        atomically (getSessVar workerSeq destSrv prs ts)
-          >>= either (newProxiedRelay clnt auth) (waitForProxiedRelay tSess)
+      sess <- withGetSessVar workerSeq destSrv prs ts (newProxiedRelay clnt auth) (waitForProxiedRelay tSess)
       pure (clnt, sess)
     newProxiedRelay :: SMPConnectedClient -> Maybe SMP.BasicAuth -> ProxiedRelayVar -> AM (Either AgentErrorType ProxiedRelay)
     newProxiedRelay (SMPConnectedClient smp prs) proxyAuth rv =
@@ -810,13 +806,17 @@ resubscribeSMPSession c@AgentClient {smpSubWorkers, workerSeq} tSess = do
         (pure Nothing) -- prevent race with cleanup and adding pending queues in another call
         (Just <$> getSessVar workerSeq tSess smpSubWorkers ts)
     newSubWorker v = do
-      a <- async $ void (E.tryAny runSubWorker) >> atomically (cleanup v)
+      a <- async $ void $ E.tryAny $ runSubWorker v
       atomically $ putTMVar (sessionVar v) a
-    runSubWorker = do
+    runSubWorker v = do
       ri <- asks $ reconnectInterval . config
       withRetryForeground ri isForeground (isNetworkOnline c) $ \_ loop -> do
-        (pendingSubs, pendingSS) <- atomically $ SS.getPendingSubs tSess $ currentSubs c
-        unless (M.null pendingSubs && isNothing pendingSS) $ do
+        pending_ <- atomically $ do
+          pending@(pendingSubs, pendingSS) <- SS.getPendingSubs tSess $ currentSubs c
+          if M.null pendingSubs && isNothing pendingSS
+            then cleanup v $> Nothing
+            else pure $ Just pending
+        forM_ pending_ $ \(pendingSubs, pendingSS) -> do
           liftIO $ waitUntilForeground c
           liftIO $ waitForUserNetwork c
           mapM_ (handleNotify . void . runExceptT . resubscribeClientService c tSess) pendingSS
@@ -844,10 +844,7 @@ getNtfServerClient :: AgentClient -> NetworkRequestMode -> NtfTransportSession -
 getNtfServerClient c@AgentClient {active, ntfClients, workerSeq, proxySessTs, presetDomains} nm tSess@(_, srv, _) = do
   unlessM (readTVarIO active) $ throwE INACTIVE
   ts <- liftIO getCurrentTime
-  atomically (getSessVar workerSeq tSess ntfClients ts)
-    >>= either
-      (newProtocolClient c tSess ntfClients connectClient)
-      (waitForProtocolClient c nm tSess ntfClients)
+  withGetSessVar workerSeq tSess ntfClients ts (newProtocolClient c tSess ntfClients connectClient) (waitForProtocolClient c nm tSess ntfClients)
   where
     connectClient :: NtfClientVar -> AM NtfClient
     connectClient v = do
@@ -868,10 +865,7 @@ getXFTPServerClient :: AgentClient -> XFTPTransportSession -> AM XFTPClient
 getXFTPServerClient c@AgentClient {active, xftpClients, workerSeq, proxySessTs, presetDomains} tSess@(_, srv, _) = do
   unlessM (readTVarIO active) $ throwE INACTIVE
   ts <- liftIO getCurrentTime
-  atomically (getSessVar workerSeq tSess xftpClients ts)
-    >>= either
-      (newProtocolClient c tSess xftpClients connectClient)
-      (waitForProtocolClient c NRMBackground tSess xftpClients)
+  withGetSessVar workerSeq tSess xftpClients ts (newProtocolClient c tSess xftpClients connectClient) (waitForProtocolClient c NRMBackground tSess xftpClients)
   where
     connectClient :: XFTPClientVar -> AM XFTPClient
     connectClient v = do
@@ -1659,9 +1653,15 @@ checkQueues c = fmap partitionEithers . mapM checkQueue
 resubscribeSessQueues :: AgentClient -> SMPTransportSession -> [RcvQueueSub] -> AM' ()
 resubscribeSessQueues _ _ [] = pure ()
 resubscribeSessQueues c tSess qs = do
+  batchSize <- asks $ subsBatchSize . config
   (errs, qs_) <- checkQueues c qs
-  forM_ (L.nonEmpty qs_) $ \qs' -> void $ subscribeSessQueues_ c True (tSess, qs')
+  subscribeChunks $ toChunks batchSize qs_
   forM_ (L.nonEmpty errs) $ notifySub c . ERRS . L.map (first qConnId)
+  where
+    subscribeChunks [] = pure ()
+    subscribeChunks (qs' : rest) = do
+      (_, active) <- subscribeSessQueues_ c True (tSess, qs')
+      when active $ subscribeChunks rest
 
 subscribeSessQueues_ :: AgentClient -> Bool -> (SMPTransportSession, NonEmpty RcvQueueSub) -> AM' (BatchResponses RcvQueueSub AgentErrorType (Maybe ServiceId), Bool)
 subscribeSessQueues_ c withEvents qs = sendClientBatch_ "SUB" False subscribe_ c NRMBackground qs
@@ -1684,7 +1684,7 @@ subscribeSessQueues_ c withEvents qs = sendClientBatch_ "SUB" False subscribe_ c
           unless (null notices) $ takeTMVar $ clientNoticesLock c
           pure r
         unless (null serviceQs) $ void $
-          processRcvServiceAssocs c serviceQs `runReaderT` agentEnv c
+          processRcvServiceAssocs c srv serviceQs `runReaderT` agentEnv c
         unless (null notices) $ void $
           (processClientNotices c tSess notices `runReaderT` agentEnv c)
             `E.finally` atomically (putTMVar (clientNoticesLock c) ())
@@ -1706,11 +1706,11 @@ subscribeSessQueues_ c withEvents qs = sendClientBatch_ "SUB" False subscribe_ c
         tSess = transportSession' smp
         sessId = sessionId $ thParams smp
 
-processRcvServiceAssocs :: SMPQueue q => AgentClient -> [q] -> AM' ()
-processRcvServiceAssocs _ [] = pure ()
-processRcvServiceAssocs c serviceQs =
-  withStore' c (`setRcvServiceAssocs` serviceQs) `catchAllErrors'` \e -> do
-    logError $ "processClientNotices error: " <> tshow e
+processRcvServiceAssocs :: SMPQueue q => AgentClient -> SMPServer -> [q] -> AM' ()
+processRcvServiceAssocs _ _ [] = pure ()
+processRcvServiceAssocs c srv serviceQs =
+  withStore' c (\db -> setRcvServiceAssocs db srv serviceQs) `catchAllErrors'` \e -> do
+    logError $ "processRcvServiceAssocs error: " <> tshow e
     notifySub' c "" $ ERR e
 
 processClientNotices :: AgentClient -> SMPTransportSession -> [(RcvQueueSub, Maybe ClientNotice)] -> AM' ()
@@ -1982,6 +1982,28 @@ getQueueLink c nm userId server lnkId =
     getViaProxy smp proxySess = proxyGetSMPQueueLink smp nm proxySess lnkId
     getDirectly smp = getSMPQueueLink smp nm lnkId
 
+-- | Resolve a public-namespace name. Prefers PFWD (hides client IP from the
+-- resolver) and falls back to a direct send when the proxy is unavailable
+-- (faster but exposes the client IP). Mode selection is delegated to
+-- `sendOrProxySMPCommand`, which honours the network config (SPMNever etc.).
+resolveName :: AgentClient -> NetworkRequestMode -> UserId -> SMPServer -> SimplexDomain -> AM NameRecord
+resolveName c nm userId server domain =
+  snd <$> sendOrProxySMPCommand c nm userId server "" "RSLV" NoEntity resolveViaProxy resolveDirectly
+  where
+    resolveViaProxy smp proxySess = proxyResolveName smp nm proxySess domain
+    resolveDirectly smp = directResolveName smp nm domain
+
+-- | Pick a names-capable server for the user (the agent owns server selection,
+-- accounting for the names role). nameSrvs is opt-in (a plain list); empty means
+-- no server resolves names - a declared agent error, never a fallback.
+getNextNameServer :: AgentClient -> UserId -> AM SMPServer
+getNextNameServer c userId =
+  liftIO (TM.lookupIO userId (userServers c :: TMap UserId (UserServers 'PSMP))) >>= \case
+    Just UserServers {nameSrvs} -> case L.nonEmpty nameSrvs of
+      Just srvs -> protoServer <$> pickServer srvs
+      Nothing -> throwE NO_NAME_SERVERS
+    Nothing -> throwE $ INTERNAL "unknown userId - no user servers"
+
 enableQueueNotifications :: AgentClient -> RcvQueue -> SMP.NtfPublicAuthKey -> SMP.RcvNtfPublicDhKey -> AM (SMP.NotifierId, SMP.RcvNtfPublicDhKey)
 enableQueueNotifications c rq@RcvQueue {rcvId, rcvPrivateKey} notifierKey rcvNtfPublicDhKey =
   withSMPClient c NRMBackground rq "NKEY <nkey>" $ \smp ->
@@ -2226,7 +2248,7 @@ cryptoError :: C.CryptoError -> AgentErrorType
 cryptoError = \case
   C.CryptoLargeMsgError -> CMD LARGE "CryptoLargeMsgError"
   C.CryptoHeaderError _ -> AGENT A_MESSAGE -- parsing error
-  C.CERatchetDuplicateMessage -> AGENT A_DUPLICATE
+  C.CERatchetDuplicateMessage -> AGENT $ A_DUPLICATE Nothing
   C.AESDecryptError -> c DECRYPT_AES
   C.CBDecryptError -> c DECRYPT_CB
   C.CERatchetHeader -> c RATCHET_HEADER

src/Simplex/Messaging/Agent/Env/SQLite.hs

@@ -105,12 +105,13 @@ data ServerCfg p = ServerCfg
 
 data ServerRoles = ServerRoles
   { storage :: Bool,
-    proxy :: Bool
+    proxy :: Bool,
+    names :: Bool
   }
   deriving (Show)
 
 allRoles :: ServerRoles
-allRoles = ServerRoles True True
+allRoles = ServerRoles True True True
 
 presetServerCfg :: Bool -> ServerRoles -> Maybe OperatorId -> ProtoServerWithAuth p -> ServerCfg p
 presetServerCfg enabled roles operator server =
@@ -119,6 +120,9 @@ presetServerCfg enabled roles operator server =
 data UserServers p = UserServers
   { storageSrvs :: NonEmpty (Maybe OperatorId, ProtoServerWithAuth p),
     proxySrvs :: NonEmpty (Maybe OperatorId, ProtoServerWithAuth p),
+    -- name resolution is opt-in: a plain list (NOT NonEmpty, no fallback-to-all).
+    -- Empty = no servers resolve names = a clean agent error, never falls back.
+    nameSrvs :: [(Maybe OperatorId, ProtoServerWithAuth p)],
     knownHosts :: Set TransportHost
   }
 
@@ -126,9 +130,10 @@ type OperatorId = Int64
 
 -- This function sets all servers as enabled in case all passed servers are disabled.
 mkUserServers :: NonEmpty (ServerCfg p) -> UserServers p
-mkUserServers srvs = UserServers {storageSrvs = filterSrvs storage, proxySrvs = filterSrvs proxy, knownHosts}
+mkUserServers srvs = UserServers {storageSrvs = filterSrvs storage, proxySrvs = filterSrvs proxy, nameSrvs, knownHosts}
   where
     filterSrvs role = L.map (\ServerCfg {operator, server} -> (operator, server)) $ fromMaybe srvs $ L.nonEmpty $ L.filter (\ServerCfg {enabled, roles} -> enabled && role roles) srvs
+    nameSrvs = map (\ServerCfg {operator, server} -> (operator, server)) $ L.filter (\ServerCfg {enabled, roles} -> enabled && names roles) srvs
     knownHosts = S.unions $ L.map (\ServerCfg {server = ProtoServerWithAuth srv _} -> serverHosts srv) srvs
 
 serverHosts :: ProtocolServer p -> Set TransportHost
@@ -169,10 +174,12 @@ data AgentConfig = AgentConfig
     ntfBatchSize :: Int,
     ntfSubFirstCheckInterval :: NominalDiffTime,
     ntfSubCheckInterval :: NominalDiffTime,
-    maxPendingSubscriptions :: Int,
+    subsBatchSize :: Int,
     caCertificateFile :: FilePath,
     privateKeyFile :: FilePath,
     certificateFile :: FilePath,
+    rcvExpireCount :: Int,
+    rcvExpireInterval :: NominalDiffTime,
     e2eEncryptVRange :: VersionRangeE2E,
     smpAgentVRange :: VersionRangeSMPA,
     smpClientVRange :: VersionRangeSMPC
@@ -242,12 +249,14 @@ defaultAgentConfig =
       ntfBatchSize = 150,
       ntfSubFirstCheckInterval = nominalDay,
       ntfSubCheckInterval = 3 * nominalDay,
-      maxPendingSubscriptions = 35000,
+      subsBatchSize = 1350,
       -- CA certificate private key is not needed for initialization
       -- ! we do not generate these
       caCertificateFile = "/etc/opt/simplex-agent/ca.crt",
       privateKeyFile = "/etc/opt/simplex-agent/agent.key",
       certificateFile = "/etc/opt/simplex-agent/agent.crt",
+      rcvExpireCount = 8,
+      rcvExpireInterval = nominalDay,
       e2eEncryptVRange = supportedE2EEncryptVRange,
       smpAgentVRange = supportedSMPAgentVRange,
       smpClientVRange = supportedSMPClientVRange

src/Simplex/Messaging/Agent/Protocol.hs

@@ -122,6 +122,10 @@ module Simplex.Messaging.Agent.Protocol
     OwnerId,
     ConnectionLink (..),
     AConnectionLink (..),
+    SimplexNameInfo (..),
+    SimplexDomain (..),
+    SimplexTLD (..),
+    SimplexNameType (..),
     ConnShortLink (..),
     AConnShortLink (..),
     CreatedConnLink (..),
@@ -133,16 +137,21 @@ module Simplex.Messaging.Agent.Protocol
     validateOwners,
     validateLinkOwners,
     sameConnReqContact,
+    sameConnShortLink,
     sameShortLinkContact,
+    sameShortLinkInv,
     simplexChat,
     connReqUriP',
     simplexConnReqUri,
     simplexShortLink,
+    fullDomainName,
+    shortNameInfoStr,
     AgentErrorType (..),
     CommandErrorType (..),
     ConnectionErrorType (..),
     BrokerErrorType (..),
     SMPAgentError (..),
+    DroppedMsg (..),
     AgentCryptoError (..),
     cryptoErrToSyncState,
     ATransmission,
@@ -229,6 +238,7 @@ import Simplex.Messaging.Crypto.Ratchet
   )
 import Simplex.Messaging.Encoding
 import Simplex.Messaging.Encoding.String
+import Simplex.Messaging.SimplexName (SimplexDomain (..), SimplexNameInfo (..), SimplexNameType (..), SimplexTLD (..), fullDomainName, shortNameInfoStr)
 import Simplex.Messaging.Parsers
 import Simplex.Messaging.Protocol
   ( AProtocolType,
@@ -798,6 +808,12 @@ data MsgMeta = MsgMeta
   }
   deriving (Eq, Show)
 
+data DroppedMsg = DroppedMsg
+  { brokerTs :: UTCTime,
+    attempts :: Int
+  }
+  deriving (Eq, Show)
+
 data SMPConfirmation = SMPConfirmation
   { -- | sender's public key to use for authentication of sender's commands at the recepient's server
     senderKey :: Maybe SndPublicAuthKey,
@@ -1675,6 +1691,10 @@ ctTypeChar = \case
   CCTRelay -> 'R'
 {-# INLINE ctTypeChar #-}
 
+instance StrEncoding ContactConnType where
+  strEncode = B.singleton . ctTypeChar
+  strP = A.anyChar >>= ctTypeP
+
 -- the servers passed to this function should be all preset servers, not servers configured by the user.
 shortenShortLink :: NonEmpty SMPServer -> ConnShortLink m -> ConnShortLink m
 shortenShortLink presetSrvs = \case
@@ -1718,10 +1738,21 @@ sameConnReqContact (CRContactUri ConnReqUriData {crSmpQueues = qs}) (CRContactUr
   where
     same (q, q') = sameQAddress (qAddress q) (qAddress q')
 
+sameConnShortLink :: AConnShortLink -> AConnShortLink -> Bool
+sameConnShortLink (ACSL m sl) (ACSL m' sl') = case testEquality m m' of
+  Just Refl -> case sl of
+    CSLContact {} -> sameShortLinkContact sl sl'
+    CSLInvitation {} -> sameShortLinkInv sl sl'
+  Nothing -> False
+
 sameShortLinkContact :: ConnShortLink 'CMContact -> ConnShortLink 'CMContact -> Bool
 sameShortLinkContact (CSLContact _ ct srv k) (CSLContact _ ct' srv' k') =
   ct == ct' && sameSrvAddr srv srv' && k == k'
 
+sameShortLinkInv :: ConnShortLink 'CMInvitation -> ConnShortLink 'CMInvitation -> Bool
+sameShortLinkInv (CSLInvitation _ srv lnkId k) (CSLInvitation _ srv' lnkId' k') =
+  sameSrvAddr srv srv' && lnkId == lnkId' && k == k'
+
 checkConnMode :: forall t m m'. (ConnectionModeI m, ConnectionModeI m') => t m' -> Either String (t m)
 checkConnMode c = case testEquality (sConnectionMode @m) (sConnectionMode @m') of
   Just Refl -> Right c
@@ -1984,6 +2015,9 @@ data AgentErrorType
     XFTP {serverAddress :: String, xftpErr :: XFTPErrorType}
   | -- | XFTP agent errors
     FILE {fileErr :: FileErrorType}
+  | -- | no name-resolving servers configured for the user (agent-origin).
+    -- Server-origin name errors arrive forwarded as SMP _ (NAME ...) instead.
+    NO_NAME_SERVERS
   | -- | SMP proxy errors
     PROXY {proxyServer :: String, relayServer :: String, proxyErr :: ProxyClientError}
   | -- | XRCP protocol errors forwarded to agent clients
@@ -2050,12 +2084,13 @@ data SMPAgentError
     A_LINK {linkErr :: String}
   | -- | cannot decrypt message
     A_CRYPTO {cryptoErr :: AgentCryptoError}
-  | -- | duplicate message - this error is detected by ratchet decryption - this message will be ignored and not shown
-    -- it may also indicate a loss of ratchet synchronization (when only one message is sent via copied ratchet)
-    A_DUPLICATE
+  | -- | duplicate message - this error is detected by ratchet decryption - this message will be ignored and not shown.
+    -- it may also indicate a loss of ratchet synchronization (when only one message is sent via copied ratchet).
+    -- when message is dropped after too many reception attempts, DroppedMsg is included.
+    A_DUPLICATE {droppedMsg_ :: Maybe DroppedMsg}
   | -- | error in the message to add/delete/etc queue in connection
     A_QUEUE {queueErr :: String}
-  deriving (Eq, Read, Show, Exception)
+  deriving (Eq, Show, Exception)
 
 data AgentCryptoError
   = -- | AES decryption error
@@ -2165,6 +2200,8 @@ $(J.deriveJSON (sumTypeJSON id) ''ConnectionErrorType)
 
 $(J.deriveJSON (sumTypeJSON id) ''AgentCryptoError)
 
+$(J.deriveJSON defaultJSON ''DroppedMsg)
+
 $(J.deriveJSON (sumTypeJSON id) ''SMPAgentError)
 
 $(J.deriveJSON (sumTypeJSON id) ''AgentErrorType)
@@ -2191,3 +2228,4 @@ instance FromJSON ACreatedConnLink where
 instance ToJSON ACreatedConnLink where
   toEncoding (ACCL _ ccLink) = toEncoding ccLink
   toJSON (ACCL _ ccLink) = toJSON ccLink
+

src/Simplex/Messaging/Agent/Store/AgentStore.hs

@@ -140,6 +140,7 @@ module Simplex.Messaging.Agent.Store.AgentStore
     setMsgUserAck,
     getRcvMsg,
     getLastMsg,
+    incMsgRcvAttempts,
     checkRcvMsgHashExists,
     getRcvMsgBrokerTs,
     deleteMsg,
@@ -410,23 +411,23 @@ deleteUsersWithoutConns db = do
   forM_ userIds $ DB.execute db "DELETE FROM users WHERE user_id = ?" . Only
   pure userIds
 
-createClientService :: DB.Connection -> UserId -> SMPServer -> (C.KeyHash, TLS.Credential) -> IO ()
-createClientService db userId srv (kh, (cert, pk)) = do
+createClientService :: DB.Connection -> UserId -> SMPServer -> (C.KeyHash, TLS.Credential) -> IO ((C.KeyHash, TLS.Credential), Maybe ServiceId)
+createClientService db userId srv tlsCreds@(kh, (cert, pk)) = do
   serverKeyHash_ <- createServer db srv
-  DB.execute
-    db
-    [sql|
-      INSERT INTO client_services
-        (user_id, host, port, server_key_hash, service_cert_hash, service_cert, service_priv_key)
-      VALUES (?,?,?,?,?,?,?)
-      ON CONFLICT (user_id, host, port, server_key_hash)
-      DO UPDATE SET
-        service_cert_hash = EXCLUDED.service_cert_hash,
-        service_cert = EXCLUDED.service_cert,
-        service_priv_key = EXCLUDED.service_priv_key,
-        service_id = NULL
-    |]
-    (userId, host srv, port srv, serverKeyHash_, kh, cert, pk)
+  (rs :: [Only Int]) <-
+    DB.query
+      db
+      [sql|
+        INSERT INTO client_services
+          (user_id, host, port, server_key_hash, service_cert_hash, service_cert, service_priv_key)
+        VALUES (?,?,?,?,?,?,?)
+        ON CONFLICT (user_id, host, port, server_key_hash) DO NOTHING
+        RETURNING 1
+      |]
+      (userId, host srv, port srv, serverKeyHash_, kh, cert, pk)
+  if null rs
+    then fromMaybe (tlsCreds, Nothing) <$> getClientServiceCredentials db userId srv
+    else pure (tlsCreds, Nothing)
 
 getClientServiceCredentials :: DB.Connection -> UserId -> SMPServer -> IO (Maybe ((C.KeyHash, TLS.Credential), Maybe ServiceId))
 getClientServiceCredentials db userId srv =
@@ -1226,6 +1227,19 @@ toRcvMsg ((agentMsgId, internalTs, brokerId, brokerTs) :. (sndMsgId, integrity,
       msgReceipt = MsgReceipt <$> rcptInternalId_ <*> rcptStatus_
    in RcvMsg {internalId = InternalId agentMsgId, msgMeta, msgType, msgBody, internalHash, msgReceipt, userAck}
 
+incMsgRcvAttempts :: DB.Connection -> ConnId -> InternalId -> IO Int
+incMsgRcvAttempts db connId (InternalId msgId) =
+  fromOnly . head
+    <$> DB.query
+      db
+      [sql|
+        UPDATE rcv_messages
+        SET receive_attempts = receive_attempts + 1
+        WHERE conn_id = ? AND internal_id = ?
+        RETURNING receive_attempts
+      |]
+      (connId, msgId)
+
 checkRcvMsgHashExists :: DB.Connection -> ConnId -> ByteString -> IO Bool
 checkRcvMsgHashExists db connId hash =
   maybeFirstRow' False fromOnlyBI $
@@ -1345,11 +1359,11 @@ deleteSndMsgsExpired db ttl limit = do
     |]
     (cutoffTs, limit)
 
-createRatchetX3dhKeys :: DB.Connection -> ConnId -> C.PrivateKeyX448 -> C.PrivateKeyX448 -> Maybe CR.RcvPrivRKEMParams -> IO ()
-createRatchetX3dhKeys db connId x3dhPrivKey1 x3dhPrivKey2 pqPrivKem =
+createRatchetX3dhKeys :: DB.Connection -> ConnId -> CR.RcvE2EPrivRatchetParams 'C.X448 -> IO ()
+createRatchetX3dhKeys db connId (x3dhPrivKey1, x3dhPrivKey2, pqPrivKem) =
   DB.execute db "INSERT INTO ratchets (conn_id, x3dh_priv_key_1, x3dh_priv_key_2, pq_priv_kem) VALUES (?, ?, ?, ?)" (connId, x3dhPrivKey1, x3dhPrivKey2, pqPrivKem)
 
-getRatchetX3dhKeys :: DB.Connection -> ConnId -> IO (Either StoreError (C.PrivateKeyX448, C.PrivateKeyX448, Maybe CR.RcvPrivRKEMParams))
+getRatchetX3dhKeys :: DB.Connection -> ConnId -> IO (Either StoreError (CR.RcvE2EPrivRatchetParams 'C.X448))
 getRatchetX3dhKeys db connId =
   firstRow' keys SEX3dhKeysNotFound $
     DB.query db "SELECT x3dh_priv_key_1, x3dh_priv_key_2, pq_priv_kem FROM ratchets WHERE conn_id = ?" (Only connId)
@@ -1359,8 +1373,8 @@ getRatchetX3dhKeys db connId =
       _ -> Left SEX3dhKeysNotFound
 
 -- used to remember new keys when starting ratchet re-synchronization
-setRatchetX3dhKeys :: DB.Connection -> ConnId -> C.PrivateKeyX448 -> C.PrivateKeyX448 -> Maybe CR.RcvPrivRKEMParams -> IO ()
-setRatchetX3dhKeys db connId x3dhPrivKey1 x3dhPrivKey2 pqPrivKem =
+setRatchetX3dhKeys :: DB.Connection -> ConnId -> CR.RcvE2EPrivRatchetParams 'C.X448 -> IO ()
+setRatchetX3dhKeys db connId (x3dhPrivKey1, x3dhPrivKey2, pqPrivKem) =
   DB.execute
     db
     [sql|
@@ -2336,14 +2350,14 @@ getSubscriptionServers db onlyNeeded =
     toUserServer (userId, host, port, keyHash) = (userId, SMPServer host port keyHash)
 
 -- TODO [certs rcv] check index for getting queues with service present
-getUserServerRcvQueueSubs :: DB.Connection -> UserId -> SMPServer -> Bool -> ServiceAssoc -> IO [RcvQueueSub]
-getUserServerRcvQueueSubs db userId (SMPServer h p kh) onlyNeeded hasService =
-  map toRcvQueueSub
-    <$> DB.query
-      db
-      (rcvQueueSubQuery <> toSubscribe <> " c.deleted = 0 AND q.deleted = 0 AND c.user_id = ? AND q.host = ? AND q.port = ? AND COALESCE(q.server_key_hash, s.key_hash) = ?" <> serviceCond)
-      (userId, h, p, kh)
+getUserServerRcvQueueSubs :: DB.Connection -> UserId -> SMPServer -> Bool -> ServiceAssoc -> Int -> Maybe SMP.RecipientId -> IO [RcvQueueSub]
+getUserServerRcvQueueSubs db userId (SMPServer h p kh) onlyNeeded hasService limit cursor_ =
+  map toRcvQueueSub <$> case cursor_ of
+    Nothing -> DB.query db (q <> orderLimit) (userId, h, p, kh, limit)
+    Just cursor -> DB.query db (q <> " AND q.rcv_id > ? " <> orderLimit) (userId, h, p, kh, cursor, limit)
   where
+    q = rcvQueueSubQuery <> toSubscribe <> " c.deleted = 0 AND q.deleted = 0 AND c.user_id = ? AND q.host = ? AND q.port = ? AND COALESCE(q.server_key_hash, s.key_hash) = ?" <> serviceCond
+    orderLimit = " ORDER BY q.rcv_id LIMIT ?"
     toSubscribe
       | onlyNeeded = " WHERE q.to_subscribe = 1 AND "
       | otherwise = " WHERE "
@@ -2385,12 +2399,18 @@ unassocUserServerRcvQueueSubs' db userId srv@(SMPServer h p kh) = do
 unsetQueuesToSubscribe :: DB.Connection -> IO ()
 unsetQueuesToSubscribe db = DB.execute_ db "UPDATE rcv_queues SET to_subscribe = 0 WHERE to_subscribe = 1"
 
-setRcvServiceAssocs :: SMPQueue q => DB.Connection -> [q] -> IO ()
-setRcvServiceAssocs db rqs = do
+setRcvServiceAssocs :: SMPQueue q => DB.Connection -> SMPServer -> [q] -> IO ()
+setRcvServiceAssocs db ProtocolServer {host, port} rqs =
 #if defined(dbPostgres)
-  DB.execute db "UPDATE rcv_queues SET rcv_service_assoc = 1 WHERE rcv_id IN ?" $ Only $ In (map queueId rqs)
+  DB.execute
+    db
+    "UPDATE rcv_queues SET rcv_service_assoc = 1 WHERE host = ? AND port = ? AND rcv_id IN ?"
+    (host, port, In (map queueId rqs))
 #else
-  DB.executeMany db "UPDATE rcv_queues SET rcv_service_assoc = 1 WHERE rcv_id = ?" $ map (Only . queueId) rqs
+  DB.executeMany
+    db
+    "UPDATE rcv_queues SET rcv_service_assoc = 1 WHERE host = ? AND port = ? AND rcv_id = ?"
+    (map (\q -> (host, port, queueId q)) rqs)
 #endif
 
 removeRcvServiceAssocs :: DB.Connection -> UserId -> SMPServer -> IO ()

src/Simplex/Messaging/Agent/Store/Postgres/Migrations/App.hs

@@ -11,7 +11,8 @@ import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20250702_conn_invitati
 import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20251009_queue_to_subscribe
 import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20251010_client_notices
 import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20251230_strict_tables
-import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260115_service_certs
+import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260410_receive_attempts
+import Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260411_service_certs
 import Simplex.Messaging.Agent.Store.Shared (Migration (..))
 
 schemaMigrations :: [(String, Text, Maybe Text)]
@@ -23,7 +24,8 @@ schemaMigrations =
     ("20251009_queue_to_subscribe", m20251009_queue_to_subscribe, Just down_m20251009_queue_to_subscribe),
     ("20251010_client_notices", m20251010_client_notices, Just down_m20251010_client_notices),
     ("20251230_strict_tables", m20251230_strict_tables, Just down_m20251230_strict_tables),
-    ("20260115_service_certs", m20260115_service_certs, Just down_m20260115_service_certs)
+    ("20260410_receive_attempts", m20260410_receive_attempts, Just down_m20260410_receive_attempts),
+    ("20260411_service_certs", m20260411_service_certs, Just down_m20260411_service_certs)
   ]
 
 -- | The list of migrations in ascending order by date

src/Simplex/Messaging/Agent/Store/Postgres/Migrations/M20260410_receive_attempts.hs

@@ -0,0 +1,19 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE QuasiQuotes #-}
+
+module Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260410_receive_attempts where
+
+import Data.Text (Text)
+import Text.RawString.QQ (r)
+
+m20260410_receive_attempts :: Text
+m20260410_receive_attempts =
+  [r|
+ALTER TABLE rcv_messages ADD COLUMN receive_attempts SMALLINT NOT NULL DEFAULT 0;
+|]
+
+down_m20260410_receive_attempts :: Text
+down_m20260410_receive_attempts =
+  [r|
+ALTER TABLE rcv_messages DROP COLUMN receive_attempts;
+|]

src/Simplex/Messaging/Agent/Store/Postgres/Migrations/M20260411_service_certs.hs

@@ -1,14 +1,14 @@
 {-# LANGUAGE OverloadedStrings #-}
 {-# LANGUAGE QuasiQuotes #-}
 
-module Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260115_service_certs where
+module Simplex.Messaging.Agent.Store.Postgres.Migrations.M20260411_service_certs where
 
 import Data.Text (Text)
 import Simplex.Messaging.Agent.Store.Postgres.Migrations.Util
 import Text.RawString.QQ (r)
 
-m20260115_service_certs :: Text
-m20260115_service_certs =
+m20260411_service_certs :: Text
+m20260411_service_certs =
   createXorHashFuncs <> [r|
 CREATE TABLE client_services(
   user_id BIGINT NOT NULL REFERENCES users ON UPDATE RESTRICT ON DELETE CASCADE,
@@ -92,8 +92,8 @@ AFTER UPDATE ON rcv_queues
 FOR EACH ROW EXECUTE PROCEDURE on_rcv_queue_update();
     |]
 
-down_m20260115_service_certs :: Text
-down_m20260115_service_certs =
+down_m20260411_service_certs :: Text
+down_m20260411_service_certs =
   [r|
 DROP TRIGGER tr_rcv_queue_insert ON rcv_queues;
 DROP TRIGGER tr_rcv_queue_delete ON rcv_queues;

src/Simplex/Messaging/Agent/Store/Postgres/Migrations/agent_postgres_schema.sql

@@ -527,7 +527,8 @@ CREATE TABLE smp_agent_test_protocol_schema.rcv_messages (
     external_prev_snd_hash bytea NOT NULL,
     integrity bytea NOT NULL,
     user_ack smallint DEFAULT 0,
-    rcv_queue_id bigint NOT NULL
+    rcv_queue_id bigint NOT NULL,
+    receive_attempts smallint DEFAULT 0 NOT NULL
 );
 
 

src/Simplex/Messaging/Agent/Store/SQLite.hs

@@ -50,7 +50,6 @@ import Data.Bits (xor)
 import Data.ByteArray (ScrubbedBytes)
 import qualified Data.ByteArray as BA
 import Data.ByteString (ByteString)
-import qualified Data.ByteString as B
 import Data.Functor (($>))
 import Data.IORef
 import Data.Maybe (fromMaybe)

src/Simplex/Messaging/Agent/Store/SQLite/Migrations/App.hs

@@ -47,7 +47,8 @@ import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20250702_conn_invitation
 import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20251009_queue_to_subscribe
 import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20251010_client_notices
 import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20251230_strict_tables
-import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260115_service_certs
+import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260410_receive_attempts
+import Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260411_service_certs
 import Simplex.Messaging.Agent.Store.Shared (Migration (..))
 
 schemaMigrations :: [(String, Query, Maybe Query)]
@@ -95,7 +96,8 @@ schemaMigrations =
     ("m20251009_queue_to_subscribe", m20251009_queue_to_subscribe, Just down_m20251009_queue_to_subscribe),
     ("m20251010_client_notices", m20251010_client_notices, Just down_m20251010_client_notices),
     ("m20251230_strict_tables", m20251230_strict_tables, Just down_m20251230_strict_tables),
-    ("m20260115_service_certs", m20260115_service_certs, Just down_m20260115_service_certs)
+    ("m20260410_receive_attempts", m20260410_receive_attempts, Just down_m20260410_receive_attempts),
+    ("m20260411_service_certs", m20260411_service_certs, Just down_m20260411_service_certs)
   ]
 
 -- | The list of migrations in ascending order by date

src/Simplex/Messaging/Agent/Store/SQLite/Migrations/M20260410_receive_attempts.hs

@@ -0,0 +1,18 @@
+{-# LANGUAGE QuasiQuotes #-}
+
+module Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260410_receive_attempts where
+
+import Database.SQLite.Simple (Query)
+import Database.SQLite.Simple.QQ (sql)
+
+m20260410_receive_attempts :: Query
+m20260410_receive_attempts =
+  [sql|
+ALTER TABLE rcv_messages ADD COLUMN receive_attempts INTEGER NOT NULL DEFAULT 0;
+|]
+
+down_m20260410_receive_attempts :: Query
+down_m20260410_receive_attempts =
+  [sql|
+ALTER TABLE rcv_messages DROP COLUMN receive_attempts;
+|]

src/Simplex/Messaging/Agent/Store/SQLite/Migrations/M20260411_service_certs.hs

@@ -1,12 +1,12 @@
 {-# LANGUAGE QuasiQuotes #-}
 
-module Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260115_service_certs where
+module Simplex.Messaging.Agent.Store.SQLite.Migrations.M20260411_service_certs where
 
 import Database.SQLite.Simple (Query)
 import Database.SQLite.Simple.QQ (sql)
 
-m20260115_service_certs :: Query
-m20260115_service_certs =
+m20260411_service_certs :: Query
+m20260411_service_certs =
   [sql|
 CREATE TABLE client_services(
   user_id INTEGER NOT NULL REFERENCES users ON DELETE CASCADE,
@@ -76,8 +76,8 @@ BEGIN
 END;
   |]
 
-down_m20260115_service_certs :: Query
-down_m20260115_service_certs =
+down_m20260411_service_certs :: Query
+down_m20260411_service_certs =
   [sql|
 DROP TRIGGER tr_rcv_queue_insert;
 DROP TRIGGER tr_rcv_queue_delete;

src/Simplex/Messaging/Agent/Store/SQLite/Migrations/agent_schema.sql

@@ -120,6 +120,7 @@ CREATE TABLE rcv_messages(
   integrity BLOB NOT NULL,
   user_ack INTEGER NULL DEFAULT 0,
   rcv_queue_id INTEGER CHECK(rcv_queue_id NOT NULL),
+  receive_attempts INTEGER NOT NULL DEFAULT 0,
   PRIMARY KEY(conn_id, internal_rcv_id),
   FOREIGN KEY(conn_id, internal_id) REFERENCES messages
   ON DELETE CASCADE

src/Simplex/Messaging/Client.hs

@@ -73,6 +73,8 @@ module Simplex.Messaging.Client
     deleteSMPQueues,
     connectSMPProxiedRelay,
     proxySMPMessage,
+    proxyResolveName,
+    directResolveName,
     forwardSMPTransmission,
     getSMPQueueInfo,
     sendProtocolCommand,
@@ -164,6 +166,7 @@ import Simplex.Messaging.Parsers (defaultJSON, dropPrefix, enumJSON, sumTypeJSON
 import Simplex.Messaging.Protocol
 import Simplex.Messaging.Protocol.Types
 import Simplex.Messaging.Server.QueueStore.QueueInfo
+import Simplex.Messaging.SimplexName (SimplexDomain)
 import Simplex.Messaging.TMap (TMap)
 import qualified Simplex.Messaging.TMap as TM
 import Simplex.Messaging.Transport
@@ -1046,6 +1049,33 @@ sendSMPMessage c nm spKey sId flags msg =
 proxySMPMessage :: SMPClient -> NetworkRequestMode -> ProxiedRelay -> Maybe SndPrivateAuthKey -> SenderId -> MsgFlags -> MsgBody -> ExceptT SMPClientError IO (Either ProxyClientError ())
 proxySMPMessage c nm proxiedRelay spKey sId flags msg = proxyOKSMPCommand c nm proxiedRelay spKey sId (SEND flags msg)
 
+-- | Resolve a public-namespace name via PFWD. Preferred path - hides the
+-- client IP from the resolver. Mirrors `proxySMPMessage`'s shape; routes
+-- through `proxySMPCommand` and pattern-matches the expected RNAME response.
+-- Version-gated on the destination relay (mirrors `connectSMPProxiedRelay`):
+-- the client never sends RSLV to a relay that predates names support.
+proxyResolveName :: SMPClient -> NetworkRequestMode -> ProxiedRelay -> SimplexDomain -> ExceptT SMPClientError IO (Either ProxyClientError NameRecord)
+proxyResolveName c nm proxiedRelay name
+  | prVersion proxiedRelay >= namesSMPVersion =
+      proxySMPCommand c nm proxiedRelay Nothing NoEntity (RSLV name) >>= \case
+        Right (RNAME nr) -> pure $ Right nr
+        Right r -> throwE $ unexpectedResponse r
+        Left e -> pure $ Left e
+  | otherwise = throwE $ PCETransportError TEVersion
+
+-- | Direct (non-PFWD) name resolution. Exposes the client IP to the resolver;
+-- callers that want anonymity should use `proxyResolveName` via the standard
+-- proxy fallback in the agent. RSLV requires no entity ID or authorization
+-- (see `noAuthCmd` in Protocol.hs). Version-gated on the session here, not the
+-- encoder, so an old server never receives RSLV.
+directResolveName :: SMPClient -> NetworkRequestMode -> SimplexDomain -> ExceptT SMPClientError IO NameRecord
+directResolveName c nm name
+  | thVersion (thParams c) >= namesSMPVersion =
+      sendProtocolCommand c nm Nothing NoEntity (Cmd SResolver (RSLV name)) >>= \case
+        RNAME nr -> pure nr
+        r -> throwE $ unexpectedResponse r
+  | otherwise = throwE $ PCETransportError TEVersion
+
 -- | Acknowledge message delivery (server deletes the message).
 --
 -- https://github.com/simplex-chat/simplexmq/blob/master/protocol/simplex-messaging.md#acknowledge-message-delivery

src/Simplex/Messaging/Client/Agent.hs

@@ -47,6 +47,7 @@ import Crypto.Random (ChaChaDRG)
 import Data.ByteString.Char8 (ByteString)
 import qualified Data.ByteString.Char8 as B
 import Data.Constraint (Dict (..))
+import Data.Functor (($>))
 import Data.List.NonEmpty (NonEmpty)
 import qualified Data.List.NonEmpty as L
 import Data.Map.Strict (Map)
@@ -106,7 +107,7 @@ data SMPClientAgentConfig = SMPClientAgentConfig
   { smpCfg :: ProtocolClientConfig SMPVersion,
     reconnectInterval :: RetryInterval,
     persistErrorInterval :: NominalDiffTime,
-    msgQSize :: Natural,
+    msgQSize :: Maybe Natural,
     agentQSize :: Natural,
     agentSubsBatchSize :: Int,
     ownServerDomains :: [ByteString]
@@ -123,7 +124,7 @@ defaultSMPClientAgentConfig =
             maxInterval = 10 * second
           },
       persistErrorInterval = 30, -- seconds
-      msgQSize = 2048,
+      msgQSize = Just 2048,
       agentQSize = 2048,
       agentSubsBatchSize = 1360,
       ownServerDomains = []
@@ -137,7 +138,7 @@ data SMPClientAgent p = SMPClientAgent
     dbService :: Maybe DBService,
     active :: TVar Bool,
     startedAt :: UTCTime,
-    msgQ :: TBQueue (ServerTransmissionBatch SMPVersion ErrorType BrokerMsg),
+    msgQ :: Maybe (TBQueue (ServerTransmissionBatch SMPVersion ErrorType BrokerMsg)),
     agentQ :: TBQueue SMPClientAgentEvent,
     randomDrg :: TVar ChaChaDRG,
     smpClients :: TMap SMPServer SMPClientVar,
@@ -161,7 +162,8 @@ newSMPClientAgent :: SParty p -> SMPClientAgentConfig -> Maybe DBService -> TVar
 newSMPClientAgent agentParty agentCfg@SMPClientAgentConfig {msgQSize, agentQSize} dbService randomDrg = do
   active <- newTVarIO True
   startedAt <- getCurrentTime
-  msgQ <- newTBQueueIO msgQSize
+  -- Only subscribing agents receive server transmissions, should not be created until processed to prevent deadlock.
+  msgQ <- mapM newTBQueueIO msgQSize
   agentQ <- newTBQueueIO agentQSize
   smpClients <- TM.emptyIO
   smpSessions <- TM.emptyIO
@@ -204,11 +206,8 @@ getSMPServerClient' ca srv = snd <$> getSMPServerClient'' ca srv
 getSMPServerClient'' :: SMPClientAgent p -> SMPServer -> ExceptT SMPClientError IO (OwnServer, SMPClient)
 getSMPServerClient'' ca@SMPClientAgent {agentCfg, smpClients, smpSessions, workerSeq} srv = do
   ts <- liftIO getCurrentTime
-  atomically (getClientVar ts) >>= either (ExceptT . newSMPClient) waitForSMPClient
+  withGetSessVar workerSeq srv smpClients ts (ExceptT . newSMPClient) waitForSMPClient
   where
-    getClientVar :: UTCTime -> STM (Either SMPClientVar SMPClientVar)
-    getClientVar = getSessVar workerSeq srv smpClients
-
     waitForSMPClient :: SMPClientVar -> ExceptT SMPClientError IO (OwnServer, SMPClient)
     waitForSMPClient v = do
       let ProtocolClientConfig {networkConfig = NetworkConfig {tcpConnectTimeout}} = smpCfg agentCfg
@@ -266,7 +265,7 @@ connectClient ca@SMPClientAgent {agentCfg, dbService, smpClients, smpSessions, m
   Nothing -> getClient cfg
   where
     cfg = smpCfg agentCfg
-    getClient cfg' = getProtocolClient randomDrg NRMBackground (1, srv, Nothing) cfg' [] (Just msgQ) startedAt clientDisconnected
+    getClient cfg' = getProtocolClient randomDrg NRMBackground (1, srv, Nothing) cfg' [] msgQ startedAt clientDisconnected
 
     clientDisconnected :: SMPClient -> IO ()
     clientDisconnected smp = do
@@ -324,12 +323,16 @@ reconnectClient ca@SMPClientAgent {active, agentCfg, smpSubWorkers, workerSeq} s
         (Just <$> getSessVar workerSeq srv smpSubWorkers ts)
     newSubWorker :: SessionVar (Async ()) -> IO ()
     newSubWorker v = do
-      a <- async $ void (E.try @E.SomeException runSubWorker) >> atomically (cleanup v)
+      a <- async $ void $ E.try @E.SomeException $ runSubWorker v
       atomically $ putTMVar (sessionVar v) a
-    runSubWorker =
+    runSubWorker v =
       withRetryInterval (reconnectInterval agentCfg) $ \_ loop -> do
-        subs <- getPending TM.lookupIO readTVarIO
-        unless (noPending subs) $ whenM (readTVarIO active) $ do
+        subs_ <- atomically $ do                                                                                                                            
+          s <- getPending TM.lookup readTVar                                                                                                                
+          if noPending s                                                                                                                                    
+            then cleanup v $> Nothing                                                                                                                       
+            else pure $ Just s                                                                                                                              
+        forM_ subs_ $ \subs -> whenM (readTVarIO active) $ do  
           void $ netTimeoutInt tcpConnectTimeout NRMBackground `timeout` runExceptT (reconnectSMPClient ca srv subs)
           loop
     ProtocolClientConfig {networkConfig = NetworkConfig {tcpConnectTimeout}} = smpCfg agentCfg

src/Simplex/Messaging/Compression.hs

@@ -7,6 +7,9 @@ module Simplex.Messaging.Compression
     compressionLevel,
     compress1,
     decompress1,
+    limitDecompress1,
+    limitDecompress',
+    decompressedSize,
   ) where
 
 import qualified Codec.Compression.Zstd as Z1
@@ -42,12 +45,28 @@ compress1 bs
   | B.length bs <= maxLengthPassthrough = Passthrough bs
   | otherwise = Compressed . Large $ Z1.compress compressionLevel bs
 
-decompress1 :: Int -> Compressed -> Either String ByteString
-decompress1 limit = \case
+decompressedSize :: Compressed -> Maybe Int
+decompressedSize = \case
+  Passthrough bs -> Just $ B.length bs
+  Compressed (Large bs) -> Z1.decompressedSize bs
+
+decompress1 :: Compressed -> Either String ByteString
+decompress1 = \case
   Passthrough bs -> Right bs
-  Compressed (Large bs) -> case Z1.decompressedSize bs of
-    Just sz | sz <= limit -> case Z1.decompress bs of
-      Z1.Error e -> Left e
-      Z1.Skip -> Right mempty
-      Z1.Decompress bs' -> Right bs'
-    _ -> Left $ "compressed size not specified or exceeds " <> show limit
+  Compressed (Large bs) -> decompress_ bs
+
+limitDecompress1 :: Int -> Compressed -> Either String ByteString
+limitDecompress1 limit = \case
+  Passthrough bs -> Right bs
+  Compressed (Large bs) -> limitDecompress' limit bs
+
+limitDecompress' :: Int -> ByteString -> Either String ByteString
+limitDecompress' limit bs = case Z1.decompressedSize bs of
+  Just sz | sz <= limit -> decompress_ bs
+  _ -> Left $ "compressed size not specified or exceeds " <> show limit
+
+decompress_ :: ByteString -> Either String ByteString
+decompress_ bs = case Z1.decompress bs of
+  Z1.Error e -> Left e
+  Z1.Skip -> Right mempty
+  Z1.Decompress bs' -> Right bs'

src/Simplex/Messaging/Crypto.hs

@@ -233,7 +233,7 @@ import qualified Data.Attoparsec.ByteString.Char8 as A
 import Data.Bifunctor (bimap, first)
 import Data.ByteArray (ByteArrayAccess)
 import qualified Data.ByteArray as BA
-import Data.ByteString.Base64 (decode, encode)
+import Data.ByteString.Base64 (decode)
 import qualified Data.ByteString.Base64.URL as U
 import Data.ByteString.Char8 (ByteString)
 import qualified Data.ByteString.Char8 as B
@@ -808,17 +808,22 @@ data ASignature
 deriving instance Show ASignature
 
 class CryptoSignature s where
-  serializeSignature :: s -> ByteString
-  serializeSignature = encode . signatureBytes
   signatureBytes :: s -> ByteString
   decodeSignature :: ByteString -> Either String s
 
 instance CryptoSignature (Signature s) => StrEncoding (Signature s) where
-  strEncode = serializeSignature
+  strEncode = strEncode . signatureBytes
   {-# INLINE strEncode #-}
   strDecode = decodeSignature
   {-# INLINE strDecode #-}
 
+instance CryptoSignature (Signature s) => ToJSON (Signature s) where
+  toJSON = strToJSON
+  toEncoding = strToJEncoding
+
+instance CryptoSignature (Signature s) => FromJSON (Signature s) where
+  parseJSON = strParseJSON "Signature"
+
 instance CryptoSignature (Signature s) => Encoding (Signature s) where
   smpEncode = smpEncode . signatureBytes
   {-# INLINE smpEncode #-}

src/Simplex/Messaging/Crypto/BBS.hs

@@ -0,0 +1,302 @@
+{-# LANGUAGE DataKinds #-}
+{-# LANGUAGE DerivingStrategies #-}
+{-# LANGUAGE DerivingVia #-}
+{-# LANGUAGE ForeignFunctionInterface #-}
+{-# LANGUAGE GeneralizedNewtypeDeriving #-}
+{-# LANGUAGE KindSignatures #-}
+{-# LANGUAGE ScopedTypeVariables #-}
+
+-- | FFI bindings to libbbs (BBS+ signatures over BLS12-381, SHA-256 suite).
+-- Values parsed from untrusted input are length-validated; see FixedBS and the
+-- BBSProof StrEncoding instance.
+module Simplex.Messaging.Crypto.BBS
+  ( BBSSecretKey (..),
+    BBSPublicKey (..),
+    BBSKeyPair,
+    BBSSignature (..),
+    BBSProof (..),
+    BBSHeader (..),
+    BBSPresHeader (..),
+    bbsKeyGen,
+    bbsPublicKey,
+    bbsSign,
+    bbsVerify,
+    bbsProofGen,
+    bbsProofVerify,
+  ) where
+
+import Data.Aeson (FromJSON, ToJSON)
+import Data.ByteString (ByteString)
+import qualified Data.ByteString as B
+import qualified Data.ByteString.Unsafe as BU
+import Data.Proxy (Proxy (..))
+import Foreign
+import Foreign.C
+import GHC.TypeLits (KnownNat, KnownSymbol, Nat, Symbol, natVal, symbolVal)
+import Simplex.Messaging.Encoding.String
+import System.IO.Unsafe (unsafePerformIO)
+
+-- Note: the data constructors below are unchecked escape hatches for trusted,
+-- internally-produced values (e.g. keygen output). Any value parsed from
+-- untrusted input (StrEncoding / FromJSON) is length-validated — see FixedBS
+-- and the BBSProof StrEncoding instance.
+
+newtype BBSSecretKey = BBSSecretKey ByteString
+  deriving newtype (Eq, Show)
+  deriving (StrEncoding) via (FixedBS "BBSSecretKey" 32)
+  deriving (ToJSON, FromJSON) via (StrJSON "BBSSecretKey" BBSSecretKey)
+
+newtype BBSPublicKey = BBSPublicKey ByteString
+  deriving newtype (Eq, Show)
+  deriving (StrEncoding) via (FixedBS "BBSPublicKey" 96)
+  deriving (ToJSON, FromJSON) via (StrJSON "BBSPublicKey" BBSPublicKey)
+
+type BBSKeyPair = (BBSPublicKey, BBSSecretKey)
+
+newtype BBSSignature = BBSSignature ByteString
+  deriving newtype (Eq, Show)
+  deriving (StrEncoding) via (FixedBS "BBSSignature" 80)
+  deriving (ToJSON, FromJSON) via (StrJSON "BBSSignature" BBSSignature)
+
+newtype BBSProof = BBSProof ByteString
+  deriving newtype (Eq, Show)
+  deriving (ToJSON, FromJSON) via (StrJSON "BBSProof" BBSProof)
+
+newtype BBSHeader = BBSHeader ByteString
+  deriving newtype (Eq, Show, StrEncoding)
+  deriving (ToJSON, FromJSON) via (StrJSON "BBSHeader" BBSHeader)
+
+newtype BBSPresHeader = BBSPresHeader ByteString
+  deriving newtype (Eq, Show, StrEncoding)
+  deriving (ToJSON, FromJSON) via (StrJSON "BBSPresHeader" BBSPresHeader)
+
+-- | A ByteString validated to be exactly @n@ bytes when parsed via StrEncoding
+-- (and the JSON derived from it). Local to BBS, where every key/signature is a
+-- fixed size; @name@ appears in the decode error only.
+newtype FixedBS (name :: Symbol) (n :: Nat) = FixedBS ByteString
+
+instance forall name n. (KnownSymbol name, KnownNat n) => StrEncoding (FixedBS name n) where
+  strEncode (FixedBS bs) = strEncode bs
+  strP = do
+    bs <- base64urlP
+    let n = fromIntegral (natVal (Proxy :: Proxy n))
+    if B.length bs == n
+      then pure (FixedBS bs)
+      else fail $ symbolVal (Proxy :: Proxy name) <> ": expected " <> show n <> " bytes, got " <> show (B.length bs)
+
+-- Constants
+
+bbsSkLen, bbsPkLen, bbsSigLen, bbsProofBaseLen, bbsProofUdElemLen :: Int
+bbsSkLen = 32
+bbsPkLen = 96
+bbsSigLen = 80
+bbsProofBaseLen = 272
+bbsProofUdElemLen = 32
+
+bbsProofLen :: Int -> Int
+bbsProofLen numUndisclosed = bbsProofBaseLen + numUndisclosed * bbsProofUdElemLen
+
+-- | A proof is @bbsProofBaseLen + 32 * numUndisclosed@ bytes; reject anything else.
+instance StrEncoding BBSProof where
+  strEncode (BBSProof bs) = strEncode bs
+  strP = do
+    bs <- base64urlP
+    let len = B.length bs
+    if len >= bbsProofBaseLen && (len - bbsProofBaseLen) `mod` bbsProofUdElemLen == 0
+      then pure (BBSProof bs)
+      else fail $ "BBS: invalid proof length " <> show len
+
+-- FFI
+
+data BBS_Ciphersuite
+
+foreign import ccall "bbs_keygen_full"
+  c_bbs_keygen_full :: Ptr BBS_Ciphersuite -> Ptr Word8 -> Ptr Word8 -> IO CInt
+
+foreign import ccall "bbs_sk_to_pk"
+  c_bbs_sk_to_pk :: Ptr BBS_Ciphersuite -> Ptr Word8 -> Ptr Word8 -> IO CInt
+
+foreign import ccall "bbs_sign"
+  c_bbs_sign ::
+    Ptr BBS_Ciphersuite ->
+    Ptr Word8 -> Ptr Word8 -> Ptr Word8 ->
+    Ptr Word8 -> CSize ->
+    CSize -> Ptr (Ptr Word8) -> Ptr CSize ->
+    IO CInt
+
+foreign import ccall "bbs_verify"
+  c_bbs_verify ::
+    Ptr BBS_Ciphersuite ->
+    Ptr Word8 -> Ptr Word8 ->
+    Ptr Word8 -> CSize ->
+    CSize -> Ptr (Ptr Word8) -> Ptr CSize ->
+    IO CInt
+
+foreign import ccall "bbs_proof_gen"
+  c_bbs_proof_gen ::
+    Ptr BBS_Ciphersuite ->
+    Ptr Word8 -> Ptr Word8 -> Ptr Word8 ->
+    Ptr Word8 -> CSize ->
+    Ptr Word8 -> CSize ->
+    Ptr CSize -> CSize ->
+    CSize -> Ptr (Ptr Word8) -> Ptr CSize ->
+    IO CInt
+
+foreign import ccall "bbs_proof_verify"
+  c_bbs_proof_verify ::
+    Ptr BBS_Ciphersuite ->
+    Ptr Word8 ->
+    Ptr Word8 -> CSize ->
+    Ptr Word8 -> CSize ->
+    Ptr Word8 -> CSize ->
+    Ptr CSize -> CSize ->
+    CSize -> Ptr (Ptr Word8) -> Ptr CSize ->
+    IO CInt
+
+foreign import ccall "&bbs_sha256_ciphersuite"
+  c_bbs_sha256_ciphersuite :: Ptr (Ptr BBS_Ciphersuite)
+
+-- The ciphersuite is a static const pointer in libbbs; read it once.
+ciphersuite :: Ptr BBS_Ciphersuite
+ciphersuite = unsafePerformIO $ peek c_bbs_sha256_ciphersuite
+{-# NOINLINE ciphersuite #-}
+
+-- Helpers
+
+withBS :: ByteString -> (Ptr Word8 -> CSize -> IO a) -> IO a
+withBS bs f = BU.unsafeUseAsCStringLen bs $ \(p, l) -> f (castPtr p) (fromIntegral l)
+
+packPtr :: Ptr Word8 -> Int -> IO ByteString
+packPtr ptr len = B.packCStringLen (castPtr ptr, len)
+
+-- Marshals a list of messages into parallel pointer/length arrays. Each
+-- ByteString is held alive (via nested unsafeUseAsCStringLen) until @f@ returns,
+-- so the C callee never sees a pointer to freed memory.
+withMessages :: [ByteString] -> (Ptr (Ptr Word8) -> Ptr CSize -> CSize -> IO a) -> IO a
+withMessages msgs f = go msgs []
+  where
+    go [] acc =
+      let cstrs = reverse acc
+       in withArray (map fst cstrs) $ \msgsPtr ->
+            withArray (map snd cstrs) $ \lensPtr ->
+              f msgsPtr lensPtr (fromIntegral $ length cstrs)
+    go (m : ms) acc =
+      BU.unsafeUseAsCStringLen m $ \(p, l) ->
+        go ms ((castPtr p :: Ptr Word8, fromIntegral l :: CSize) : acc)
+
+withIndexes :: [Int] -> (Ptr CSize -> CSize -> IO a) -> IO a
+withIndexes idxs f =
+  withArrayLen (map fromIntegral idxs :: [CSize]) $ \n ptr -> f ptr (fromIntegral n)
+
+-- libbbs expects disclosed indexes strictly ascending and in [0, total). This
+-- both matches the spec and guarantees the output-buffer size we compute matches
+-- what libbbs writes (no out-of-bounds write from a bad index list).
+ascendingInRange :: [Int] -> Int -> Bool
+ascendingInRange idxs total =
+  all (\i -> i >= 0 && i < total) idxs && and (zipWith (<) idxs (drop 1 idxs))
+
+-- Public API
+
+bbsKeyGen :: IO (Either String BBSKeyPair)
+bbsKeyGen =
+  allocaBytes bbsSkLen $ \skPtr ->
+    allocaBytes bbsPkLen $ \pkPtr -> do
+      rc <- c_bbs_keygen_full ciphersuite skPtr pkPtr
+      if rc /= 0
+        then pure $ Left "bbsKeyGen failed"
+        else do
+          sk <- packPtr skPtr bbsSkLen
+          pk <- packPtr pkPtr bbsPkLen
+          pure $ Right (BBSPublicKey pk, BBSSecretKey sk)
+
+bbsPublicKey :: BBSSecretKey -> IO (Either String BBSPublicKey)
+bbsPublicKey (BBSSecretKey sk) =
+  allocaBytes bbsPkLen $ \pkPtr ->
+    withBS sk $ \skPtr _ -> do
+      rc <- c_bbs_sk_to_pk ciphersuite skPtr pkPtr
+      if rc /= 0
+        then pure $ Left "bbsPublicKey failed"
+        else Right . BBSPublicKey <$> packPtr pkPtr bbsPkLen
+
+bbsSign ::
+  BBSSecretKey ->
+  BBSHeader ->
+  [ByteString] ->
+  IO (Either String BBSSignature)
+bbsSign secret@(BBSSecretKey sk) (BBSHeader header) msgs =
+  bbsPublicKey secret >>= either (pure . Left) sign'
+  where
+    sign' (BBSPublicKey pk) =
+      allocaBytes bbsSigLen $ \sigPtr ->
+        withBS sk $ \skPtr _ ->
+          withBS pk $ \pkPtr _ ->
+            withBS header $ \hdrPtr hdrLen ->
+              withMessages msgs $ \msgsPtr lensPtr n -> do
+                rc <- c_bbs_sign ciphersuite skPtr pkPtr sigPtr hdrPtr hdrLen n msgsPtr lensPtr
+                if rc /= 0
+                  then pure $ Left "bbsSign failed"
+                  else Right . BBSSignature <$> packPtr sigPtr bbsSigLen
+
+bbsVerify ::
+  BBSPublicKey ->
+  BBSSignature ->
+  BBSHeader ->
+  [ByteString] ->
+  IO Bool
+bbsVerify (BBSPublicKey pk) (BBSSignature sig) (BBSHeader header) msgs =
+  withBS pk $ \pkPtr _ ->
+    withBS sig $ \sigPtr _ ->
+      withBS header $ \hdrPtr hdrLen ->
+        withMessages msgs $ \msgsPtr lensPtr n -> do
+          rc <- c_bbs_verify ciphersuite pkPtr sigPtr hdrPtr hdrLen n msgsPtr lensPtr
+          pure (rc == 0)
+
+bbsProofGen ::
+  BBSPublicKey ->
+  BBSSignature ->
+  BBSHeader ->
+  BBSPresHeader ->
+  [Int] ->
+  [ByteString] ->
+  IO (Either String BBSProof)
+bbsProofGen (BBSPublicKey pk) (BBSSignature sig) (BBSHeader header) (BBSPresHeader ph) disclosedIdxs msgs
+  | not (ascendingInRange disclosedIdxs (length msgs)) = pure $ Left "bbsProofGen: invalid disclosed indexes"
+  | otherwise =
+  allocaBytes proofSz $ \proofPtr ->
+    withBS pk $ \pkPtr _ ->
+      withBS sig $ \sigPtr _ ->
+        withBS header $ \hdrPtr hdrLen ->
+          withBS ph $ \phPtr phLen ->
+            withIndexes disclosedIdxs $ \idxsPtr idxsLen ->
+              withMessages msgs $ \msgsPtr lensPtr n -> do
+                rc <- c_bbs_proof_gen ciphersuite pkPtr sigPtr proofPtr hdrPtr hdrLen phPtr phLen idxsPtr idxsLen n msgsPtr lensPtr
+                if rc /= 0
+                  then pure $ Left "bbsProofGen failed"
+                  else Right . BBSProof <$> packPtr proofPtr proofSz
+  where
+    numUndisclosed = length msgs - length disclosedIdxs
+    proofSz = bbsProofLen numUndisclosed
+
+bbsProofVerify ::
+  BBSPublicKey ->
+  BBSProof ->
+  BBSHeader ->
+  BBSPresHeader ->
+  [Int] ->
+  Int ->
+  [ByteString] ->
+  IO Bool
+bbsProofVerify (BBSPublicKey pk) (BBSProof proof) (BBSHeader header) (BBSPresHeader ph) disclosedIdxs numMessages disclosedMsgs
+  | numMessages < 0 = pure False
+  | length disclosedIdxs /= length disclosedMsgs = pure False
+  | not (ascendingInRange disclosedIdxs numMessages) = pure False
+  | B.length proof /= bbsProofLen (numMessages - length disclosedIdxs) = pure False
+  | otherwise =
+  withBS pk $ \pkPtr _ ->
+    withBS proof $ \proofPtr proofLen ->
+      withBS header $ \hdrPtr hdrLen ->
+        withBS ph $ \phPtr phLen ->
+          withIndexes disclosedIdxs $ \idxsPtr idxsLen ->
+            withMessages disclosedMsgs $ \msgsPtr lensPtr _ -> do
+              rc <- c_bbs_proof_verify ciphersuite pkPtr proofPtr proofLen hdrPtr hdrLen phPtr phLen idxsPtr idxsLen (fromIntegral numMessages) msgsPtr lensPtr
+              pure (rc == 0)

src/Simplex/Messaging/Crypto/Ratchet.hs

@@ -45,6 +45,7 @@ module Simplex.Messaging.Crypto.Ratchet
     AE2ERatchetParams (..),
     E2ERatchetParamsUri (..),
     E2ERatchetParams (..),
+    RcvE2EPrivRatchetParams,
     VersionE2E,
     VersionRangeE2E,
     pattern VersionE2E,
@@ -403,24 +404,30 @@ instance RatchetKEMStateI s => ToField (PrivRKEMParams s) where toField = toFiel
 
 instance (Typeable s, RatchetKEMStateI s) => FromField (PrivRKEMParams s) where fromField = blobFieldDecoder smpDecode
 
+type E2EPrivRatchetParams s a = (PrivateKey a, PrivateKey a, Maybe (PrivRKEMParams s))\
+
+type RcvE2EPrivRatchetParams a = E2EPrivRatchetParams 'RKSProposed a
+
+type AE2EPrivRatchetParams a = (PrivateKey a, PrivateKey a, Maybe APrivRKEMParams)
+
 data UseKEM (s :: RatchetKEMState) where
   ProposeKEM :: UseKEM 'RKSProposed
   AcceptKEM :: KEMPublicKey -> UseKEM 'RKSAccepted
 
 data AUseKEM = forall s. RatchetKEMStateI s => AUseKEM (SRatchetKEMState s) (UseKEM s)
 
-mkRcvE2ERatchetParams :: VersionE2E -> (PrivateKey a, PrivateKey a, Maybe RcvPrivRKEMParams) -> RcvE2ERatchetParams a
+mkRcvE2ERatchetParams :: VersionE2E -> RcvE2EPrivRatchetParams a -> RcvE2ERatchetParams a
 mkRcvE2ERatchetParams v (pk1, pk2, pKem) = E2ERatchetParams v (publicKey pk1) (publicKey pk2) (mkKem <$> pKem)
   where
     mkKem :: RcvPrivRKEMParams -> RcvRKEMParams
     mkKem (PrivateRKParamsProposed (k, _)) = RKParamsProposed k
 
-generateE2EParams :: forall s a. (AlgorithmI a, DhAlgorithm a) => TVar ChaChaDRG -> VersionE2E -> Maybe (UseKEM s) -> IO (PrivateKey a, PrivateKey a, Maybe (PrivRKEMParams s), E2ERatchetParams s a)
+generateE2EParams :: forall s a. (AlgorithmI a, DhAlgorithm a) => TVar ChaChaDRG -> VersionE2E -> Maybe (UseKEM s) -> IO (E2EPrivRatchetParams s a, E2ERatchetParams s a)
 generateE2EParams g v useKEM_ = do
   (k1, pk1) <- atomically $ generateKeyPair g
   (k2, pk2) <- atomically $ generateKeyPair g
   kems <- kemParams
-  pure (pk1, pk2, snd <$> kems, E2ERatchetParams v k1 k2 (fst <$> kems))
+  pure ((pk1, pk2, snd <$> kems), E2ERatchetParams v k1 k2 (fst <$> kems))
   where
     kemParams :: IO (Maybe (RKEMParams s, PrivRKEMParams s))
     kemParams = case useKEM_ of
@@ -436,7 +443,7 @@ generateE2EParams g v useKEM_ = do
       _ -> pure Nothing
 
 -- used by party initiating connection, Bob in double-ratchet spec
-generateRcvE2EParams :: (AlgorithmI a, DhAlgorithm a) => TVar ChaChaDRG -> VersionE2E -> PQSupport -> IO (PrivateKey a, PrivateKey a, Maybe (PrivRKEMParams 'RKSProposed), E2ERatchetParams 'RKSProposed a)
+generateRcvE2EParams :: (AlgorithmI a, DhAlgorithm a) => TVar ChaChaDRG -> VersionE2E -> PQSupport -> IO (RcvE2EPrivRatchetParams a, RcvE2ERatchetParams a)
 generateRcvE2EParams g v = generateE2EParams g v . proposeKEM_
   where
     proposeKEM_ :: PQSupport -> Maybe (UseKEM 'RKSProposed)
@@ -445,14 +452,14 @@ generateRcvE2EParams g v = generateE2EParams g v . proposeKEM_
       PQSupportOff -> Nothing
 
 -- used by party accepting connection, Alice in double-ratchet spec
-generateSndE2EParams :: forall a. (AlgorithmI a, DhAlgorithm a) => TVar ChaChaDRG -> VersionE2E -> Maybe AUseKEM -> IO (PrivateKey a, PrivateKey a, Maybe APrivRKEMParams, AE2ERatchetParams a)
+generateSndE2EParams :: forall a. (AlgorithmI a, DhAlgorithm a) => TVar ChaChaDRG -> VersionE2E -> Maybe AUseKEM -> IO (AE2EPrivRatchetParams a, AE2ERatchetParams a)
 generateSndE2EParams g v = \case
   Nothing -> do
-    (pk1, pk2, _, e2eParams) <- generateE2EParams g v Nothing
-    pure (pk1, pk2, Nothing, AE2ERatchetParams SRKSProposed e2eParams)
+    ((pk1, pk2, _), e2eParams) <- generateE2EParams g v Nothing
+    pure ((pk1, pk2, Nothing), AE2ERatchetParams SRKSProposed e2eParams)
   Just (AUseKEM s useKEM) -> do
-    (pk1, pk2, pKem, e2eParams) <- generateE2EParams g v (Just useKEM)
-    pure (pk1, pk2, APRKP s <$> pKem, AE2ERatchetParams s e2eParams)
+    ((pk1, pk2, pKem), e2eParams) <- generateE2EParams g v (Just useKEM)
+    pure ((pk1, pk2, APRKP s <$> pKem), AE2ERatchetParams s e2eParams)
 
 data RatchetInitParams = RatchetInitParams
   { assocData :: Str,
@@ -464,9 +471,9 @@ data RatchetInitParams = RatchetInitParams
   deriving (Show)
 
 -- this is used by the peer joining the connection
-pqX3dhSnd :: DhAlgorithm a => PrivateKey a -> PrivateKey a -> Maybe APrivRKEMParams -> E2ERatchetParams 'RKSProposed a -> Either CryptoError (RatchetInitParams, Maybe KEMKeyPair)
+pqX3dhSnd :: DhAlgorithm a => AE2EPrivRatchetParams a -> E2ERatchetParams 'RKSProposed a -> Either CryptoError (RatchetInitParams, Maybe KEMKeyPair)
 --        3. replied       2. received
-pqX3dhSnd spk1 spk2 spKem_ (E2ERatchetParams v rk1 rk2 rKem_) = do
+pqX3dhSnd (spk1, spk2, spKem_) (E2ERatchetParams v rk1 rk2 rKem_) = do
   (ks_, kem_) <- sndPq
   let initParams = pqX3dh (publicKey spk1, rk1) (dh' rk1 spk2) (dh' rk2 spk1) (dh' rk2 spk2) kem_
   pure (initParams, ks_)
@@ -480,9 +487,9 @@ pqX3dhSnd spk1 spk2 spKem_ (E2ERatchetParams v rk1 rk2 rKem_) = do
       _ -> Right (Nothing, Nothing)
 
 -- this is used by the peer that created new connection, after receiving the reply
-pqX3dhRcv :: forall s a. (RatchetKEMStateI s, DhAlgorithm a) => PrivateKey a -> PrivateKey a -> Maybe (PrivRKEMParams 'RKSProposed) -> E2ERatchetParams s a -> ExceptT CryptoError IO (RatchetInitParams, Maybe KEMKeyPair)
+pqX3dhRcv :: forall s a. (RatchetKEMStateI s, DhAlgorithm a) => RcvE2EPrivRatchetParams a -> E2ERatchetParams s a -> ExceptT CryptoError IO (RatchetInitParams, Maybe KEMKeyPair)
 --        1. sent          4. received in reply
-pqX3dhRcv rpk1 rpk2 rpKem_ (E2ERatchetParams v sk1 sk2 sKem_) = do
+pqX3dhRcv (rpk1, rpk2, rpKem_) (E2ERatchetParams v sk1 sk2 sKem_) = do
   kem_ <- rcvPq
   let initParams = pqX3dh (sk1, publicKey rpk1) (dh' sk2 rpk1) (dh' sk1 rpk2) (dh' sk2 rpk2) (snd <$> kem_)
   pure (initParams, fst <$> kem_)

src/Simplex/Messaging/Crypto/SNTRUP761/Bindings.hs

@@ -1,11 +1,14 @@
 {-# LANGUAGE CPP #-}
 {-# LANGUAGE TypeApplications #-}
+{-# LANGUAGE PatternSynonyms #-}
 
 module Simplex.Messaging.Crypto.SNTRUP761.Bindings
-  ( KEMPublicKey (..),
+  ( KEMPublicKey,
     KEMSecretKey,
-    KEMCiphertext (..),
-    KEMSharedKey (..),
+    KEMCiphertext,
+    KEMSharedKey,
+    pattern KEMPublicKey,
+    pattern KEMSharedKey,
     KEMKeyPair,
     sntrup761Keypair,
     sntrup761Enc,
@@ -25,8 +28,9 @@ import Simplex.Messaging.Crypto.SNTRUP761.Bindings.FFI
 import Simplex.Messaging.Crypto.SNTRUP761.Bindings.RNG (rngFuncPtr, withDRG)
 import Simplex.Messaging.Encoding
 import Simplex.Messaging.Encoding.String
+import Simplex.Messaging.Util ((<$?>))
 
-newtype KEMPublicKey = KEMPublicKey ByteString
+newtype KEMPublicKey = KEMPublicKey_ ByteString
   deriving (Eq, Show)
 
 newtype KEMSecretKey = KEMSecretKey ScrubbedBytes
@@ -35,18 +39,24 @@ newtype KEMSecretKey = KEMSecretKey ScrubbedBytes
 newtype KEMCiphertext = KEMCiphertext ByteString
   deriving (Eq, Show)
 
-newtype KEMSharedKey = KEMSharedKey ScrubbedBytes
+newtype KEMSharedKey = KEMSharedKey_ ScrubbedBytes
   deriving (Eq, Show)
 
-unsafeRevealKEMSharedKey :: KEMSharedKey -> String
-unsafeRevealKEMSharedKey (KEMSharedKey scrubbed) = show (BA.convert scrubbed :: ByteString)
-{-# DEPRECATED unsafeRevealKEMSharedKey "unsafeRevealKEMSharedKey left in code" #-}
+pattern KEMPublicKey :: ByteString -> KEMPublicKey
+pattern KEMPublicKey s <- KEMPublicKey_ s
+
+pattern KEMSharedKey :: ScrubbedBytes -> KEMSharedKey
+pattern KEMSharedKey s <- KEMSharedKey_ s
+
+{-# COMPLETE KEMPublicKey #-}
+
+{-# COMPLETE KEMSharedKey #-}
 
 type KEMKeyPair = (KEMPublicKey, KEMSecretKey)
 
 sntrup761Keypair :: TVar ChaChaDRG -> IO KEMKeyPair
 sntrup761Keypair drg =
-  bimap KEMPublicKey KEMSecretKey
+  bimap KEMPublicKey_ KEMSecretKey
     <$> BA.allocRet
       c_SNTRUP761_SECRETKEY_SIZE
       ( \skPtr ->
@@ -57,7 +67,7 @@ sntrup761Keypair drg =
 sntrup761Enc :: TVar ChaChaDRG -> KEMPublicKey -> IO (KEMCiphertext, KEMSharedKey)
 sntrup761Enc drg (KEMPublicKey pk) =
   BA.withByteArray pk $ \pkPtr ->
-    bimap KEMCiphertext KEMSharedKey
+    bimap KEMCiphertext KEMSharedKey_
       <$> BA.allocRet
         c_SNTRUP761_SIZE
         ( \kPtr ->
@@ -69,40 +79,47 @@ sntrup761Dec :: KEMCiphertext -> KEMSecretKey -> IO KEMSharedKey
 sntrup761Dec (KEMCiphertext c) (KEMSecretKey sk) =
   BA.withByteArray sk $ \skPtr ->
     BA.withByteArray c $ \cPtr ->
-      KEMSharedKey
+      KEMSharedKey_
         <$> BA.alloc c_SNTRUP761_SIZE (\kPtr -> c_sntrup761_dec kPtr cPtr skPtr)
 
+parseKey :: BA.ByteArrayAccess bs => (bs -> key) -> String -> Int -> bs -> Either String key
+parseKey kCon name expected s
+  | len == expected = Right $ kCon s
+  | otherwise = Left $ name <> " must be " <> show expected <> " bytes, got " <> show len
+  where
+    len = BA.length s    
+
 instance Encoding KEMSecretKey where
   smpEncode (KEMSecretKey c) = smpEncode . Large $ BA.convert c
-  smpP = KEMSecretKey . BA.convert . unLarge <$> smpP
+  smpP = parseKey KEMSecretKey "SNTRUP761 secret key" c_SNTRUP761_SECRETKEY_SIZE . BA.convert . unLarge <$?> smpP
 
 instance StrEncoding KEMSecretKey where
   strEncode (KEMSecretKey pk) = strEncode (BA.convert pk :: ByteString)
-  strP = KEMSecretKey . BA.convert <$> strP @ByteString
+  strP = parseKey KEMSecretKey "SNTRUP761 secret key" c_SNTRUP761_SECRETKEY_SIZE . BA.convert <$?> strP @ByteString
 
 instance Encoding KEMPublicKey where
   smpEncode (KEMPublicKey pk) = smpEncode . Large $ BA.convert pk
-  smpP = KEMPublicKey . BA.convert . unLarge <$> smpP
+  smpP = parseKey KEMPublicKey_ "SNTRUP761 public key" c_SNTRUP761_PUBLICKEY_SIZE . unLarge <$?> smpP
 
 instance StrEncoding KEMPublicKey where
   strEncode (KEMPublicKey pk) = strEncode (BA.convert pk :: ByteString)
-  strP = KEMPublicKey . BA.convert <$> strP @ByteString
+  strP = parseKey KEMPublicKey_ "SNTRUP761 public key" c_SNTRUP761_PUBLICKEY_SIZE <$?> strP @ByteString
 
 instance Encoding KEMCiphertext where
   smpEncode (KEMCiphertext c) = smpEncode . Large $ BA.convert c
-  smpP = KEMCiphertext . BA.convert . unLarge <$> smpP
+  smpP = parseKey KEMCiphertext "SNTRUP761 ciphertext" c_SNTRUP761_CIPHERTEXT_SIZE . unLarge <$?> smpP
 
 instance Encoding KEMSharedKey where
   smpEncode (KEMSharedKey c) = smpEncode (BA.convert c :: ByteString)
-  smpP = KEMSharedKey . BA.convert <$> smpP @ByteString
+  smpP = KEMSharedKey_ . BA.convert <$> smpP @ByteString
 
 instance StrEncoding KEMCiphertext where
   strEncode (KEMCiphertext pk) = strEncode (BA.convert pk :: ByteString)
-  strP = KEMCiphertext . BA.convert <$> strP @ByteString
+  strP = parseKey KEMCiphertext "SNTRUP761 ciphertext" c_SNTRUP761_CIPHERTEXT_SIZE <$?> strP @ByteString
 
 instance StrEncoding KEMSharedKey where
   strEncode (KEMSharedKey pk) = strEncode (BA.convert pk :: ByteString)
-  strP = KEMSharedKey . BA.convert <$> strP @ByteString
+  strP = KEMSharedKey_ . BA.convert <$> strP @ByteString
 
 instance ToJSON KEMSecretKey where
   toJSON = strToJSON
@@ -130,9 +147,9 @@ instance ToField KEMSharedKey where
 
 instance FromField KEMSharedKey where
 #if defined(dbPostgres)
-  fromField f dat = KEMSharedKey . BA.convert @ByteString <$> fromField f dat
+  fromField f dat = KEMSharedKey_ . BA.convert @ByteString <$> fromField f dat
 #else
-  fromField f = KEMSharedKey . BA.convert @ByteString <$> fromField f
+  fromField f = KEMSharedKey_ . BA.convert @ByteString <$> fromField f
 #endif
 
 instance ToJSON KEMSharedKey where

src/Simplex/Messaging/Encoding/String.hs

@@ -1,10 +1,14 @@
+{-# LANGUAGE DataKinds #-}
 {-# LANGUAGE FlexibleInstances #-}
+{-# LANGUAGE KindSignatures #-}
 {-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE ScopedTypeVariables #-}
 
 module Simplex.Messaging.Encoding.String
   ( TextEncoding (..),
     StrEncoding (..),
     Str (..),
+    StrJSON (..),
     strP_,
     _strP,
     strToJSON,
@@ -34,6 +38,7 @@ import Data.Int (Int64)
 import Data.IntSet (IntSet)
 import qualified Data.IntSet as IS
 import qualified Data.List.NonEmpty as L
+import Data.Proxy (Proxy (..))
 import Data.Set (Set)
 import qualified Data.Set as S
 import Data.Text (Text)
@@ -44,6 +49,7 @@ import Data.Time.Format.ISO8601
 import Data.Word (Word16, Word32)
 import qualified Data.X509 as X
 import qualified Data.X509.Validation as XV
+import GHC.TypeLits (KnownSymbol, Symbol, symbolVal)
 import Simplex.Messaging.Encoding
 import Simplex.Messaging.Parsers (parseAll)
 import Simplex.Messaging.Util (bshow, safeDecodeUtf8, (<$?>))
@@ -247,3 +253,21 @@ textToEncoding = JE.text . textEncode
 
 textParseJSON :: TextEncoding a => String -> J.Value -> JT.Parser a
 textParseJSON name = J.withText name $ maybe (fail name) pure . textDecode
+
+-- | Derives ToJSON/FromJSON from the wrapped type's own StrEncoding (a base64url
+-- string), so any validation that StrEncoding performs (e.g. length) also applies
+-- to JSON parsing. The @name@ symbol is the parse error label. The type parameter
+-- @a@ is essential: it makes parseJSON resolve at the wrapped type rather than at
+-- ByteString. Use via DerivingVia, e.g.:
+--
+-- > newtype Key = Key ByteString
+-- >   deriving (ToJSON, FromJSON) via (StrJSON "Key" Key)
+newtype StrJSON (name :: Symbol) a = StrJSON {unStrJSON :: a}
+  deriving (Eq, Show)
+
+instance StrEncoding a => ToJSON (StrJSON name a) where
+  toJSON (StrJSON a) = strToJSON a
+  toEncoding (StrJSON a) = strToJEncoding a
+
+instance forall name a. (KnownSymbol name, StrEncoding a) => FromJSON (StrJSON name a) where
+  parseJSON = fmap StrJSON . strParseJSON (symbolVal (Proxy :: Proxy name))

src/Simplex/Messaging/Names/Record.hs

@@ -0,0 +1,46 @@
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE StrictData #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+module Simplex.Messaging.Names.Record
+  ( NameRecord (..),
+  )
+where
+
+import qualified Data.Aeson as J
+import qualified Data.Aeson.TH as JQ
+import Data.Text (Text)
+import Simplex.Messaging.Parsers (defaultJSON, dropPrefix)
+
+-- | Resolved name record returned by the names role. JSON keys match the
+--   resolver REST output; both FromJSON (resolver -> server) and ToJSON
+--   (server diagnostics) are TH-derived from one Options value, so the Haskell
+--   type IS the schema. Text fields use the empty string as the "unset"
+--   sentinel; coin fields use JSON null. simplexContact / simplexChannel are
+--   arrays of links (primary first, empty when unset) so a name can advertise
+--   fallback SMP servers. owner / resolver are 0x-hex Ethereum addresses, kept
+--   verbatim as text (the resolver is the source of truth for their validity).
+--   The only size bound is the SMP transport block (enforced by the framing).
+data NameRecord = NameRecord
+  { nrName :: Text,
+    nrNickname :: Text,
+    nrWebsite :: Text,
+    nrLocation :: Text,
+    nrSimplexContact :: [Text],
+    nrSimplexChannel :: [Text],
+    nrEth :: Maybe Text,
+    nrBtc :: Maybe Text,
+    nrXmr :: Maybe Text,
+    nrDot :: Maybe Text,
+    nrOwner :: Text,
+    nrResolver :: Text -- resolver address (0x hex) that produced the record
+  }
+  deriving (Eq, Show)
+
+-- omitNothingFields False so absent coin fields surface as JSON null (matches
+-- the resolver output for unset coins).
+$( JQ.deriveJSON
+    defaultJSON {J.omitNothingFields = False, J.fieldLabelModifier = dropPrefix "nr"}
+    ''NameRecord
+ )

src/Simplex/Messaging/Notifications/Server.hs

@@ -34,6 +34,7 @@ import Data.ByteString.Char8 (ByteString)
 import qualified Data.ByteString.Char8 as B
 import Data.Either (partitionEithers)
 import Data.Functor (($>))
+import Data.Hashable (hash)
 import Data.IORef
 import Data.Int (Int64)
 import qualified Data.IntSet as IS
@@ -53,6 +54,7 @@ import Data.Time.Format.ISO8601 (iso8601Show)
 import GHC.IORef (atomicSwapIORef)
 import GHC.Stats (getRTSStats)
 import Network.Socket (ServiceName, Socket, socketToHandle)
+import Numeric.Natural (Natural)
 import Simplex.Messaging.Client (ProtocolClientError (..), SMPClientError, ServerTransmission (..))
 import Simplex.Messaging.Client.Agent
 import qualified Simplex.Messaging.Crypto as C
@@ -85,7 +87,7 @@ import System.Exit (exitFailure, exitSuccess)
 import System.IO (BufferMode (..), hClose, hPrint, hPutStrLn, hSetBuffering, hSetNewlineMode, universalNewlineMode)
 import System.Mem.Weak (deRefWeak)
 import System.Timeout (timeout)
-import UnliftIO (IOMode (..), UnliftIO, askUnliftIO, race_, unliftIO, withFile)
+import UnliftIO (IOMode (..), UnliftIO (..), askUnliftIO, race_, unliftIO, withFile)
 import UnliftIO.Concurrent (forkIO, killThread, mkWeakThreadId)
 import UnliftIO.Directory (doesFileExist, renameFile)
 import UnliftIO.Exception
@@ -116,7 +118,6 @@ ntfServer cfg@NtfServerConfig {transports, transportConfig = tCfg, startOptions}
   void $ forkIO $ resubscribe s
   raceAny_
     ( ntfSubscriber s
-        : ntfPush ps
         : periodicNtfsThread ps
         : map runServer transports
           <> serverStatsThread_ cfg
@@ -147,12 +148,17 @@ ntfServer cfg@NtfServerConfig {transports, transportConfig = tCfg, startOptions}
       saveServer
       NtfSubscriber {smpSubscribers, smpAgent} <- asks subscriber
       liftIO $ readTVarIO smpSubscribers >>= mapM_ stopSubscriber
+      NtfPushServer {pushWorkers} <- asks pushServer
+      liftIO $ readTVarIO pushWorkers >>= mapM_ stopPushWorker
       liftIO $ closeSMPClientAgent smpAgent
       logNote "Server stopped"
       where
         stopSubscriber v =
           atomically (tryReadTMVar $ sessionVar v)
             >>= mapM (deRefWeak . subThreadId >=> mapM_ killThread)
+        stopPushWorker v =
+          atomically (tryReadTMVar $ sessionVar v)
+            >>= mapM (deRefWeak . workerThreadId >=> mapM_ killThread)
 
     saveServer :: M ()
     saveServer = asks store >>= liftIO . closeNtfDbStore >> saveServerStats
@@ -257,7 +263,7 @@ ntfServer cfg@NtfServerConfig {transports, transportConfig = tCfg, startOptions}
       let threadsCount = 0
 #endif
       let NtfSubscriber {smpSubscribers, smpAgent = a} = subscriber
-          NtfPushServer {pushQ} = pushServer
+          NtfPushServer {pushWorkers} = pushServer
           SMPClientAgent {smpClients, smpSessions, smpSubWorkers} = a
       srvSubscribers <- getSMPWorkerMetrics a smpSubscribers
       srvClients <- getSMPWorkerMetrics a smpClients
@@ -267,7 +273,7 @@ ntfServer cfg@NtfServerConfig {transports, transportConfig = tCfg, startOptions}
       ntfPendingServiceSubs <- getSMPServiceSubMetrics a pendingServiceSubs smpQueueCount
       ntfPendingQueueSubs <- getSMPSubMetrics a pendingQueueSubs
       smpSessionCount <- M.size <$> readTVarIO smpSessions
-      apnsPushQLength <- atomically $ lengthTBQueue pushQ
+      apnsPushQLength <- pushWorkersQLength pushWorkers
       pure
         NtfRealTimeMetrics
           { threadsCount,
@@ -521,40 +527,41 @@ subscribeNtfs NtfSubscriber {smpSubscribers, subscriberSeq, smpAgent = ca} st sm
       subscribeQueuesNtfs ca smpServer' [sub]
 
 ntfSubscriber :: NtfSubscriber -> M ()
-ntfSubscriber NtfSubscriber {smpAgent = ca@SMPClientAgent {msgQ, agentQ}} =
+ntfSubscriber NtfSubscriber {smpAgent = ca@SMPClientAgent {msgQ = msgQ_, agentQ}} =
   race_ receiveSMP receiveAgent
   where
-    receiveSMP = do
+    receiveSMP = forM_ msgQ_ $ \msgQ -> do
       st <- asks store
-      NtfPushServer {pushQ} <- asks pushServer
+      ps <- asks pushServer
       stats <- asks serverStats
-      liftIO $ forever $ do
+      forever $ do
         ((_, srv@(SMPServer (h :| _) _ _), _), THandleParams {sessionId}, ts) <- atomically $ readTBQueue msgQ
-        forM ts $ \(ntfId, t) -> case t of
+        forM_ ts $ \(ntfId, t) -> case t of
           STUnexpectedError e -> logError $ "SMP client unexpected error: " <> tshow e -- uncorrelated response, should not happen
           STResponse {} -> pure () -- it was already reported as timeout error
           STEvent msgOrErr -> do
             let smpQueue = SMPQueueNtf srv ntfId
             case msgOrErr of
               Right (SMP.NMSG nmsgNonce encNMsgMeta) -> do
-                ntfTs <- getSystemTime
-                updatePeriodStats (activeSubs stats) ntfId
+                ntfTs <- liftIO getSystemTime
+                liftIO $ updatePeriodStats (activeSubs stats) ntfId
                 let newNtf = PNMessageData {smpQueue, ntfTs, nmsgNonce, encNMsgMeta}
-                    srvHost_ = if isOwnServer ca srv then Just (safeDecodeUtf8 $ strEncode h) else Nothing
-                addTokenLastNtf st newNtf >>= \case
+                    srvHost = safeDecodeUtf8 $ strEncode h
+                    isOwn = isOwnServer ca srv
+                liftIO (addTokenLastNtf st newNtf) >>= \case
                   Right (tkn, lastNtfs) -> do
-                    atomically $ writeTBQueue pushQ (srvHost_, tkn, PNMessage lastNtfs)
-                    incNtfStat_ stats ntfReceived
-                    mapM_ (`incServerStat` ntfReceivedOwn stats) srvHost_
-                  Left AUTH -> do
+                    pushNotification ps (Just srvHost) isOwn tkn $ PNMessage lastNtfs
+                    liftIO $ incNtfStat_ stats ntfReceived
+                    when isOwn $ liftIO $ incServerStat srvHost (ntfReceivedOwn stats)
+                  Left AUTH -> liftIO $ do
                     incNtfStat_ stats ntfReceivedAuth
-                    mapM_ (`incServerStat` ntfReceivedAuthOwn stats) srvHost_
+                    when isOwn $ incServerStat srvHost (ntfReceivedAuthOwn stats)
                   Left _ -> pure ()
               Right SMP.END ->
                 whenM (atomically $ activeClientSession' ca sessionId srv) $
-                  void $ updateSrvSubStatus st smpQueue NSEnd
+                  void $ liftIO $ updateSrvSubStatus st smpQueue NSEnd
               Right SMP.DELD ->
-                void $ updateSrvSubStatus st smpQueue NSDeleted
+                void $ liftIO $ updateSrvSubStatus st smpQueue NSDeleted
               Right (SMP.ERR e) -> logError $ "SMP server error: " <> tshow e
               Right _ -> logError "SMP server unexpected response"
               Left e -> logError $ "SMP client error: " <> tshow e
@@ -633,9 +640,41 @@ logSubStatus srv event n updated =
 showServer' :: SMPServer -> Text
 showServer' = decodeLatin1 . strEncode . host
 
-ntfPush :: NtfPushServer -> M ()
-ntfPush s@NtfPushServer {pushQ} = forever $ do
-  (srvHost_, tkn@NtfTknRec {ntfTknId, token = t@(DeviceToken pp _), tknStatus}, ntf) <- atomically (readTBQueue pushQ)
+pushNotification :: NtfPushServer -> Maybe T.Text -> OwnServer -> NtfTknRec -> PushNotification -> M ()
+pushNotification s srvHost_ isOwn tkn@NtfTknRec {ntfTknId, token = token@(DeviceToken pp _)} ntf =
+  ifM
+    (pushProviderAllowed token)
+    (getOrCreatePushWorker s (srvHost_, pp, hash (unEntityId ntfTknId) `mod` pushWorkersPerServer) isOwn >>= atomically . (`writeTBQueue` (tkn, ntf)))
+    (logWarn "skipping disabled APNS test push provider")
+  where
+    pushWorkersPerServer = 8
+
+pushProviderAllowed :: DeviceToken -> M Bool
+pushProviderAllowed (DeviceToken PPApnsTest _) = asks (allowTestPushProvider . config)
+pushProviderAllowed _ = pure True
+
+guardPushProvider :: DeviceToken -> M NtfResponse -> M NtfResponse
+guardPushProvider token action =
+  ifM
+    (pushProviderAllowed token)
+    action
+    (pure $ NRErr $ CMD SMP.PROHIBITED)
+
+getOrCreatePushWorker :: NtfPushServer -> (Maybe T.Text, PushProvider, Int) -> OwnServer -> M (TBQueue (NtfTknRec, PushNotification))
+getOrCreatePushWorker s@NtfPushServer {pushWorkers, pushWorkerSeq, pushQSize} key@(srvHost_, _, _) isOwn = do
+  ts <- liftIO getCurrentTime
+  withGetSessVar' pushWorkerSeq key pushWorkers ts createWorker existingWorker
+  where
+    createWorker v = do
+      q <- liftIO $ newTBQueueIO pushQSize
+      tId <- mkWeakThreadId =<< forkIO (runPushWorker s srvHost_ isOwn q)
+      atomically $ putTMVar (sessionVar v) PushWorker {workerQ = q, workerThreadId = tId}
+      pure q
+    existingWorker v = workerQ <$> atomically (readTMVar $ sessionVar v)
+
+runPushWorker :: NtfPushServer -> Maybe T.Text -> OwnServer -> TBQueue (NtfTknRec, PushNotification) -> M ()
+runPushWorker s srvHost_ isOwn q = forever $ do
+  (tkn@NtfTknRec {ntfTknId, token = t@(DeviceToken pp _), tknStatus}, ntf) <- atomically (readTBQueue q)
   liftIO $ logDebug $ "sending push notification to " <> T.pack (show pp)
   st <- asks store
   case ntf of
@@ -645,7 +684,7 @@ ntfPush s@NtfPushServer {pushQ} = forever $ do
           void $ liftIO $ setTknStatusConfirmed st tkn
           incNtfStatT t ntfVrfDelivered
         Left _ -> incNtfStatT t ntfVrfFailed
-    PNCheckMessages -> do
+    PNCheckMessages ->
       liftIO (deliverNotification st pp tkn ntf) >>= \case
         Right _ -> do
           void $ liftIO $ updateTokenCronSentAt st ntfTknId . systemSeconds =<< getSystemTime
@@ -657,24 +696,23 @@ ntfPush s@NtfPushServer {pushQ} = forever $ do
       liftIO (deliverNotification st pp tkn ntf) >>= \case
         Left _ -> do
           incNtfStatT t ntfFailed
-          liftIO $ mapM_ (`incServerStat` ntfFailedOwn stats) srvHost_
+          when isOwn $ liftIO $ mapM_ (`incServerStat` ntfFailedOwn stats) srvHost_
         Right () -> do
           incNtfStatT t ntfDelivered
-          liftIO $ mapM_ (`incServerStat` ntfDeliveredOwn stats) srvHost_
-
+          when isOwn $ liftIO $ mapM_ (`incServerStat` ntfDeliveredOwn stats) srvHost_
   where
     checkActiveTkn :: NtfTknStatus -> M () -> M ()
     checkActiveTkn status action
       | status == NTActive = action
       | otherwise = liftIO $ logError "bad notification token status"
     deliverNotification :: NtfPostgresStore -> PushProvider -> NtfTknRec -> PushNotification -> IO (Either PushProviderError ())
-    deliverNotification st pp tkn@NtfTknRec {ntfTknId} ntf = do
-      deliver <- getPushClient s pp
-      runExceptT (deliver tkn ntf) >>= \case
+    deliverNotification st pp tkn@NtfTknRec {ntfTknId} ntf' = do
+      (deliver, clientVar) <- getPushClient s pp
+      runExceptT (deliver tkn ntf') >>= \case
         Right _ -> pure $ Right ()
         Left e -> case e of
-          PPConnection _ -> retryDeliver
-          PPRetryLater -> retryDeliver
+          PPConnection ce -> retryDeliver clientVar $ "connection " <> tshow ce
+          PPRetryLater r -> retryDeliver clientVar r
           PPCryptoError _ -> err e
           PPResponseError {} -> err e
           PPTokenInvalid r -> do
@@ -682,10 +720,12 @@ ntfPush s@NtfPushServer {pushQ} = forever $ do
             err e
           PPPermanentError -> err e
       where
-        retryDeliver :: IO (Either PushProviderError ())
-        retryDeliver = do
-          deliver <- newPushClient s pp
-          runExceptT (deliver tkn ntf) >>= \case
+        retryDeliver :: PushClientVar -> Text -> IO (Either PushProviderError ())
+        retryDeliver oldVar reason = do
+          logWarn $ "retrying push (" <> tshow pp <> ", " <> tshow ntfTknId <> "): " <> reason
+          atomically $ removeSessVar oldVar pp (pushClients s)
+          (deliver, _) <- getPushClient s pp
+          runExceptT (deliver tkn ntf') >>= \case
             Right _ -> pure $ Right ()
             Left e -> case e of
               PPTokenInvalid r -> do
@@ -694,15 +734,26 @@ ntfPush s@NtfPushServer {pushQ} = forever $ do
               _ -> err e
         err e = logError ("Push provider error (" <> tshow pp <> ", " <> tshow ntfTknId <> "): " <> tshow e) $> Left e
 
+pushWorkersQLength :: TMap (Maybe T.Text, PushProvider, Int) PushWorkerVar -> IO Natural
+pushWorkersQLength workers = do
+  ws <- readTVarIO workers
+  foldM addQLength 0 ws
+  where
+    addQLength acc v =
+      atomically (tryReadTMVar $ sessionVar v) >>= \case
+        Just PushWorker {workerQ} -> (acc +) <$> atomically (lengthTBQueue workerQ)
+        Nothing -> pure acc
+
 periodicNtfsThread :: NtfPushServer -> M ()
-periodicNtfsThread NtfPushServer {pushQ} = do
+periodicNtfsThread s = do
   st <- asks store
   ntfsInterval <- asks $ periodicNtfsInterval . config
   let interval = 1000000 * ntfsInterval
+  UnliftIO unlift <- askUnliftIO
   liftIO $ forever $ do
     threadDelay interval
     now <- systemSeconds <$> getSystemTime
-    cnt <- withPeriodicNtfTokens st now $ \tkn -> atomically $ writeTBQueue pushQ (Nothing, tkn, PNCheckMessages)
+    cnt <- withPeriodicNtfTokens st now $ \tkn -> unlift $ pushNotification s Nothing False tkn PNCheckMessages
     logNote $ "Scheduled periodic notifications: " <> tshow cnt
 
 runNtfClientTransport :: Transport c => THandleNTF c 'TServer -> M ()
@@ -792,7 +843,7 @@ verifyNtfTransmission st thAuth (tAuth, authorized, (corrId, entId, cmd)) = case
       e -> VRFailed e
 
 client :: NtfServerClient -> NtfSubscriber -> NtfPushServer -> M ()
-client NtfServerClient {rcvQ, sndQ} ns@NtfSubscriber {smpAgent = ca} NtfPushServer {pushQ} =
+client NtfServerClient {rcvQ, sndQ} ns@NtfSubscriber {smpAgent = ca} ps =
   forever $
     atomically (readTBQueue rcvQ)
       >>= mapM processCommand
@@ -800,7 +851,7 @@ client NtfServerClient {rcvQ, sndQ} ns@NtfSubscriber {smpAgent = ca} NtfPushServ
   where
     processCommand :: NtfRequest -> M (Transmission NtfResponse)
     processCommand = \case
-      NtfReqNew corrId (ANE SToken newTkn@(NewNtfTkn token _ dhPubKey)) -> (corrId,NoEntity,) <$> do
+      NtfReqNew corrId (ANE SToken newTkn@(NewNtfTkn token _ dhPubKey)) -> (corrId,NoEntity,) <$> guardPushProvider token (do
         logDebug "TNEW - new token"
         (srvDhPubKey, srvDhPrivKey) <- atomically . C.generateKeyPair =<< asks random
         let dhSecret = C.dh' dhPubKey srvDhPrivKey
@@ -809,13 +860,13 @@ client NtfServerClient {rcvQ, sndQ} ns@NtfSubscriber {smpAgent = ca} NtfPushServ
         ts <- liftIO $ getSystemDate
         let tkn = mkNtfTknRec tknId newTkn srvDhPrivKey dhSecret regCode ts
         withNtfStore (`addNtfToken` tkn) $ \_ -> do
-          atomically $ writeTBQueue pushQ (Nothing, tkn, PNVerification regCode)
+          pushNotification ps Nothing False tkn $ PNVerification regCode
           incNtfStatT token ntfVrfQueued
           incNtfStatT token tknCreated
-          pure $ NRTknId tknId srvDhPubKey
+          pure $ NRTknId tknId srvDhPubKey)
       NtfReqCmd SToken (NtfTkn tkn@NtfTknRec {token, ntfTknId, tknStatus, tknRegCode, tknDhSecret, tknDhPrivKey}) (corrId, tknId, cmd) -> do
         (corrId,tknId,) <$> case cmd of
-          TNEW (NewNtfTkn _ _ dhPubKey) -> do
+          TNEW (NewNtfTkn _ _ dhPubKey) -> guardPushProvider token $ do
             logDebug "TNEW - registered token"
             let dhSecret = C.dh' dhPubKey tknDhPrivKey
             -- it is required that DH secret is the same, to avoid failed verifications if notification is delaying
@@ -825,7 +876,7 @@ client NtfServerClient {rcvQ, sndQ} ns@NtfSubscriber {smpAgent = ca} NtfPushServ
               | otherwise -> withNtfStore (\st -> updateTknStatus st tkn NTRegistered) $ \_ -> sendVerification
             where
               sendVerification = do
-                atomically $ writeTBQueue pushQ (Nothing, tkn, PNVerification tknRegCode)
+                pushNotification ps Nothing False tkn $ PNVerification tknRegCode
                 incNtfStatT token ntfVrfQueued
                 pure $ NRTknId ntfTknId $ C.publicKey tknDhPrivKey
           TVFY code -- this allows repeated verification for cases when client connection dropped before server response
@@ -838,12 +889,12 @@ client NtfServerClient {rcvQ, sndQ} ns@NtfSubscriber {smpAgent = ca} NtfPushServ
           TCHK -> do
             logDebug "TCHK"
             pure $ NRTkn tknStatus
-          TRPL token' -> do
+          TRPL token' -> guardPushProvider token' $ do
             logDebug "TRPL - replace token"
             regCode <- getRegCode
             let tkn' = tkn {token = token', tknStatus = NTRegistered, tknRegCode = regCode}
             withNtfStore (`replaceNtfToken` tkn') $ \_ -> do
-              atomically $ writeTBQueue pushQ (Nothing, tkn', PNVerification regCode)
+              pushNotification ps Nothing False tkn' $ PNVerification regCode
               incNtfStatT token ntfVrfQueued
               incNtfStatT token tknReplaced
               pure NROk

src/Simplex/Messaging/Notifications/Server/Env.hs

@@ -14,22 +14,29 @@ module Simplex.Messaging.Notifications.Server.Env
     SMPSubscriberVar,
     SMPSubscriber (..),
     NtfPushServer (..),
+    PushClientVar,
+    PushWorker (..),
+    PushWorkerVar,
     NtfRequest (..),
     NtfServerClient (..),
     defaultInactiveClientExpiration,
     newNtfServerEnv,
     newNtfSubscriber,
     newNtfPushServer,
-    newPushClient,
     getPushClient,
     newNtfServerClient,
   ) where
 
 import Control.Concurrent (ThreadId)
+import qualified Control.Exception as E
+import Control.Logger.Simple
+import Control.Monad
 import Control.Monad.Except
 import Control.Monad.Trans.Except
 import Crypto.Random
+import Data.Functor (($>))
 import Data.Int (Int64)
+import Simplex.Messaging.Agent.RetryInterval
 import Data.List.NonEmpty (NonEmpty)
 import qualified Data.Text as T
 import Data.Time.Clock (getCurrentTime)
@@ -57,7 +64,9 @@ import qualified Simplex.Messaging.TMap as TM
 import Simplex.Messaging.Transport (ASrvTransport, SMPServiceRole (..), ServiceCredentials (..), THandleParams, TransportPeer (..))
 import Simplex.Messaging.Transport.Credentials (genCredentials, tlsCredentials)
 import Simplex.Messaging.Transport.Server (AddHTTP, ServerCredentials, TransportServerConfig, loadFingerprint, loadServerCredential)
-import Simplex.Messaging.Util (liftEitherWith)
+import Simplex.Messaging.Util (liftEitherWith, tshow)
+import Simplex.Messaging.Util ()
+import System.Exit (exitFailure)
 import System.Mem.Weak (Weak)
 import UnliftIO.STM
 
@@ -72,6 +81,7 @@ data NtfServerConfig = NtfServerConfig
     pushQSize :: Natural,
     smpAgentCfg :: SMPClientAgentConfig,
     apnsConfig :: APNSPushClientConfig,
+    allowTestPushProvider :: Bool,
     subsBatchSize :: Int,
     inactiveClientExpiration :: Maybe ExpirationConfig,
     dbStoreConfig :: PostgresStoreCfg,
@@ -164,28 +174,62 @@ data SMPSubscriber = SMPSubscriber
   }
 
 data NtfPushServer = NtfPushServer
-  { pushQ :: TBQueue (Maybe T.Text, NtfTknRec, PushNotification), -- Maybe Text is a hostname of "own" server
-    pushClients :: TMap PushProvider PushProviderClient,
+  { pushWorkers :: TMap (Maybe T.Text, PushProvider, Int) PushWorkerVar, -- Int is the worker shard
+    pushWorkerSeq :: TVar Int,
+    pushQSize :: Natural,
+    pushClients :: TMap PushProvider PushClientVar,
+    pushClientSeq :: TVar Int,
     apnsConfig :: APNSPushClientConfig
   }
 
-newNtfPushServer :: Natural -> APNSPushClientConfig -> IO NtfPushServer
-newNtfPushServer qSize apnsConfig = do
-  pushQ <- newTBQueueIO qSize
-  pushClients <- TM.emptyIO
-  pure NtfPushServer {pushQ, pushClients, apnsConfig}
+data PushWorker = PushWorker
+  { workerQ :: TBQueue (NtfTknRec, PushNotification),
+    workerThreadId :: Weak ThreadId
+  }
 
-newPushClient :: NtfPushServer -> PushProvider -> IO PushProviderClient
-newPushClient NtfPushServer {apnsConfig, pushClients} pp = do
-  c <- case apnsProviderHost pp of
+type PushWorkerVar = SessionVar PushWorker
+
+-- The Either communicates client-creation failure from the winner to the waiters.
+type PushClientVar = SessionVar (Either E.SomeException PushProviderClient)
+
+newNtfPushServer :: Natural -> APNSPushClientConfig -> IO NtfPushServer
+newNtfPushServer pushQSize apnsConfig = do
+  pushWorkers <- TM.emptyIO
+  pushWorkerSeq <- newTVarIO 0
+  pushClients <- TM.emptyIO
+  pushClientSeq <- newTVarIO 0
+  pure NtfPushServer {pushWorkers, pushWorkerSeq, pushQSize, pushClients, pushClientSeq, apnsConfig}
+
+-- | Single-flight access to the per-provider push client with bounded retry.
+-- The returned PushClientVar is the handle retryDeliver passes to removeSessVar to evict
+-- this specific instance before re-fetching.
+getPushClient :: NtfPushServer -> PushProvider -> IO (PushProviderClient, PushClientVar)
+getPushClient s@NtfPushServer {apnsConfig = APNSPushClientConfig {reconnectInterval}} pp =
+  withRetryIntervalCount reconnectInterval $ \n _delay loop -> do
+    ts <- getCurrentTime
+    E.try (atomically (getSessVar (pushClientSeq s) pp (pushClients s) ts) >>= either (newPushClient s pp) waitForPushClient) >>= \case
+      Right result -> pure result
+      Left e
+        | n < 2 -> do
+            logError $ "getPushClient error (" <> tshow pp <> "): " <> tshow (e :: E.SomeException)
+            loop
+        | otherwise -> E.throwIO e
+
+newPushClient :: NtfPushServer -> PushProvider -> PushClientVar -> IO (PushProviderClient, PushClientVar)
+newPushClient NtfPushServer {pushClients, apnsConfig} pp v = do
+  r <- E.try $ case apnsProviderHost pp of
     Nothing -> pure $ \_ _ -> pure ()
     Just host -> apnsPushProviderClient <$> createAPNSPushClient host apnsConfig
-  atomically $ TM.insert pp c pushClients
-  pure c
+  atomically $ do
+    putTMVar (sessionVar v) r
+    case r of
+      Left _ -> removeSessVar v pp pushClients
+      Right _ -> pure ()
+  either E.throwIO (\c -> pure (c, v)) r
 
-getPushClient :: NtfPushServer -> PushProvider -> IO PushProviderClient
-getPushClient s@NtfPushServer {pushClients} pp =
-  TM.lookupIO pp pushClients >>= maybe (newPushClient s pp) pure
+waitForPushClient :: PushClientVar -> IO (PushProviderClient, PushClientVar)
+waitForPushClient v =
+  atomically (readTMVar $ sessionVar v) >>= either E.throwIO (\c -> pure (c, v))
 
 data NtfRequest
   = NtfReqNew CorrId ANewNtfEntity

src/Simplex/Messaging/Notifications/Server/Main.hs

@@ -97,50 +97,50 @@ ntfServerCLI cfgPath logPath =
           \# This option enables saving memory to append only log,\n\
           \# and restoring it when the server is started.\n\
           \# Log is compacted on start (deleted objects are removed).\n"
-            <> ("enable: " <> onOff enableStoreLog <> "\n\n")
+            <> ("enable = " <> onOff enableStoreLog <> "\n\n")
             <> "# Database connection settings for PostgreSQL database.\n"
             <> iniDbOpts dbOptions defaultNtfDBOpts
-            <> "Time to retain deleted entities in the database, days.\n"
-            <> ("# db_deleted_ttl: " <> tshow defaultDeletedTTL <> "\n\n")
-            <> "log_stats: off\n\n\
+            <> "# Time to retain deleted entities in the database, days.\n"
+            <> ("# db_deleted_ttl = " <> tshow defaultDeletedTTL <> "\n\n")
+            <> "log_stats = off\n\n\
                \# Log interval for real-time Prometheus metrics\n\
-               \# prometheus_interval: 60\n\
+               \# prometheus_interval = 60\n\
                \\n\
                \[AUTH]\n\
-               \# control_port_admin_password:\n\
-               \# control_port_user_password:\n\
+               \# control_port_admin_password =\n\
+               \# control_port_user_password =\n\
                \\n\
                \[TRANSPORT]\n\
                \# Host is only used to print server address on start.\n\
                \# You can specify multiple server ports.\n"
-            <> ("host: " <> T.pack host <> "\n")
-            <> ("port: " <> T.pack defaultServerPort <> "\n")
-            <> "log_tls_errors: off\n\n\
-               \# Use `websockets: 443` to run websockets server in addition to plain TLS.\n\
-               \websockets: off\n\n\
-               \# control_port: 5227\n\
+            <> ("host = " <> T.pack host <> "\n")
+            <> ("port = " <> T.pack defaultServerPort <> "\n")
+            <> "log_tls_errors = off\n\n\
+               \# Use `websockets = 443` to run websockets server in addition to plain TLS.\n\
+               \websockets = off\n\n\
+               \# control_port = 5227\n\
                \\n\
                \[SUBSCRIBER]\n\
                \# Network configuration for notification server client.\n\
                \# `host_mode` can be 'public' (default) or 'onion'.\n\
                \# It defines prefferred hostname for destination servers with multiple hostnames.\n\
-               \# host_mode: public\n\
-               \# required_host_mode: off\n\n\
+               \# host_mode = public\n\
+               \# required_host_mode = off\n\n\
                \# SOCKS proxy port for subscribing to SMP servers.\n\
                \# You may need a separate instance of SOCKS proxy for incoming single-hop requests.\n\
-               \# socks_proxy: localhost:9050\n\n\
+               \# socks_proxy = localhost:9050\n\n\
                \# `socks_mode` can be 'onion' for SOCKS proxy to be used for .onion destination hosts only (default)\n\
                \# or 'always' to be used for all destination hosts (can be used if it is an .onion server).\n\
-               \# socks_mode: onion\n\n\
+               \# socks_mode = onion\n\n\
                \# The domain suffixes of the relays you operate (space-separated) to count as separate proxy statistics.\n\
-               \# own_server_domains: \n\n\
+               \# own_server_domains = \n\n\
                \# User service subscriptions with server certificate\n\n\
-               \# use_service_credentials: off\n\n\
+               \# use_service_credentials = off\n\n\
                \[INACTIVE_CLIENTS]\n\
                \# TTL and interval to check inactive clients\n\
-               \disconnect: off\n"
-            <> ("# ttl: " <> tshow (ttl defaultInactiveClientExpiration) <> "\n")
-            <> ("# check_interval: " <> tshow (checkInterval defaultInactiveClientExpiration) <> "\n")
+               \disconnect = off\n"
+            <> ("# ttl = " <> tshow (ttl defaultInactiveClientExpiration) <> "\n")
+            <> ("# check_interval = " <> tshow (checkInterval defaultInactiveClientExpiration) <> "\n")
     enableStoreLog' = settingIsOn "STORE_LOG" "enable"
     runServer startOptions ini = do
       setLogLevel $ logLevel startOptions
@@ -193,6 +193,7 @@ ntfServerCLI cfgPath logPath =
                     persistErrorInterval = 0 -- seconds
                   },
               apnsConfig = defaultAPNSPushClientConfig,
+              allowTestPushProvider = False,
               subsBatchSize = 900,
               inactiveClientExpiration =
                 settingIsOn "INACTIVE_CLIENTS" "disconnect" ini

src/Simplex/Messaging/Notifications/Server/Push/APNS.hs

@@ -23,7 +23,7 @@ module Simplex.Messaging.Notifications.Server.Push.APNS
     apnsPushProviderClient,
   ) where
 
-import Control.Exception (Exception)
+import Control.Exception (Exception, throwIO)
 import Control.Logger.Simple
 import Control.Monad
 import Control.Monad.Except
@@ -66,6 +66,7 @@ import qualified Network.HTTP2.Client as H
 import Network.Socket (HostName, ServiceName)
 import qualified Simplex.Messaging.Crypto as C
 import Simplex.Messaging.Notifications.Protocol
+import Simplex.Messaging.Agent.RetryInterval (RetryInterval (..))
 import Simplex.Messaging.Notifications.Server.Push.APNS.Internal
 import Simplex.Messaging.Notifications.Server.Store.Types (NtfTknRec (..))
 import Simplex.Messaging.Parsers (defaultJSON)
@@ -192,7 +193,8 @@ data APNSPushClientConfig = APNSPushClientConfig
     appTeamId :: Text,
     apnsPort :: ServiceName,
     http2cfg :: HTTP2ClientConfig,
-    caStoreFile :: FilePath
+    caStoreFile :: FilePath,
+    reconnectInterval :: RetryInterval
   }
 
 apnsProviderHost :: PushProvider -> Maybe HostName
@@ -214,7 +216,8 @@ defaultAPNSPushClientConfig =
       appTeamId = "5NN7GUYB6T",
       apnsPort = "443",
       http2cfg = defaultHTTP2ClientConfig {bufferSize = 16384},
-      caStoreFile = "/etc/ssl/cert.pem"
+      caStoreFile = "/etc/ssl/cert.pem",
+      reconnectInterval = RetryInterval {initialInterval = 2000000, increaseAfter = 0, maxInterval = 10000000}
     }
 
 data APNSPushClient = APNSPushClient
@@ -230,7 +233,7 @@ data APNSPushClient = APNSPushClient
 createAPNSPushClient :: HostName -> APNSPushClientConfig -> IO APNSPushClient
 createAPNSPushClient apnsHost apnsCfg@APNSPushClientConfig {authKeyFileEnv, authKeyAlg, authKeyIdEnv, appTeamId} = do
   https2Client <- newTVarIO Nothing
-  void $ connectHTTPS2 apnsHost apnsCfg https2Client
+  connectHTTPS2 apnsHost apnsCfg https2Client >>= either (throwIO . userError . show) (\_ -> pure ())
   privateKey <- readECPrivateKey =<< getEnv authKeyFileEnv
   authKeyId <- T.pack <$> getEnv authKeyIdEnv
   let jwtHeader = JWTHeader {alg = authKeyAlg, kid = authKeyId}
@@ -326,7 +329,7 @@ data PushProviderError
   | PPCryptoError C.CryptoError
   | PPResponseError (Maybe Status) Text
   | PPTokenInvalid NTInvalidReason
-  | PPRetryLater
+  | PPRetryLater Text
   | PPPermanentError
   deriving (Show, Exception)
 
@@ -343,8 +346,7 @@ apnsPushProviderClient c@APNSPushClient {nonceDrg, apnsCfg} tkn@NtfTknRec {token
   nonce <- atomically $ C.randomCbNonce nonceDrg
   apnsNtf <- liftEither $ first PPCryptoError $ apnsNotification tkn nonce (paddedNtfLength apnsCfg) pn
   req <- liftIO $ apnsRequest c tknStr apnsNtf
-  -- TODO when HTTP2 client is thread-safe, we can use sendRequestDirect
-  HTTP2Response {response, respBody = HTTP2Body {bodyHead}} <- liftHTTPS2 $ sendRequest http2 req Nothing
+  HTTP2Response {response, respBody = HTTP2Body {bodyHead}} <- liftHTTPS2 $ sendRequestDirect http2 req Nothing
   let status = H.responseStatus response
       reason' = maybe "" reason $ J.decodeStrict' bodyHead
   if status == Just N.ok200
@@ -373,8 +375,8 @@ apnsPushProviderClient c@APNSPushClient {nonceDrg, apnsCfg} tkn@NtfTknRec {token
       | status == Just N.gone410 = throwE $ case reason' of
           "ExpiredToken" -> PPTokenInvalid NTIRExpiredToken
           "Unregistered" -> PPTokenInvalid NTIRUnregistered
-          _ -> PPRetryLater
-      | status == Just N.serviceUnavailable503 = liftIO (disconnectApnsHTTP2Client c) >> throwE PPRetryLater
+          _ -> PPRetryLater $ "410 " <> reason'
+      | status == Just N.serviceUnavailable503 = liftIO (disconnectApnsHTTP2Client c) >> throwE (PPRetryLater "503")
       -- Just tooManyRequests429 -> TooManyRequests - too many requests for the same token
       | otherwise = throwE $ PPResponseError status reason'
     liftHTTPS2 a = ExceptT $ first PPConnection <$> a

src/Simplex/Messaging/Notifications/Server/Store/Postgres.hs

@@ -270,7 +270,7 @@ getUsedSMPServers st =
             smp_host, smp_port, smp_keyhash, smp_server_id,
             ntf_service_id, smp_notifier_count, smp_notifier_ids_hash
           FROM smp_servers
-          WHERE EXISTS (SELECT 1 FROM subscriptions WHERE status IN ?)
+          WHERE EXISTS (SELECT 1 FROM subscriptions WHERE smp_server_id = smp_servers.smp_server_id AND status IN ?)
         |]
         (Only (In subscribeNtfStatuses))
   where

src/Simplex/Messaging/Protocol.hs

@@ -80,6 +80,7 @@ module Simplex.Messaging.Protocol
     ErrorType (..),
     CommandError (..),
     ProxyError (..),
+    NameErrorType (..),
     BrokerErrorType (..),
     NetworkError (..),
     BlockingInfo (..),
@@ -163,6 +164,7 @@ module Simplex.Messaging.Protocol
     EncTransmission (..),
     FwdResponse (..),
     FwdTransmission (..),
+    NameRecord (..),
     MsgFlags (..),
     initialSMPClientVersion,
     currentSMPClientVersion,
@@ -263,10 +265,12 @@ import Simplex.Messaging.Agent.Store.DB (Binary (..), FromField (..), ToField (.
 import qualified Simplex.Messaging.Crypto as C
 import Simplex.Messaging.Encoding
 import Simplex.Messaging.Encoding.String
+import Simplex.Messaging.Names.Record (NameRecord (..))
 import Simplex.Messaging.Parsers
 import Simplex.Messaging.Protocol.Types
 import Simplex.Messaging.Server.QueueStore.QueueInfo
 import Simplex.Messaging.ServiceScheme
+import Simplex.Messaging.SimplexName (SimplexDomain)
 import Simplex.Messaging.Transport
 import Simplex.Messaging.Transport.Client (TransportHost, TransportHosts (..))
 import Simplex.Messaging.Util (bshow, eitherToMaybe, safeDecodeUtf8, (<$?>))
@@ -343,6 +347,7 @@ data Party
   | LinkClient
   | ProxiedClient
   | ProxyService
+  | Resolver
   deriving (Show)
 
 -- | Singleton types for SMP protocol clients
@@ -357,6 +362,7 @@ data SParty :: Party -> Type where
   SSenderLink :: SParty LinkClient
   SProxiedClient :: SParty ProxiedClient
   SProxyService :: SParty ProxyService
+  SResolver :: SParty Resolver
 
 instance TestEquality SParty where
   testEquality SCreator SCreator = Just Refl
@@ -369,6 +375,7 @@ instance TestEquality SParty where
   testEquality SSenderLink SSenderLink = Just Refl
   testEquality SProxiedClient SProxiedClient = Just Refl
   testEquality SProxyService SProxyService = Just Refl
+  testEquality SResolver SResolver = Just Refl
   testEquality _ _ = Nothing
 
 deriving instance Show (SParty p)
@@ -395,6 +402,8 @@ instance PartyI ProxiedClient where sParty = SProxiedClient
 
 instance PartyI ProxyService where sParty = SProxyService
 
+instance PartyI Resolver where sParty = SResolver
+
 -- command parties that can read queues
 type family QueueParty (p :: Party) :: Constraint where
   QueueParty Recipient = ()
@@ -473,6 +482,7 @@ partyClientRole = \case
   SSenderLink -> Just SRMessaging
   SProxiedClient -> Just SRMessaging
   SProxyService -> Just SRProxy
+  SResolver -> Just SRMessaging
 {-# INLINE partyClientRole #-}
 
 partyServiceRole :: ServiceParty p => SParty p -> SMPServiceRole
@@ -597,6 +607,8 @@ data Command (p :: Party) where
   -- - entity ID: empty
   -- - corrId: unique correlation ID between proxy and relay, also used as a nonce to encrypt forwarded transmission
   RFWD :: EncFwdTransmission -> Command ProxyService -- use CorrId as CbNonce, proxy to relay
+  -- Resolve SimpleX name.
+  RSLV :: SimplexDomain -> Command Resolver
 
 deriving instance Show (Command p)
 
@@ -732,6 +744,8 @@ data BrokerMsg where
   OK :: BrokerMsg
   ERR :: ErrorType -> BrokerMsg
   PONG :: BrokerMsg
+  -- Resolved SimpleX name.
+  RNAME :: NameRecord -> BrokerMsg
   deriving (Eq, Show)
 
 data RcvMessage = RcvMessage
@@ -942,6 +956,7 @@ data CommandTag (p :: Party) where
   RFWD_ :: CommandTag ProxyService
   NSUB_ :: CommandTag Notifier
   NSUBS_ :: CommandTag NotifierService
+  RSLV_ :: CommandTag Resolver
 
 data CmdTag = forall p. PartyI p => CT (SParty p) (CommandTag p)
 
@@ -968,6 +983,7 @@ data BrokerMsgTag
   | OK_
   | ERR_
   | PONG_
+  | RNAME_
   deriving (Show)
 
 class ProtocolMsgTag t where
@@ -1004,6 +1020,7 @@ instance PartyI p => Encoding (CommandTag p) where
     RFWD_ -> "RFWD"
     NSUB_ -> "NSUB"
     NSUBS_ -> "NSUBS"
+    RSLV_ -> "RSLV"
   smpP = messageTagP
 
 instance ProtocolMsgTag CmdTag where
@@ -1032,6 +1049,7 @@ instance ProtocolMsgTag CmdTag where
     "RFWD" -> Just $ CT SProxyService RFWD_
     "NSUB" -> Just $ CT SNotifier NSUB_
     "NSUBS" -> Just $ CT SNotifierService NSUBS_
+    "RSLV" -> Just $ CT SResolver RSLV_
     _ -> Nothing
 
 instance Encoding CmdTag where
@@ -1061,6 +1079,7 @@ instance Encoding BrokerMsgTag where
     OK_ -> "OK"
     ERR_ -> "ERR"
     PONG_ -> "PONG"
+    RNAME_ -> "RNAME"
   smpP = messageTagP
 
 instance ProtocolMsgTag BrokerMsgTag where
@@ -1083,6 +1102,7 @@ instance ProtocolMsgTag BrokerMsgTag where
     "OK" -> Just OK_
     "ERR" -> Just ERR_
     "PONG" -> Just PONG_
+    "RNAME" -> Just RNAME_
     _ -> Nothing
 
 -- | SMP message body format
@@ -1526,11 +1546,14 @@ queueIdHash = IdsHash . C.md5Hash . unEntityId
 {-# INLINE queueIdHash #-}
 
 addServiceSubs :: (Int64, IdsHash) -> (Int64, IdsHash) -> (Int64, IdsHash)
-addServiceSubs (n', idsHash') (n, idsHash) = (n + n', idsHash <> idsHash')
+addServiceSubs (n', idsHash') (n, idsHash) =
+  let !n'' = n + n'
+      !h = idsHash <> idsHash'
+   in (n'', h)
 
 subtractServiceSubs :: (Int64, IdsHash) -> (Int64, IdsHash) -> (Int64, IdsHash)
 subtractServiceSubs (n', idsHash') (n, idsHash)
-  | n > n' = (n - n', idsHash <> idsHash') -- concat is a reversible xor: (x `xor` y) `xor` y == x
+  | n > n' = let !n'' = n - n'; !h = idsHash <> idsHash' in (n'', h) -- concat is a reversible xor: (x `xor` y) `xor` y == x
   | otherwise = (0, mempty)
 
 data ProtocolErrorType = PECmdSyntax | PECmdUnknown | PESession | PEBlock
@@ -1565,10 +1588,22 @@ data ErrorType
     EXPIRED
   | -- | internal server error
     INTERNAL
+  | -- | name resolution error
+    NAME {nameErr :: NameErrorType}
   | -- | used internally, never returned by the server (to be removed)
     DUPLICATE_ -- not part of SMP protocol, used internally
   deriving (Eq, Show)
 
+-- | Name resolution error
+data NameErrorType
+  = -- | the names role / resolver is not configured on this server
+    NO_RESOLVER
+  | -- | the name is not registered (resolver returned not-found)
+    NOT_FOUND
+  | -- | backing resolver/RPC failure - contains the diagnostic detail
+    RESOLVER {resolverErr :: Text}
+  deriving (Eq, Show)
+
 instance StrEncoding ErrorType where
   strEncode = \case
     BLOCK -> "BLOCK"
@@ -1585,6 +1620,7 @@ instance StrEncoding ErrorType where
     LARGE_MSG -> "LARGE_MSG"
     EXPIRED -> "EXPIRED"
     INTERNAL -> "INTERNAL"
+    NAME e -> "NAME " <> strEncode e
     DUPLICATE_ -> "DUPLICATE_"
   strP =
     A.choice
@@ -1592,6 +1628,7 @@ instance StrEncoding ErrorType where
         "SESSION" $> SESSION,
         "CMD " *> (CMD <$> parseRead1),
         "PROXY " *> (PROXY <$> strP),
+        "NAME " *> (NAME <$> strP),
         "AUTH" $> AUTH,
         "BLOCKED " *> strP,
         "SERVICE" $> SERVICE,
@@ -1792,6 +1829,7 @@ instance PartyI p => ProtocolEncoding SMPVersion ErrorType (Command p) where
     PRXY host auth_ -> e (PRXY_, ' ', host, auth_)
     PFWD fwdV pubKey (EncTransmission s) -> e (PFWD_, ' ', fwdV, pubKey, Tail s)
     RFWD (EncFwdTransmission s) -> e (RFWD_, ' ', Tail s)
+    RSLV d -> e (RSLV_, ' ', d)
     where
       e :: Encoding a => a -> ByteString
       e = smpEncode
@@ -1816,6 +1854,7 @@ instance PartyI p => ProtocolEncoding SMPVersion ErrorType (Command p) where
     PRXY {} -> noAuthCmd
     PFWD {} -> entityCmd
     RFWD _ -> noAuthCmd
+    RSLV _ -> noAuthCmd
     SUB -> serviceCmd
     NSUB -> serviceCmd
     -- other client commands must have both signature and queue ID
@@ -1899,6 +1938,7 @@ instance ProtocolEncoding SMPVersion ErrorType Cmd where
     CT SNotifierService NSUBS_
       | v >= rcvServiceSMPVersion -> Cmd SNotifierService <$> (NSUBS <$> _smpP <*> smpP)
       | otherwise -> pure $ Cmd SNotifierService $ NSUBS (-1) mempty
+    CT SResolver RSLV_ -> Cmd SResolver . RSLV <$> _smpP <* A.takeByteString
 
   fromProtocolError = fromProtocolError @SMPVersion @ErrorType @BrokerMsg
   {-# INLINE fromProtocolError #-}
@@ -1945,6 +1985,7 @@ instance ProtocolEncoding SMPVersion ErrorType BrokerMsg where
             | v < clientNoticesSMPVersion -> BLOCKED info {notice = Nothing}
           _ -> err
     PONG -> e PONG_
+    RNAME rec -> e (RNAME_, ' ', Tail $ LB.toStrict $ J.encode rec)
     where
       e :: Encoding a => a -> ByteString
       e = smpEncode
@@ -1992,6 +2033,7 @@ instance ProtocolEncoding SMPVersion ErrorType BrokerMsg where
     OK_ -> pure OK
     ERR_ -> ERR <$> _smpP
     PONG_ -> pure PONG
+    RNAME_ -> fmap RNAME . J.eitherDecodeStrict . unTail <$?> _smpP
     where
       serviceRespP resp
         | v >= rcvServiceSMPVersion = resp <$> _smpP <*> smpP
@@ -2014,6 +2056,7 @@ instance ProtocolEncoding SMPVersion ErrorType BrokerMsg where
     PKEY {} -> noEntityMsg
     RRES _ -> noEntityMsg
     ALLS -> noEntityMsg
+    RNAME _ -> noEntityMsg
     -- other broker responses must have queue ID
     _
       | B.null entId -> Left $ CMD NO_ENTITY
@@ -2056,6 +2099,7 @@ instance Encoding ErrorType where
     NO_MSG -> "NO_MSG"
     LARGE_MSG -> "LARGE_MSG"
     INTERNAL -> "INTERNAL"
+    NAME err -> "NAME " <> smpEncode err
     DUPLICATE_ -> "DUPLICATE_"
 
   smpP =
@@ -2074,9 +2118,26 @@ instance Encoding ErrorType where
       "NO_MSG" -> pure NO_MSG
       "LARGE_MSG" -> pure LARGE_MSG
       "INTERNAL" -> pure INTERNAL
+      "NAME" -> NAME <$> _smpP
       "DUPLICATE_" -> pure DUPLICATE_
       _ -> fail "bad ErrorType"
 
+instance Encoding NameErrorType where
+  smpEncode = \case
+    NO_RESOLVER -> "NO_RESOLVER"
+    NOT_FOUND -> "NOT_FOUND"
+    RESOLVER e -> "RESOLVER " <> encodeUtf8 e
+  smpP =
+    A.takeTill (== ' ') >>= \case
+      "NO_RESOLVER" -> pure NO_RESOLVER
+      "NOT_FOUND" -> pure NOT_FOUND
+      "RESOLVER" -> RESOLVER . safeDecodeUtf8 <$> (A.space *> A.takeByteString)
+      _ -> fail "bad NameErrorType"
+
+instance StrEncoding NameErrorType where
+  strEncode = smpEncode
+  strP = smpP
+
 instance Encoding CommandError where
   smpEncode e = case e of
     UNKNOWN -> "UNKNOWN"
@@ -2376,4 +2437,4 @@ $(J.deriveJSON (sumTypeJSON id) ''BrokerErrorType)
 $(J.deriveJSON defaultJSON ''BlockingInfo)
 
 -- run deriveJSON in one TH splice to allow mutual instance
-$(concat <$> mapM @[] (J.deriveJSON (sumTypeJSON id)) [''ProxyError, ''ErrorType])
+$(concat <$> mapM @[] (J.deriveJSON (sumTypeJSON id)) [''ProxyError, ''NameErrorType, ''ErrorType])

src/Simplex/Messaging/Server.hs

@@ -65,7 +65,7 @@ import Data.Constraint (Dict (..))
 import Data.Dynamic (toDyn)
 import Data.Either (fromRight, partitionEithers)
 import Data.Foldable (foldrM)
-import Data.Functor (($>))
+import Data.Functor (($>), (<&>))
 import Data.IORef
 import Data.Int (Int64)
 import qualified Data.IntMap.Strict as IM
@@ -91,7 +91,7 @@ import qualified Data.X509 as X
 import qualified Data.X509.Validation as XV
 import GHC.Conc.Signal
 import GHC.IORef (atomicSwapIORef)
-import GHC.Stats (RTSStats (..), GCDetails (..), getRTSStats)
+import GHC.Stats (getRTSStats)
 import GHC.TypeLits (KnownNat)
 import Network.Socket (ServiceName, Socket, socketToHandle)
 import qualified Network.TLS as TLS
@@ -103,11 +103,13 @@ import qualified Simplex.Messaging.Crypto as C
 import Simplex.Messaging.Encoding
 import Simplex.Messaging.Encoding.String
 import Simplex.Messaging.Protocol
+import Simplex.Messaging.SimplexName (SimplexDomain)
 import Simplex.Messaging.Server.Control
 import Simplex.Messaging.Server.Env.STM as Env
 import Simplex.Messaging.Server.Expiration
 import Simplex.Messaging.Server.MsgStore
 import Simplex.Messaging.Server.MsgStore.Journal (JournalMsgStore, JournalQueue (..), getJournalQueueMessages)
+import Simplex.Messaging.Server.Names (NamesEnv, closeNamesEnv, resolveName)
 import Simplex.Messaging.Server.MsgStore.STM
 import Simplex.Messaging.Server.MsgStore.Types
 import Simplex.Messaging.Server.NtfStore
@@ -198,7 +200,6 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
             <> serverStatsThread_ cfg
             <> prometheusMetricsThread_ cfg
             <> controlPortThread_ cfg
-            <> [memoryDiagThread]
     )
     `finally` stopServer s
   where
@@ -246,7 +247,9 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
       saveServerStats
 
     closeServer :: M s ()
-    closeServer = asks (smpAgent . proxyAgent) >>= liftIO . closeSMPClientAgent
+    closeServer = do
+      asks (smpAgent . proxyAgent) >>= liftIO . closeSMPClientAgent
+      asks namesEnv >>= liftIO . mapM_ closeNamesEnv
 
     serverThread ::
       forall sub. String ->
@@ -293,7 +296,7 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
                 pure $ as ++ as'
               CSService serviceId changedSubs -> do
                 modifyTVar' subClients $ IS.insert clntId -- add ID to server's subscribed cients
-                modifyTVar' totalServiceSubs $ subtractServiceSubs changedSubs -- server count and IDs hash for all services
+                modifyTVar' totalServiceSubs $ addServiceSubs changedSubs -- server count and IDs hash for all services
                 cancelServiceSubs serviceId =<< upsertSubscribedClient serviceId c serviceSubscribers
             updateSubDisconnected = case clntSub of
                 -- do not insert client if it is already disconnected, but send END/DELD to any other client subscribed to this queue or service
@@ -330,21 +333,25 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
         endPreviousSubscriptions = mapM_ $ \(c, subAction, evt) -> do
           atomically $ modifyTVar' pendingEvents $ IM.alter (Just . maybe [evt] (evt <|)) (clientId c)
           case subAction of
-            CSAEndSub qId -> atomically (endSub c qId) >>= a unsub_
-              where
-                a (Just unsub) (Just s) = unsub s
-                a _ _ = pure ()
-            CSAEndServiceSub qId -> atomically $ do
-              modifyTVar' (clientServiceSubs c) decrease
-              modifyTVar' totalServiceSubs decrease
-              where
-                decrease = subtractServiceSubs (1, queueIdHash qId)
+            CSAEndSub qId -> atomically (endSub c qId) >>= unsubPrev
+            -- like endSub, also removes the delivery subscription from the service client's subscriptions map,
+            -- otherwise the map retains entries for queues unassociated/deleted while the service stays connected.
+            CSAEndServiceSub qId -> atomically (endServiceQueueSub c qId) >>= unsubPrev
             CSADecreaseSubs changedSubs -> do
               atomically $ modifyTVar' totalServiceSubs $ subtractServiceSubs changedSubs
               forM_ unsub_ $ \unsub -> atomically (swapTVar (clientSubs c) M.empty) >>= mapM_ unsub
           where
+            unsubPrev :: Maybe sub -> IO ()
+            unsubPrev s_ = sequence_ (unsub_ <*> s_)
             endSub :: Client s -> QueueId -> STM (Maybe sub)
             endSub c qId = TM.lookupDelete qId (clientSubs c) >>= (removeWhenNoSubs c $>)
+            endServiceQueueSub :: Client s -> QueueId -> STM (Maybe sub)
+            endServiceQueueSub c qId = do
+              modifyTVar' (clientServiceSubs c) decrease
+              modifyTVar' totalServiceSubs decrease
+              endSub c qId
+              where
+                decrease = subtractServiceSubs (1, queueIdHash qId)
         -- remove client from server's subscribed cients
         removeWhenNoSubs c = do
           noClientSubs <- null <$> readTVar (clientSubs c)
@@ -514,7 +521,7 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
       initialDelay <- (startAt -) . fromIntegral . (`div` 1000000_000000) . diffTimeToPicoseconds . utctDayTime <$> liftIO getCurrentTime
       liftIO $ putStrLn $ "server stats log enabled: " <> statsFilePath
       liftIO $ threadDelay' $ 1000000 * (initialDelay + if initialDelay < 0 then 86400 else 0)
-      ss@ServerStats {fromTime, qCreated, qSecured, qDeletedAll, qDeletedAllB, qDeletedNew, qDeletedSecured, qSub, qSubAllB, qSubAuth, qSubDuplicate, qSubProhibited, qSubEnd, qSubEndB, ntfCreated, ntfDeleted, ntfDeletedB, ntfSub, ntfSubB, ntfSubAuth, ntfSubDuplicate, msgSent, msgSentAuth, msgSentQuota, msgSentLarge, msgRecv, msgRecvGet, msgGet, msgGetNoMsg, msgGetAuth, msgGetDuplicate, msgGetProhibited, msgExpired, activeQueues, msgSentNtf, msgRecvNtf, activeQueuesNtf, qCount, msgCount, ntfCount, pRelays, pRelaysOwn, pMsgFwds, pMsgFwdsOwn, pMsgFwdsRecv, rcvServices, ntfServices}
+      ss@ServerStats {fromTime, qCreated, qSecured, qDeletedAll, qDeletedAllB, qDeletedNew, qDeletedSecured, qSub, qSubAllB, qSubAuth, qSubDuplicate, qSubProhibited, qSubEnd, qSubEndB, ntfCreated, ntfDeleted, ntfDeletedB, ntfSub, ntfSubB, ntfSubAuth, ntfSubDuplicate, msgSent, msgSentAuth, msgSentQuota, msgSentLarge, msgRecv, msgRecvGet, msgGet, msgGetNoMsg, msgGetAuth, msgGetDuplicate, msgGetProhibited, msgExpired, activeQueues, msgSentNtf, msgRecvNtf, activeQueuesNtf, qCount, msgCount, ntfCount, pRelays, pRelaysOwn, pMsgFwds, pMsgFwdsOwn, pMsgFwdsRecv, rcvServices, ntfServices, rslvStats}
         <- asks serverStats
       st <- asks msgStore
       EntityCounts {queueCount, notifierCount, rcvServiceCount, ntfServiceCount, rcvServiceQueuesCount, ntfServiceQueuesCount} <-
@@ -577,6 +584,7 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
           qCount' <- readIORef qCount
           msgCount' <- readIORef msgCount
           ntfCount' <- readIORef ntfCount
+          rslvStats' <- getResetNameResolverStatsData rslvStats
           T.hPutStrLn h $
             T.intercalate
               ","
@@ -650,6 +658,7 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
                      ]
                        <> showServiceStats rcvServices'
                        <> showServiceStats ntfServices'
+                       <> showNameResolverStats rslvStats'
               )
         liftIO $ threadDelay' interval
       where
@@ -657,6 +666,8 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
           map tshow [_pRequests, _pSuccesses, _pErrorsConnect, _pErrorsCompat, _pErrorsOther]
         showServiceStats ServiceStatsData {_srvAssocNew, _srvAssocDuplicate, _srvAssocUpdated, _srvAssocRemoved, _srvSubCount, _srvSubDuplicate, _srvSubQueues, _srvSubEnd} =
           map tshow [_srvAssocNew, _srvAssocDuplicate, _srvAssocUpdated, _srvAssocRemoved, _srvSubCount, _srvSubDuplicate, _srvSubQueues, _srvSubEnd]
+        showNameResolverStats NameResolverStatsData {_rslvReqs, _rslvSucc, _rslvNotFound, _rslvResolverErrs, _rslvDisabled} =
+          map tshow [_rslvReqs, _rslvSucc, _rslvNotFound, _rslvResolverErrs, _rslvDisabled]
 
     prometheusMetricsThread_ :: ServerConfig s -> [M s ()]
     prometheusMetricsThread_ ServerConfig {prometheusInterval = Just interval, prometheusMetricsFile} =
@@ -702,12 +713,13 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
       loadedCounts <- loadedQueueCounts $ fromMsgStore ms
       pure RealTimeMetrics {socketStats, threadsCount, clientsCount, deliveredSubs, deliveredTimes, smpSubs, ntfSubs, loadedCounts}
       where
-        getSubscribersMetrics ServerSubscribers {queueSubscribers, serviceSubscribers, subClients} = do
+        getSubscribersMetrics ServerSubscribers {queueSubscribers, serviceSubscribers, totalServiceSubs, subClients} = do
           subsCount <- M.size <$> getSubscribedClients queueSubscribers
           subClientsCount <- IS.size <$> readTVarIO subClients
           subServicesCount <- M.size <$> getSubscribedClients serviceSubscribers
-          pure RTSubscriberMetrics {subsCount, subClientsCount, subServicesCount}
-        getDeliveredMetrics ts' = foldM countClnt (RTSubscriberMetrics 0 0 0, emptyTimeBuckets) =<< getServerClients srv
+          subServiceSubsCount <- fst <$> readTVarIO totalServiceSubs
+          pure RTSubscriberMetrics {subsCount, subClientsCount, subServicesCount, subServiceSubsCount}
+        getDeliveredMetrics ts' = foldM countClnt (RTSubscriberMetrics 0 0 0 0, emptyTimeBuckets) =<< getServerClients srv
           where
             countClnt acc@(metrics, times) Client {subscriptions} = do
               (cnt, times') <- foldM countSubs (0, times) =<< readTVarIO subscriptions
@@ -720,75 +732,6 @@ smpServer started cfg@ServerConfig {transports, transportConfig = tCfg, startOpt
                 Nothing -> acc
                 Just (_, ts) -> (cnt + 1, updateTimeBuckets ts ts' times)
 
-    memoryDiagThread :: M s ()
-    memoryDiagThread = do
-      labelMyThread "memoryDiag"
-      Env
-        { ntfStore = NtfStore ntfMap,
-          server = srv@Server {subscribers, ntfSubscribers},
-          proxyAgent = ProxyAgent {smpAgent = pa},
-          msgStore_ = ms
-        } <- ask
-      let SMPClientAgent {smpClients, smpSessions, activeServiceSubs, activeQueueSubs, pendingServiceSubs, pendingQueueSubs, smpSubWorkers} = pa
-      liftIO $ forever $ do
-        threadDelay 300_000_000 -- 5 minutes
-        rts <- getRTSStats
-        let GCDetails {gcdetails_live_bytes, gcdetails_mem_in_use_bytes, gcdetails_large_objects_bytes, gcdetails_compact_bytes, gcdetails_block_fragmentation_bytes} = gc rts
-        clientCount <- IM.size <$> getServerClients srv
-        smpQSubs <- M.size <$> getSubscribedClients (queueSubscribers subscribers)
-        smpSSubs <- M.size <$> getSubscribedClients (serviceSubscribers subscribers)
-        ntfQSubs <- M.size <$> getSubscribedClients (queueSubscribers ntfSubscribers)
-        ntfSSubs <- M.size <$> getSubscribedClients (serviceSubscribers ntfSubscribers)
-        smpPending <- IM.size <$> readTVarIO (pendingEvents subscribers)
-        ntfPending <- IM.size <$> readTVarIO (pendingEvents ntfSubscribers)
-        ntfStoreSize <- M.size <$> readTVarIO ntfMap
-        paClients' <- M.size <$> readTVarIO smpClients
-        paSessions' <- M.size <$> readTVarIO smpSessions
-        paActSvc <- M.size <$> readTVarIO activeServiceSubs
-        paActQ <- M.size <$> readTVarIO activeQueueSubs
-        paPndSvc <- M.size <$> readTVarIO pendingServiceSubs
-        paPndQ <- M.size <$> readTVarIO pendingQueueSubs
-        paWorkers <- M.size <$> readTVarIO smpSubWorkers
-        lc <- loadedQueueCounts $ fromMsgStore ms
-        -- per-client metrics: total subscriptions and queue fill
-        clients <- getServerClients srv
-        let clientsList = IM.elems clients
-        totalSubs <- sum <$> mapM (\Client {subscriptions} -> M.size <$> readTVarIO subscriptions) clientsList
-        totalSndQ <- sum <$> mapM (\Client {sndQ} -> fromIntegral <$> atomically (lengthTBQueue sndQ)) clientsList
-        totalMsgQ <- sum <$> mapM (\Client {msgQ} -> fromIntegral <$> atomically (lengthTBQueue msgQ)) clientsList
-        totalEndThreads <- sum <$> mapM (\Client {endThreads} -> IM.size <$> readTVarIO endThreads) clientsList
-        logInfo $
-          "MEMORY"
-            <> " rts_live=" <> tshow gcdetails_live_bytes
-            <> " rts_heap=" <> tshow gcdetails_mem_in_use_bytes
-            <> " rts_max_live=" <> tshow (max_live_bytes rts)
-            <> " rts_large=" <> tshow gcdetails_large_objects_bytes
-            <> " rts_compact=" <> tshow gcdetails_compact_bytes
-            <> " rts_frag=" <> tshow gcdetails_block_fragmentation_bytes
-            <> " rts_gc=" <> tshow (gcs rts)
-            <> " clients=" <> tshow clientCount
-            <> " clientSubs=" <> tshow totalSubs
-            <> " clientSndQ=" <> tshow (totalSndQ :: Int)
-            <> " clientMsgQ=" <> tshow (totalMsgQ :: Int)
-            <> " clientThreads=" <> tshow totalEndThreads
-            <> " smpQSubs=" <> tshow smpQSubs
-            <> " smpSSubs=" <> tshow smpSSubs
-            <> " ntfQSubs=" <> tshow ntfQSubs
-            <> " ntfSSubs=" <> tshow ntfSSubs
-            <> " smpPending=" <> tshow smpPending
-            <> " ntfPending=" <> tshow ntfPending
-            <> " ntfStore=" <> tshow ntfStoreSize
-            <> " paClients=" <> tshow paClients'
-            <> " paSessions=" <> tshow paSessions'
-            <> " paActSvc=" <> tshow paActSvc
-            <> " paActQ=" <> tshow paActQ
-            <> " paPndSvc=" <> tshow paPndSvc
-            <> " paPndQ=" <> tshow paPndQ
-            <> " paWorkers=" <> tshow paWorkers
-            <> " loadedQ=" <> tshow (loadedQueueCount lc)
-            <> " loadedNtf=" <> tshow (loadedNotifierCount lc)
-            <> " ntfLocks=" <> tshow (notifierLockCount lc)
-
     runClient :: Transport c => X.CertificateChain -> C.APrivateSignKey -> TProxy c 'TServer -> c 'TServer -> M s ()
     runClient srvCert srvSignKey tp h = do
       ms <- asks msgStore
@@ -1331,6 +1274,7 @@ verifyQueueTransmission service thAuth (tAuth, authorized, (corrId, entId, comma
     vc SNotifierService NSUBS {} = verifyServiceCmd
     vc SProxiedClient _ = VRVerified Nothing
     vc SProxyService (RFWD _) = VRVerified Nothing
+    vc SResolver (RSLV _) = VRVerified Nothing
     checkRole = case (service, partyClientRole p) of
       (Just THClientService {serviceRole}, Just role) -> serviceRole == role
       _ -> True
@@ -1435,14 +1379,38 @@ client
     labelMyThread . B.unpack $ "client $" <> encode sessionId <> " commands"
     let THandleParams {thVersion} = thParams'
         clntServiceId = (\THClientService {serviceId} -> serviceId) <$> (peerClientService =<< thAuth thParams')
-        process t acc@(rs, msgs) =
+        process batchSubs t acc@(rs, msgs) =
           (maybe acc (\(!r, !msg_) -> (r : rs, maybe msgs (: msgs) msg_)))
-            <$> processCommand clntServiceId thVersion t
-    forever $
-      atomically (readTBQueue rcvQ)
-        >>= foldrM process ([], [])
+            <$> processCommand clntServiceId thVersion batchSubs t
+    forever $ do
+      batch <- atomically (readTBQueue rcvQ)
+      batchSubs <- prepareBatchSubs clntServiceId batch
+      foldrM (process batchSubs) ([], []) batch
         >>= \(rs_, msgs) -> mapM_ (atomically . writeTBQueue sndQ . (,msgs)) (L.nonEmpty rs_)
   where
+    prepareBatchSubs ::
+      Maybe ServiceId ->
+      NonEmpty (VerifiedTransmission s) ->
+      M s (Either ErrorType (Map RecipientId Message, Map RecipientId (Either ErrorType ()), Map RecipientId (Either ErrorType ())))
+    prepareBatchSubs clntServiceId_ batch = do
+      let (subMsgQs, rcvAssocQs, ntfAssocQs) = foldr partitionSubs ([], [], []) batch
+          partitionSubs t (msgQs, rcvQs, ntfQs) = case t of
+            (Just (q, qr), (_, _, Cmd SRecipient SUB))
+              | clntServiceId_ /= rcvServiceId qr -> (q : msgQs, q : rcvQs, ntfQs)
+              | otherwise -> (q : msgQs, rcvQs, ntfQs)
+            (Just (q, qr), (_, _, Cmd SNotifier NSUB))
+              | clntServiceId_ /= (notifier qr >>= ntfServiceId) -> (msgQs, rcvQs, q : ntfQs)
+            _ -> (msgQs, rcvQs, ntfQs)
+      liftIO $ runExceptT $ do
+        rcvAssocs <- ifNotNull rcvAssocQs $ setService SRecipientService clntServiceId_
+        ntfAssocs <- ifNotNull ntfAssocQs $ setService SNotifierService clntServiceId_
+        msgs <- ifNotNull subMsgQs $ tryPeekMsgs ms
+        pure (msgs, rcvAssocs, ntfAssocs)
+      where
+        ifNotNull qs f = if null qs then pure M.empty else f qs
+        setService :: (PartyI p, ServiceParty p) => SParty p -> Maybe ServiceId -> [StoreQueue s] -> ExceptT ErrorType IO (Map RecipientId (Either ErrorType ()))
+        setService party sId = ExceptT . setQueueServices (queueStore ms) party sId
+
     processProxiedCmd :: Transmission (Command 'ProxiedClient) -> M s (Maybe ResponseAndMessage)
     processProxiedCmd (corrId, EntityId sessId, command) = (\t -> ((corrId, EntityId sessId, t), Nothing)) <$$> case command of
       PRXY srv auth -> ifM allowProxy getRelay (pure $ Just $ ERR $ PROXY BASIC_AUTH)
@@ -1504,38 +1472,64 @@ client
           Nothing -> inc False pRequests >> inc False pErrorsConnect $> Just (ERR $ PROXY NO_SESSION)
       where
         forkProxiedCmd :: M s BrokerMsg -> M s (Maybe BrokerMsg)
-        forkProxiedCmd cmdAction = do
-          bracket_ wait signal . forkClient clnt (B.unpack $ "client $" <> encode sessionId <> " proxy") $ do
-            -- commands MUST be processed under a reasonable timeout or the client would halt
-            cmdAction >>= \t -> atomically $ writeTBQueue sndQ ([(corrId, EntityId sessId, t)], [])
-          pure Nothing
-          where
-            wait = do
-              ServerConfig {serverClientConcurrency} <- asks config
-              atomically $ do
-                used <- readTVar procThreads
-                when (used >= serverClientConcurrency) retry
-                writeTVar procThreads $! used + 1
-            signal = atomically $ modifyTVar' procThreads (\t -> t - 1)
+        forkProxiedCmd = forkCmd serverClientConcurrency corrId (EntityId sessId)
+    -- Run a slow command on a thread
+    forkCmd :: (ServerConfig s -> Int) -> CorrId -> EntityId -> M s BrokerMsg -> M s (Maybe a)
+    forkCmd concurrency corrId entId cmdAction = do
+      bracket_ wait signal . forkClient clnt (B.unpack $ "client $" <> encode sessionId <> " cmd") $
+        -- commands MUST be processed under a reasonable timeout or the client would halt
+        cmdAction >>= \t -> atomically $ writeTBQueue sndQ ([(corrId, entId, t)], [])
+      pure Nothing
+      where
+        wait = do
+          limit <- asks (concurrency . config)
+          atomically $ do
+            used <- readTVar procThreads
+            when (used >= limit) retry
+            writeTVar procThreads $! used + 1
+        signal = atomically $ modifyTVar' procThreads (\t -> t - 1)
+    rslvNamesEnv :: M s (Maybe NamesEnv)
+    rslvNamesEnv = do
+      st <- asks (rslvStats . serverStats)
+      incStat (rslvReqs st)
+      asks namesEnv >>= \case
+        Nothing -> incStat (rslvDisabled st) $> Nothing
+        Just nenv -> pure (Just nenv)
+    -- Runs on a forked thread so RSLV does not block other commands;
+    -- concurrency is limited by serverResolverConcurrency in forkCmd.
+    resolveNameMsg :: NamesEnv -> SimplexDomain -> M s BrokerMsg
+    resolveNameMsg nenv d = do
+      st <- asks (rslvStats . serverStats)
+      (selector, msg) <-
+        liftIO (resolveName nenv d) <&> \case
+          Right rec -> (rslvSucc, RNAME rec)
+          Left e@NOT_FOUND -> (rslvNotFound, ERR $ NAME e)
+          Left e -> (rslvResolverErrs, ERR $ NAME e)
+      incStat (selector st) $> msg
     transportErr :: TransportError -> ErrorType
     transportErr = PROXY . BROKER . TRANSPORT
     mkIncProxyStats :: MonadIO m => ProxyStats -> ProxyStats -> OwnServer -> (ProxyStats -> IORef Int) -> m ()
     mkIncProxyStats ps psOwn own sel = do
       incStat $ sel ps
       when own $ incStat $ sel psOwn
-    processCommand :: Maybe ServiceId -> VersionSMP -> VerifiedTransmission s -> M s (Maybe ResponseAndMessage)
-    processCommand clntServiceId clntVersion (q_, (corrId, entId, cmd)) = case cmd of
+    processCommand :: Maybe ServiceId -> VersionSMP -> Either ErrorType (Map RecipientId Message, Map RecipientId (Either ErrorType ()), Map RecipientId (Either ErrorType ())) -> VerifiedTransmission s -> M s (Maybe ResponseAndMessage)
+    processCommand clntServiceId clntVersion batchSubs (q_, (corrId, entId, cmd)) = case cmd of
       Cmd SProxiedClient command -> processProxiedCmd (corrId, entId, command)
       Cmd SSender command -> case command of
         SKEY k -> withQueue $ \q qr -> checkMode QMMessaging qr $ secureQueue_ q k
         SEND flags msgBody -> response <$> withQueue_ False err (sendMessage flags msgBody)
       Cmd SIdleClient PING -> pure $ response (corrId, NoEntity, PONG)
-      Cmd SProxyService (RFWD encBlock) -> response . (corrId,NoEntity,) <$> processForwardedCommand encBlock
+      Cmd SProxyService (RFWD encBlock) -> (response . (corrId, NoEntity,) =<<) <$> processForwardedCommand encBlock
+      Cmd SResolver (RSLV d) -> rslvNamesEnv >>= \case
+        Nothing -> pure $ response (corrId, NoEntity, ERR (NAME NO_RESOLVER))
+        Just nenv -> forkCmd serverResolverConcurrency corrId NoEntity (resolveNameMsg nenv d)
       Cmd SSenderLink command -> case command of
         LKEY k -> withQueue $ \q qr -> checkMode QMMessaging qr $ secureQueue_ q k $>> getQueueLink_ q qr
         LGET -> withQueue $ \q qr -> checkContact qr $ getQueueLink_ q qr
       Cmd SNotifier NSUB -> response . (corrId,entId,) <$> case q_ of
-        Just (q, QueueRec {notifier = Just ntfCreds}) -> subscribeNotifications q ntfCreds
+        Just (q, QueueRec {notifier = Just ntfCreds}) ->
+          either (pure . ERR) (\_ -> subscribeNotifications q ntfCreds)
+            $ batchSubs >>= \(_, _, ntfAssocs) -> sequence (M.lookup (recipientId q) ntfAssocs)
         _ -> pure $ ERR INTERNAL
       Cmd SNotifierService (NSUBS n idsHash) -> response . (corrId,entId,) <$> case clntServiceId of
         Just serviceId -> subscribeServiceNotifications serviceId (n, idsHash)
@@ -1548,7 +1542,9 @@ client
               pure $ allowNewQueues && maybe True ((== auth_) . Just) newQueueBasicAuth
       Cmd SRecipient command ->
         case command of
-          SUB -> withQueue' subscribeQueueAndDeliver
+          SUB -> case batchSubs >>= \(msgs, rcvAssocs, _) -> sequence (M.lookup entId rcvAssocs) $> msgs of
+            Left e -> pure $ Just (err e, Nothing)
+            Right msgs -> withQueue' $ subscribeQueueAndDeliver $ M.lookup entId msgs
           GET -> withQueue getMessage
           ACK msgId -> withQueue $ acknowledgeMsg msgId
           KEY sKey -> withQueue $ \q _ -> either err (corrId,entId,) <$> secureQueue_ q sKey
@@ -1689,13 +1685,11 @@ client
         suspendQueue_ :: (StoreQueue s, QueueRec) -> M s (Transmission BrokerMsg)
         suspendQueue_ (q, _) = liftIO $ either err (const ok) <$> suspendQueue (queueStore ms) q
 
-        subscribeQueueAndDeliver :: StoreQueue s -> QueueRec -> M s ResponseAndMessage
-        subscribeQueueAndDeliver q qr@QueueRec {rcvServiceId} =
+        subscribeQueueAndDeliver :: Maybe Message -> StoreQueue s -> QueueRec -> M s ResponseAndMessage
+        subscribeQueueAndDeliver msg_ q qr@QueueRec {rcvServiceId} =
           liftIO (TM.lookupIO entId $ subscriptions clnt) >>= \case
             Nothing ->
-              sharedSubscribeQueue q SRecipientService rcvServiceId subscribers subscriptions serviceSubsCount (newSubscription NoSub) rcvServices >>= \case
-                Left e -> pure (err e, Nothing)
-                Right s -> deliver s
+              deliver =<< sharedSubscribeQueue q rcvServiceId subscribers subscriptions serviceSubsCount (newSubscription NoSub) rcvServices
             Just s@Sub {subThread} -> do
               stats <- asks serverStats
               case subThread of
@@ -1711,7 +1705,6 @@ client
             deliver (hasSub, sub_) = do
               stats <- asks serverStats
               fmap (either ((,Nothing) . err) id) $ liftIO $ runExceptT $ do
-                msg_ <- tryPeekMsg ms q
                 msg' <- forM msg_ $ \msg -> liftIO $ do
                   ts <- getSystemSeconds
                   sub <- maybe (atomically getSub) pure sub_
@@ -1797,26 +1790,22 @@ client
                 else liftIO (updateQueueTime (queueStore ms) q t) >>= either (pure . err') (action q)
 
         subscribeNotifications :: StoreQueue s -> NtfCreds -> M s BrokerMsg
-        subscribeNotifications q NtfCreds {ntfServiceId} =
-          sharedSubscribeQueue q SNotifierService ntfServiceId ntfSubscribers ntfSubscriptions ntfServiceSubsCount (pure ()) ntfServices >>= \case
-            Left e -> pure $ ERR e
-            Right (hasSub, _) -> do
-              when (isNothing clntServiceId) $
-                asks serverStats >>= incStat . (if hasSub then ntfSubDuplicate else ntfSub)
-              pure $ SOK clntServiceId
+        subscribeNotifications q NtfCreds {ntfServiceId} = do
+          (hasSub, _) <- sharedSubscribeQueue q ntfServiceId ntfSubscribers ntfSubscriptions ntfServiceSubsCount (pure ()) ntfServices
+          when (isNothing clntServiceId) $
+            asks serverStats >>= incStat . (if hasSub then ntfSubDuplicate else ntfSub)
+          pure $ SOK clntServiceId
 
         sharedSubscribeQueue ::
-          (PartyI p, ServiceParty p) =>
           StoreQueue s ->
-          SParty p ->
           Maybe ServiceId ->
           ServerSubscribers s ->
           (Client s -> TMap QueueId sub) ->
           (Client s -> TVar (Int64, IdsHash)) ->
           STM sub ->
           (ServerStats -> ServiceStats) ->
-          M s (Either ErrorType (Bool, Maybe sub))
-        sharedSubscribeQueue q party queueServiceId srvSubscribers clientSubs clientServiceSubs mkSub servicesSel = do
+          M s (Bool, Maybe sub)
+        sharedSubscribeQueue q queueServiceId srvSubscribers clientSubs clientServiceSubs mkSub servicesSel = do
           stats <- asks serverStats
           let incSrvStat sel = incStat $ sel $ servicesSel stats
               writeSub = writeTQueue (subQ srvSubscribers) (CSClient entId queueServiceId clntServiceId, clientId)
@@ -1830,25 +1819,23 @@ client
                     incSrvStat srvSubCount
                     incSrvStat srvSubQueues
                   incSrvStat srvAssocDuplicate
-                  pure $ Right (hasSub, Nothing)
-              | otherwise -> runExceptT $ do
-                  -- new or updated queue-service association
-                  ExceptT $ setQueueService (queueStore ms) q party (Just serviceId)
+                  pure (hasSub, Nothing)
+              | otherwise -> do
+                  -- association already done in prepareBatchSubs
                   hasSub <- atomically $ (<$ incServiceQueueSubs) =<< hasServiceSub
                   atomically writeSub
-                  liftIO $ do
-                    unless hasSub $ incSrvStat srvSubCount
-                    incSrvStat srvSubQueues
-                    incSrvStat $ maybe srvAssocNew (const srvAssocUpdated) queueServiceId
+                  unless hasSub $ incSrvStat srvSubCount
+                  incSrvStat srvSubQueues
+                  incSrvStat $ maybe srvAssocNew (const srvAssocUpdated) queueServiceId
                   pure (hasSub, Nothing)
               where
                 hasServiceSub = ((0 /=) . fst) <$> readTVar (clientServiceSubs clnt)
                 -- This function is used when queue association with the service is created.
-                incServiceQueueSubs = modifyTVar' (clientServiceSubs clnt) $ addServiceSubs (1, queueIdHash (recipientId q)) -- service count and IDs hash
+                incServiceQueueSubs = modifyTVar' (clientServiceSubs clnt) $ addServiceSubs (1, queueIdHash (recipientId q)) -- service count and IDS hash
             Nothing -> case queueServiceId of
-              Just _ -> runExceptT $ do
-                ExceptT $ setQueueService (queueStore ms) q party Nothing
-                liftIO $ incSrvStat srvAssocRemoved
+              Just _ -> do
+                -- unassociation already done in prepareBatchSubs
+                incSrvStat srvAssocRemoved
                 -- getSubscription may be Just for receiving service, where clientSubs also hold active deliveries for service subscriptions.
                 -- For notification service it can only be Just if storage and session states diverge.
                 r <- atomically $ getSubscription >>= newSub
@@ -1857,7 +1844,7 @@ client
               Nothing -> do
                 r@(hasSub, _) <- atomically $ getSubscription >>= newSub
                 unless hasSub $ atomically writeSub
-                pure $ Right r
+                pure r
               where
                 getSubscription = TM.lookup entId $ clientSubs clnt
                 newSub = \case
@@ -1933,7 +1920,7 @@ client
                   let incSrvStat sel n = liftIO $ atomicModifyIORef'_ (sel $ servicesSel stats) (+ n)
                       diff = fromIntegral $ count' - count
                   if -- `count == -1` only for subscriptions by old NTF servers
-                    | count == -1 && (diff == 0 && idsHash == idsHash') -> incSrvStat srvSubOk 1
+                    | count == -1 || (diff == 0 && idsHash == idsHash') -> incSrvStat srvSubOk 1
                     | diff > 0 -> incSrvStat srvSubMore 1 >> incSrvStat srvSubMoreTotal diff
                     | diff < 0 -> incSrvStat srvSubFewer 1 >> incSrvStat srvSubFewerTotal (- diff)
                     | otherwise -> incSrvStat srvSubDiff 1
@@ -2133,8 +2120,8 @@ client
                   encNMsgMeta = C.cbEncrypt rcvNtfDhSecret ntfNonce (smpEncode msgMeta) 128
               pure $ MsgNtf {ntfMsgId = msgId, ntfTs = msgTs, ntfNonce, ntfEncMeta = fromRight "" encNMsgMeta}
 
-        processForwardedCommand :: EncFwdTransmission -> M s BrokerMsg
-        processForwardedCommand (EncFwdTransmission s) = fmap (either ERR RRES) . runExceptT $ do
+        processForwardedCommand :: EncFwdTransmission -> M s (Maybe BrokerMsg)
+        processForwardedCommand (EncFwdTransmission s) = fmap (either (Just . ERR) id) . runExceptT $ do
           THAuthServer {serverPrivKey, sessSecret'} <- maybe (throwE $ transportErr TENoServerAuth) pure (thAuth thParams')
           sessSecret <- maybe (throwE $ transportErr TENoServerAuth) pure sessSecret'
           let proxyNonce = C.cbNonce $ bs corrId
@@ -2149,28 +2136,31 @@ client
             t :| [] -> pure $ tDecodeServer clntTHParams t
             _ -> throwE BLOCK
           let clntThAuth = Just $ THAuthServer {serverPrivKey, peerClientService = Nothing, sessSecret' = Just clientSecret}
-          -- process forwarded command
-          r <-
-            lift (rejectOrVerify clntThAuth t') >>= \case
-              Left r -> pure r
-              -- rejectOrVerify filters allowed commands, no need to repeat it here.
-              -- INTERNAL is used because processCommand never returns Nothing for sender commands (could be extracted for better types).
-              -- `fst` removes empty message that is only returned for `SUB` command
-              Right t''@(_, (corrId', entId', _)) -> maybe (corrId', entId', ERR INTERNAL) fst <$> lift (processCommand Nothing fwdVersion t'')
-          -- encode response
-          r' <- case batchTransmissions clntTHParams [Right (Nothing, encodeTransmission clntTHParams r)] of
-            [] -> throwE INTERNAL -- at least 1 item is guaranteed from NonEmpty/Right
-            TBError _ _ : _ -> throwE BLOCK
-            TBTransmission b' _ : _ -> pure b'
-            TBTransmissions b' _ _ : _ -> pure b'
-          -- encrypt to client
-          r2 <- liftEitherWith (const BLOCK) $ EncResponse <$> C.cbEncrypt clientSecret (C.reverseNonce clientNonce) r' paddedProxiedTLength
-          -- encrypt to proxy
-          let fr = FwdResponse {fwdCorrId, fwdResponse = r2}
-              r3 = EncFwdResponse $ C.cbEncryptNoPad sessSecret (C.reverseNonce proxyNonce) (smpEncode fr)
+              encodeResp r = do
+                r' <- case batchTransmissions clntTHParams [Right (Nothing, encodeTransmission clntTHParams r)] of
+                  [] -> throwE INTERNAL -- at least 1 item is guaranteed from NonEmpty/Right
+                  TBError _ _ : _ -> throwE BLOCK
+                  TBTransmission b' _ : _ -> pure b'
+                  TBTransmissions b' _ _ : _ -> pure b'
+                r2 <- liftEitherWith (const BLOCK) $ EncResponse <$> C.cbEncrypt clientSecret (C.reverseNonce clientNonce) r' paddedProxiedTLength
+                let fr = FwdResponse {fwdCorrId, fwdResponse = r2}
+                pure $ RRES $ EncFwdResponse $ C.cbEncryptNoPad sessSecret (C.reverseNonce proxyNonce) (smpEncode fr)
+          -- the inner response, or Nothing if forked (RSLV).
+          r_ <- lift (rejectOrVerify clntThAuth t') >>= \case
+            -- rejectOrVerify filters allowed commands, no need to repeat it here.
+            Left r -> pure $ Just r
+            Right t''@(_, (corrId', entId', cmd')) -> case cmd' of
+              Cmd SResolver (RSLV d) -> lift $ rslvNamesEnv >>= \case
+                Nothing -> pure $ Just (corrId', entId', ERR (NAME NO_RESOLVER))
+                Just nenv -> forkCmd serverResolverConcurrency corrId NoEntity $ do
+                  msg <- resolveNameMsg nenv d
+                  either ERR id <$> runExceptT (encodeResp (corrId', entId', msg))
+              -- INTERNAL because processCommand never returns Nothing for sender commands;
+              -- `fst` drops the empty message only returned for SUB.
+              _ -> Just . maybe (corrId', entId', ERR INTERNAL) fst <$> lift (processCommand Nothing fwdVersion (Right (M.empty, M.empty, M.empty)) t'')
           stats <- asks serverStats
           incStat $ pMsgFwdsRecv stats
-          pure r3
+          traverse encodeResp r_
           where
             rejectOrVerify :: Maybe (THandleAuth 'TServer) -> SignedTransmissionOrError ErrorType Cmd -> M s (VerifiedTransmissionOrError s)
             rejectOrVerify clntThAuth = \case
@@ -2184,6 +2174,7 @@ client
                     Cmd SSender (SKEY _) -> True
                     Cmd SSenderLink (LKEY _) -> True
                     Cmd SSenderLink LGET -> True
+                    Cmd SResolver (RSLV _) -> True
                     _ -> False
                   verified = \case
                     VRVerified q -> Right (q, t'')
@@ -2518,4 +2509,4 @@ restoreServerStats msgStats_ ntfStats = asks (serverStatsBackupFile . config) >>
           logNote $ "error restoring server stats: " <> T.pack e
           liftIO exitFailure
     compareCounts name statsCnt storeCnt =
-      when (statsCnt /= storeCnt) $ logWarn $ name <> " count differs: stats: " <> tshow statsCnt <> ", store: " <> tshow storeCnt
+      when (statsCnt /= storeCnt) $ logWarn $ name <> " count differs: stats: " <> tshow statsCnt <> ", store: " <> tshow storeCnt

src/Simplex/Messaging/Server/CLI.hs

@@ -27,6 +27,7 @@ module Simplex.Messaging.Server.CLI
     certOptionsP,
     dbOptsP,
     startOptionsP,
+    parseConfirmMigrations,
     parseLogLevel,
     genOnline,
     warnCAPrivateKeyFile,
@@ -288,12 +289,12 @@ startOptionsP = do
           <> value MCConsole
       )
   pure StartOptions {maintenance, compactLog, logLevel, skipWarnings, confirmMigrations}
-    where
-      parseConfirmMigrations :: ReadM MigrationConfirmation
-      parseConfirmMigrations = eitherReader $ \case
-        "up" -> Right MCYesUp
-        "down" -> Right MCYesUpDown
-        _ -> Left "invalid migration confirmation, pass 'up' or 'down'"
+
+parseConfirmMigrations :: ReadM MigrationConfirmation
+parseConfirmMigrations = eitherReader $ \case
+  "up" -> Right MCYesUp
+  "down" -> Right MCYesUpDown
+  _ -> Left "invalid migration confirmation, pass 'up' or 'down'"
 
 parseLogLevel :: ReadM LogLevel
 parseLogLevel = eitherReader $ \case

src/Simplex/Messaging/Server/Env/STM.hs

@@ -67,6 +67,7 @@ module Simplex.Messaging.Server.Env.STM
     defaultNtfExpiration,
     defaultInactiveClientExpiration,
     defaultProxyClientConcurrency,
+    defaultNameResolverConcurrency,
     defaultMaxJournalMsgCount,
     defaultMaxJournalStateLines,
     defaultIdleQueueInterval,
@@ -115,6 +116,7 @@ import Simplex.Messaging.Server.Information
 import Simplex.Messaging.Server.MsgStore.Journal
 import Simplex.Messaging.Server.MsgStore.STM
 import Simplex.Messaging.Server.MsgStore.Types
+import Simplex.Messaging.Server.Names (NamesConfig (..), NamesEnv, newNamesEnv, pingEndpoint)
 import Simplex.Messaging.Server.NtfStore
 import Simplex.Messaging.Server.QueueStore
 import Simplex.Messaging.Server.QueueStore.Postgres.Config
@@ -128,7 +130,7 @@ import Simplex.Messaging.TMap (TMap)
 import qualified Simplex.Messaging.TMap as TM
 import Simplex.Messaging.Transport (ASrvTransport, SMPVersion, THandleParams, TransportPeer (..), VersionRangeSMP)
 import Simplex.Messaging.Transport.Server
-import Simplex.Messaging.Util (ifM, whenM, ($>>=))
+import Simplex.Messaging.Util (ifM, tshow, whenM, ($>>=))
 import System.Directory (doesFileExist)
 import System.Exit (exitFailure)
 import System.IO (IOMode (..))
@@ -197,6 +199,13 @@ data ServerConfig s = ServerConfig
     smpAgentCfg :: SMPClientAgentConfig,
     allowSMPProxy :: Bool, -- auth is the same with `newQueueBasicAuth`
     serverClientConcurrency :: Int,
+    -- | max concurrent name resolutions per connection, enforced in forkCmd.
+    -- Much higher than serverClientConcurrency: forwarded RSLVs from many clients
+    -- aggregate over a single proxy->relay connection (only servers send proxied
+    -- requests), so bounding them by the per-client limit would throttle unduly.
+    serverResolverConcurrency :: Int,
+    -- | public-namespace resolver config; Nothing disables the names role
+    namesConfig :: Maybe NamesConfig,
     -- | server public information
     information :: Maybe ServerPublicInfo,
     startOptions :: StartOptions
@@ -243,6 +252,9 @@ defaultInactiveClientExpiration =
 defaultProxyClientConcurrency :: Int
 defaultProxyClientConcurrency = 32
 
+defaultNameResolverConcurrency :: Int
+defaultNameResolverConcurrency = 1000
+
 journalMsgStoreDepth :: Int
 journalMsgStoreDepth = 5
 
@@ -272,7 +284,8 @@ data Env s = Env
     serverStats :: ServerStats,
     sockets :: TVar [(ServiceName, SocketState)],
     clientSeq :: TVar ClientId,
-    proxyAgent :: ProxyAgent -- senders served on this proxy
+    proxyAgent :: ProxyAgent, -- senders served on this proxy
+    namesEnv :: Maybe NamesEnv -- public-namespace resolver, present when [NAMES] enable: on
   }
 
 msgStore :: Env s -> s
@@ -558,7 +571,7 @@ newProhibitedSub = do
   return Sub {subThread = ProhibitSub, delivered}
 
 newEnv :: ServerConfig s -> IO (Env s)
-newEnv config@ServerConfig {smpCredentials, httpCredentials, serverStoreCfg, smpAgentCfg, information, messageExpiration, idleQueueInterval, msgQueueQuota, maxJournalMsgCount, maxJournalStateLines} = do
+newEnv config@ServerConfig {smpCredentials, httpCredentials, serverStoreCfg, smpAgentCfg, information, messageExpiration, idleQueueInterval, msgQueueQuota, maxJournalMsgCount, maxJournalStateLines, namesConfig} = do
   serverActive <- newTVarIO True
   server <- newServer
   msgStore_ <- case serverStoreCfg of
@@ -603,6 +616,16 @@ newEnv config@ServerConfig {smpCredentials, httpCredentials, serverStoreCfg, smp
   sockets <- newTVarIO []
   clientSeq <- newTVarIO 0
   proxyAgent <- newSMPProxyAgent smpAgentCfg random
+  namesEnv <- forM namesConfig $ \nc -> do
+    logInfo $ "[NAMES] resolver enabled, endpoint=" <> T.pack (resolverEndpoint nc)
+    env <- newNamesEnv nc
+    -- Probe the endpoint at startup. Don't exitFailure: a flapping network or a
+    -- resolver host coming up minutes after smp-server should not block the
+    -- server. Log so operators can spot it.
+    pingEndpoint env >>= \case
+      Right _ -> logInfo "[NAMES] endpoint probe ok"
+      Left e -> logWarn $ "[NAMES] endpoint probe failed (server will still start, RSLV will return ERR (NAME ...) until reachable): " <> tshow e
+    pure env
   pure
     Env
       { serverActive,
@@ -618,7 +641,8 @@ newEnv config@ServerConfig {smpCredentials, httpCredentials, serverStoreCfg, smp
         serverStats,
         sockets,
         clientSeq,
-        proxyAgent
+        proxyAgent,
+        namesEnv
       }
   where
     loadStoreLog :: StoreQueueClass q => (RecipientId -> QueueRec -> IO q) -> FilePath -> STMQueueStore q -> IO ()

src/Simplex/Messaging/Server/Main.hs

@@ -34,6 +34,7 @@ module Simplex.Messaging.Server.Main
     simplexmqSource,
     serverPublicInfo,
     validCountryValue,
+    validateUrl,
     printSourceCode,
     cliCommandP,
     strParse,
@@ -50,7 +51,7 @@ import Data.Char (isAlpha, isAscii, toUpper)
 import Data.Either (fromRight)
 import Data.Functor (($>))
 import Data.Ini (Ini, lookupValue, readIniFile)
-import Data.List (find, isPrefixOf)
+import Data.List (dropWhileEnd, find, isPrefixOf)
 import qualified Data.List.NonEmpty as L
 import Data.Maybe (fromMaybe, isJust, isNothing)
 import Data.Text (Text)
@@ -66,6 +67,7 @@ import Simplex.Messaging.Client.Agent (SMPClientAgentConfig (..), defaultSMPClie
 import qualified Simplex.Messaging.Crypto as C
 import Simplex.Messaging.Encoding.String
 import Simplex.Messaging.Parsers (parseAll)
+import Network.URI (URI (..), URIAuth (..), parseAbsoluteURI)
 import Simplex.Messaging.Protocol (BasicAuth (..), ProtoServerWithAuth (ProtoServerWithAuth), pattern SMPServer)
 import Simplex.Messaging.Server (AttachHTTP, exportMessages, importMessages, printMessageStats, runSMPServer)
 import Simplex.Messaging.Server.CLI
@@ -76,6 +78,7 @@ import Simplex.Messaging.Server.Main.Init
 import Simplex.Messaging.Server.Web (EmbeddedWebParams (..), WebHttpsParams (..))
 import Simplex.Messaging.Server.MsgStore.Journal (JournalMsgStore (..), QStoreCfg (..), stmQueueStore)
 import Simplex.Messaging.Server.MsgStore.Types (MsgStoreClass (..), SQSType (..), SMSType (..), newMsgStore)
+import Simplex.Messaging.Server.Names (NamesConfig (..), RpcAuth (..))
 import Simplex.Messaging.Server.QueueStore.Postgres.Config
 import Simplex.Messaging.Server.StoreLog.ReadWrite (readQueueStore)
 import Simplex.Messaging.Transport (supportedProxyClientSMPRelayVRange, alpnSupportedSMPHandshakes, supportedServerSMPRelayVRange)
@@ -601,10 +604,13 @@ smpServerCLI_ generateSite serveStaticFiles attachStaticFiles cfgPath logPath =
                               }
                         },
                     ownServerDomains = either (const []) textToOwnServers $ lookupValue "PROXY" "own_server_domains" ini,
+                    msgQSize = Nothing, -- to prevent accumulation of late responses, and deadlocks in SMP proxy
                     persistErrorInterval = 30 -- seconds
                   },
               allowSMPProxy = True,
               serverClientConcurrency = readIniDefault defaultProxyClientConcurrency "PROXY" "client_concurrency" ini,
+              serverResolverConcurrency = readIniDefault defaultNameResolverConcurrency "NAMES" "resolver_concurrency" ini,
+              namesConfig = readNamesConfig ini,
               information = serverPublicInfo ini,
               startOptions
             }
@@ -796,6 +802,64 @@ validCountryValue field s
   | length s == 2 && all (\c -> isAscii c && isAlpha c) s = Right $ T.pack $ map toUpper s
   | otherwise = Left $ "Use ISO3166 2-letter code for " <> field
 
+readNamesConfig :: Ini -> Maybe NamesConfig
+readNamesConfig ini
+  | not enabled = Nothing
+  | otherwise =
+      let resolverAuth_ = either (error . ("[NAMES] resolver_auth: " <>)) Just . parseRpcAuth =<< eitherToMaybe (lookupValue "NAMES" "resolver_auth" ini)
+          endpoint = requiredText "resolver_endpoint"
+       in Just
+            NamesConfig
+              { resolverEndpoint = either (error . ("[NAMES] resolver_endpoint: " <>)) id (validateUrl endpoint resolverAuth_),
+                resolverAuth = resolverAuth_,
+                resolverTimeoutMs = boundedIniInt 3000 100 60000 "resolver_timeout_ms",
+                resolverMaxResponseBytes = boundedIniInt 16000 1024 16000 "resolver_max_response_bytes"
+              }
+  where
+    enabled = fromMaybe False (iniOnOff "NAMES" "enable" ini)
+    requiredText key =
+      either (error . (("[NAMES] " <> T.unpack key <> " is required: ") <>)) id $
+        lookupValue "NAMES" key ini
+    boundedIniInt def floor_ ceiling_ key = case lookupValue "NAMES" key ini of
+      Left _ -> def
+      Right raw -> case readMaybe (T.unpack (T.strip raw)) of
+        Nothing ->
+          error $ "[NAMES] " <> T.unpack key <> ": not an integer (got " <> show raw <> ")"
+        Just n
+          | n >= floor_ && n <= ceiling_ -> n
+          | otherwise ->
+              error $ "[NAMES] " <> T.unpack key <> " must be in [" <> show floor_ <> ".." <> show ceiling_ <> "] (got " <> show n <> ")"
+
+-- | Validate the resolver_endpoint URL: it must be an absolute http(s) URL with a host.
+-- http + resolver_auth to a non-loopback host is rejected.
+validateUrl :: Text -> Maybe RpcAuth -> Either String String
+validateUrl url auth_ = do
+  let s = T.unpack url
+  uri <- maybe (Left "not an absolute URI") Right $ parseAbsoluteURI s
+  let scheme = uriScheme uri
+  unless (scheme == "http:" || scheme == "https:") $ Left "scheme must be http or https"
+  ua <- maybe (Left "missing host") Right (uriAuthority uri)
+  let host = uriRegName ua
+  when (null host) $ Left "empty host"
+  unless (null (uriUserInfo ua)) $ Left "userinfo (user:pass@) not allowed; put credentials in resolver_auth"
+  when (scheme == "http:" && isJust auth_ && not (isLoopback host)) $
+    Left "http with resolver_auth on a non-loopback host not allowed (the Authorization header would travel in cleartext); use https, or drop resolver_auth"
+  Right (dropWhileEnd (== '/') s)
+  where
+    isLoopback h = h == "localhost" || h == "127.0.0.1" || h == "[::1]" || h == "0.0.0.0"
+
+-- | Parse an rpc_auth INI value. Scheme keyword is case-insensitive so
+-- "Bearer <token>" / "BEARER <token>" (Caddy / RFC 7235 convention) work
+-- as well as the lowercase form.
+parseRpcAuth :: Text -> Either String RpcAuth
+parseRpcAuth t = case T.words t of
+  [scheme, tok] | T.toLower scheme == "bearer" -> Right $ AuthBearer tok
+  [scheme, up] | T.toLower scheme == "basic" -> case T.breakOn ":" up of
+    (u, rest)
+      | not (T.null u) && ":" `T.isPrefixOf` rest -> Right $ AuthBasic u (T.drop 1 rest)
+    _ -> Left "basic auth expects user:password"
+  _ -> Left "expected `bearer <token>` or `basic <user>:<pass>`"
+
 printSourceCode :: Maybe Text -> IO ()
 printSourceCode = \case
   Just sourceCode -> T.putStrLn $ "Server source code: " <> sourceCode

src/Simplex/Messaging/Server/Main/Init.hs

@@ -78,101 +78,117 @@ iniFileContent cfgPath logPath opts host basicAuth controlPortPwds =
   informationIniContent opts
     <> "[STORE_LOG]\n\
         \# The server uses memory or PostgreSQL database for persisting queue records.\n\
-        \# Use `enable: on` to use append-only log to preserve and restore queue records on restart.\n\
+        \# Use `enable = on` to use append-only log to preserve and restore queue records on restart.\n\
         \# Log is compacted on start (deleted objects are removed).\n"
-    <> ("enable: " <> onOff enableStoreLog <> "\n\n")
+    <> ("enable = " <> onOff enableStoreLog <> "\n\n")
     <> "# Queue storage mode: `memory` or `database` (to store queue records in PostgreSQL database).\n\
-        \# `memory` - in-memory persistence, with optional append-only log (`enable: on`).\n\
-        \# `database`- PostgreSQL databass (requires `store_messages: journal`).\n\
-        \store_queues: memory\n\n\
-        \# Database connection settings for PostgreSQL database (`store_queues: database`).\n"
+        \# `memory` - in-memory persistence, with optional append-only log (`enable = on`).\n\
+        \# `database`- PostgreSQL databass (requires `store_messages = journal`).\n\
+        \store_queues = memory\n\n\
+        \# Database connection settings for PostgreSQL database (`store_queues = database`).\n"
     <> iniDbOpts dbOptions defaultDBOpts
     <> "# Write database changes to store log file\n\
-        \# db_store_log: off\n\n\
+        \# db_store_log = off\n\n\
         \# Time to retain deleted queues in the database, days.\n"
-    <> ("# db_deleted_ttl: " <> tshow defaultDeletedTTL <> "\n\n")
+    <> ("# db_deleted_ttl = " <> tshow defaultDeletedTTL <> "\n\n")
     <> "# Message storage mode: `memory` or `journal`.\n\
-        \store_messages: memory\n\n\
+        \store_messages = memory\n\n\
         \# When store_messages is `memory`, undelivered messages are optionally saved and restored\n\
         \# when the server restarts, they are preserved in the .bak file until the next restart.\n"
-    <> ("restore_messages: " <> onOff enableStoreLog <> "\n\n")
+    <> ("restore_messages = " <> onOff enableStoreLog <> "\n\n")
     <> "# Messages and notifications expiration periods.\n"
-    <> ("expire_messages_days: " <> tshow defMsgExpirationDays <> "\n")
-    <> "expire_messages_on_start: on\n\
-        \expire_messages_on_send: off\n"
-    <> ("expire_ntfs_hours: " <> tshow defNtfExpirationHours <> "\n\n")
+    <> ("expire_messages_days = " <> tshow defMsgExpirationDays <> "\n")
+    <> "expire_messages_on_start = on\n\
+        \expire_messages_on_send = off\n"
+    <> ("expire_ntfs_hours = " <> tshow defNtfExpirationHours <> "\n\n")
     <> "# Log daily server statistics to CSV file\n"
-    <> ("log_stats: " <> onOff logStats <> "\n\n")
+    <> ("log_stats = " <> onOff logStats <> "\n\n")
     <> "# Log interval for real-time Prometheus metrics\n\
-        \# prometheus_interval: 60\n\n\
+        \# prometheus_interval = 60\n\n\
         \[AUTH]\n\
         \# Set new_queues option to off to completely prohibit creating new messaging queues.\n\
         \# This can be useful when you want to decommission the server, but not all connections are switched yet.\n\
-        \new_queues: on\n\n\
+        \new_queues = on\n\n\
         \# Use create_password option to enable basic auth to create new messaging queues.\n\
         \# The password should be used as part of server address in client configuration:\n\
         \# smp://fingerprint:password@host1,host2\n\
         \# The password will not be shared with the connecting contacts, you must share it only\n\
         \# with the users who you want to allow creating messaging queues on your server.\n"
     <> ( let noPassword = "password to create new queues and forward messages (any printable ASCII characters without whitespace, '@', ':' and '/')"
-          in optDisabled basicAuth <> "create_password: " <> maybe noPassword (safeDecodeUtf8 . strEncode) basicAuth
+          in optDisabled basicAuth <> "create_password = " <> maybe noPassword (safeDecodeUtf8 . strEncode) basicAuth
         )
     <> "\n\n"
-    <> (optDisabled controlPortPwds <> "control_port_admin_password: " <> maybe "" fst controlPortPwds <> "\n")
-    <> (optDisabled controlPortPwds <> "control_port_user_password: " <> maybe "" snd controlPortPwds <> "\n\n")
+    <> (optDisabled controlPortPwds <> "control_port_admin_password = " <> maybe "" fst controlPortPwds <> "\n")
+    <> (optDisabled controlPortPwds <> "control_port_user_password = " <> maybe "" snd controlPortPwds <> "\n\n")
     <> "# The limit for queues that can be blocked via control port per day, resets at 0:00 UTC.\n\
         \# Set to 0 to disable limit, to -1 to prohibit blocking. Default is 20.\n\
-        \# daily_block_queue_quota: 20\n\
+        \# daily_block_queue_quota = 20\n\
         \\n\
         \[TRANSPORT]\n\
         \# Host is only used to print server address on start.\n\
         \# You can specify multiple server ports.\n"
-    <> ("host: " <> T.pack host <> "\n")
-    <> ("port: " <> defaultServerPorts <> "\n")
-    <> "log_tls_errors: off\n\n\
-        \# Use `websockets: 443` to run websockets server in addition to plain TLS.\n\
+    <> ("host = " <> T.pack host <> "\n")
+    <> ("port = " <> defaultServerPorts <> "\n")
+    <> "log_tls_errors = off\n\n\
+        \# Use `websockets = 443` to run websockets server in addition to plain TLS.\n\
         \# This option is deprecated and should be used for testing only.\n\
         \# , port 443 should be specified in port above\n\
-        \websockets: off\n"
-    <> (optDisabled controlPort <> "control_port: " <> tshow (fromMaybe defaultControlPort controlPort))
+        \websockets = off\n"
+    <> (optDisabled controlPort <> "control_port = " <> tshow (fromMaybe defaultControlPort controlPort))
     <> "\n\n\
         \[PROXY]\n\
         \# Network configuration for SMP proxy client.\n\
         \# `host_mode` can be 'public' (default) or 'onion'.\n\
         \# It defines prefferred hostname for destination servers with multiple hostnames.\n\
-        \# host_mode: public\n\
-        \# required_host_mode: off\n\n\
+        \# host_mode = public\n\
+        \# required_host_mode = off\n\n\
         \# The domain suffixes of the relays you operate (space-separated) to count as separate proxy statistics.\n"
-    <> (optDisabled ownDomains <> "own_server_domains: " <> maybe "" (safeDecodeUtf8 . strEncode) ownDomains)
+    <> (optDisabled ownDomains <> "own_server_domains = " <> maybe "" (safeDecodeUtf8 . strEncode) ownDomains)
     <> "\n\n\
         \# SOCKS proxy port for forwarding messages to destination servers.\n\
         \# You may need a separate instance of SOCKS proxy for incoming single-hop requests.\n"
-    <> (optDisabled socksProxy <> "socks_proxy: " <> maybe "localhost:9050" (safeDecodeUtf8 . strEncode) socksProxy)
+    <> (optDisabled socksProxy <> "socks_proxy = " <> maybe "localhost:9050" (safeDecodeUtf8 . strEncode) socksProxy)
     <> "\n\n\
         \# `socks_mode` can be 'onion' for SOCKS proxy to be used for .onion destination hosts only (default)\n\
         \# or 'always' to be used for all destination hosts (can be used if it is an .onion server).\n\
-        \# socks_mode: onion\n\n\
+        \# socks_mode = onion\n\n\
         \# Limit number of threads a client can spawn to process proxy commands in parrallel.\n"
-    <> ("# client_concurrency: " <> tshow defaultProxyClientConcurrency)
+    <> ("# client_concurrency = " <> tshow defaultProxyClientConcurrency)
+    <> "\n\n\
+        \[NAMES]\n\
+        \# Public-namespace resolution via the snrc-resolve.py REST resolver.\n\
+        \# Operator runs the resolver alongside smp-server (default port 8000)\n\
+        \# with its own Ethereum JSON-RPC endpoint configured in resolver.toml.\n\
+        \enable: off\n\
+        \# Same-host:\n\
+        \# resolver_endpoint: http://127.0.0.1:8000\n\
+        \# Resolver behind TLS reverse proxy:\n\
+        \# resolver_endpoint: https://names.simplex.chat:443\n\
+        \# resolver_auth: basic <username>:<password>\n\
+        \# resolver_timeout_ms: 3000\n\
+        \# resolver_max_response_bytes: 16000\n\
+        \# Max concurrent name resolutions per connection (forwarded RSLVs from many\n\
+        \# clients share one proxy connection, so this is much higher than PROXY client_concurrency).\n"
+    <> ("# resolver_concurrency = " <> tshow defaultNameResolverConcurrency)
     <> "\n\n\
         \[INACTIVE_CLIENTS]\n\
         \# TTL and interval to check inactive clients\n\
-        \disconnect: on\n"
-    <> ("ttl: " <> tshow (ttl defaultInactiveClientExpiration) <> "\n")
-    <> ("check_interval: " <> tshow (checkInterval defaultInactiveClientExpiration))
+        \disconnect = on\n"
+    <> ("ttl = " <> tshow (ttl defaultInactiveClientExpiration) <> "\n")
+    <> ("check_interval = " <> tshow (checkInterval defaultInactiveClientExpiration))
     <> "\n\n\
         \[WEB]\n\
         \# Set path to generate static mini-site for server information and qr codes/links\n"
-    <> ("static_path: " <> T.pack (fromMaybe defaultStaticPath webStaticPath) <> "\n\n")
+    <> ("static_path = " <> T.pack (fromMaybe defaultStaticPath webStaticPath) <> "\n\n")
     <> "# Run an embedded server on this port\n\
         \# Onion sites can use any port and register it in the hidden service config.\n\
         \# Running on a port 80 may require setting process capabilities.\n\
-        \# http: 8000\n\n\
+        \# http = 8000\n\n\
         \# You can run an embedded TLS web server too if you provide port and cert and key files.\n\
         \# Not required for running relay on onion address.\n"
-    <> (webDisabled <> "https: 443\n")
-    <> (webDisabled <> "cert: " <> T.pack httpsCertFile <> "\n")
-    <> (webDisabled <> "key: " <> T.pack httpsKeyFile <> "\n")
+    <> (webDisabled <> "https = 443\n")
+    <> (webDisabled <> "cert = " <> T.pack httpsCertFile <> "\n")
+    <> (webDisabled <> "key = " <> T.pack httpsKeyFile <> "\n")
   where
     InitOptions {enableStoreLog, dbOptions, socksProxy, ownDomains, controlPort, webStaticPath, disableWeb, logStats} = opts
     defaultServerPorts = "5223,443"
@@ -189,53 +205,53 @@ informationIniContent InitOptions {sourceCode, serverInfo} =
   \# LICENSE: https://github.com/simplex-chat/simplexmq/blob/stable/LICENSE\n\
   \# Include correct source code URI in case the server source code is modified in any way.\n\
   \# If any other information fields are present, source code property also MUST be present.\n\n"
-    <> (optDisabled sourceCode <> "source_code: " <> fromMaybe "URI" sourceCode)
+    <> (optDisabled sourceCode <> "source_code = " <> fromMaybe "URI" sourceCode)
     <> "\n\n\
        \# Declaring all below information is optional, any of these fields can be omitted.\n\
        \\n\
        \# Server usage conditions and amendments.\n\
        \# It is recommended to use standard conditions with any amendments in a separate document.\n\
-       \# usage_conditions: https://github.com/simplex-chat/simplex-chat/blob/stable/PRIVACY.md\n\
-       \# condition_amendments: link\n\
+       \# usage_conditions = https://github.com/simplex-chat/simplex-chat/blob/stable/PRIVACY.md\n\
+       \# condition_amendments = link\n\
        \\n\
        \# Server location and operator.\n"
     <> countryStr "server" serverCountry
     <> enitiyStrs "operator" operator
-    <> (optDisabled website <> "website: " <> fromMaybe "" website)
+    <> (optDisabled website <> "website = " <> fromMaybe "" website)
     <> "\n\n\
        \# Administrative contacts.\n\
-       \# admin_simplex: SimpleX address\n\
-       \# admin_email:\n\
-       \# admin_pgp:\n\
-       \# admin_pgp_fingerprint:\n\
+       \# admin_simplex = SimpleX address\n\
+       \# admin_email =\n\
+       \# admin_pgp =\n\
+       \# admin_pgp_fingerprint =\n\
        \\n\
        \# Contacts for complaints and feedback.\n\
-       \# complaints_simplex: SimpleX address\n\
-       \# complaints_email:\n\
-       \# complaints_pgp:\n\
-       \# complaints_pgp_fingerprint:\n\
+       \# complaints_simplex = SimpleX address\n\
+       \# complaints_email =\n\
+       \# complaints_pgp =\n\
+       \# complaints_pgp_fingerprint =\n\
        \\n\
        \# Hosting provider.\n"
     <> enitiyStrs "hosting" hosting
     <> "\n\
        \# Hosting type can be `virtual`, `dedicated`, `colocation`, `owned`\n"
-    <> ("hosting_type: " <> maybe "virtual" (decodeLatin1 . strEncode) hostingType <> "\n\n")
+    <> ("hosting_type = " <> maybe "virtual" (decodeLatin1 . strEncode) hostingType <> "\n\n")
   where
     ServerPublicInfo {operator, website, hosting, hostingType, serverCountry} = serverInfo
-    countryStr optName country = optDisabled country <> optName <> "_country: " <> fromMaybe "ISO-3166 2-letter code" country <> "\n"
+    countryStr optName country = optDisabled country <> optName <> "_country = " <> fromMaybe "ISO-3166 2-letter code" country <> "\n"
     enitiyStrs optName entity =
       optDisabled entity
         <> optName
-        <> ": "
+        <> " = "
         <> maybe "entity (organization or person name)" name entity
         <> "\n"
         <> countryStr optName (country =<< entity)
 
 iniDbOpts :: DBOpts -> DBOpts -> Text
 iniDbOpts DBOpts {connstr, schema, poolSize} DBOpts {connstr = defConnstr, schema = defSchema, poolSize = defPoolSize} =
-  (optDisabled' (connstr == defConnstr) <> "db_connection: " <> safeDecodeUtf8 connstr <> "\n")
-    <> (optDisabled' (schema == defSchema) <> "db_schema: " <> safeDecodeUtf8 schema <> "\n")
-    <> (optDisabled' (poolSize == defPoolSize) <> "db_pool_size: " <> tshow poolSize <> "\n\n")
+  (optDisabled' (connstr == defConnstr) <> "db_connection = " <> safeDecodeUtf8 connstr <> "\n")
+    <> (optDisabled' (schema == defSchema) <> "db_schema = " <> safeDecodeUtf8 schema <> "\n")
+    <> (optDisabled' (poolSize == defPoolSize) <> "db_pool_size = " <> tshow poolSize <> "\n\n")
 
 optDisabled :: Maybe a -> Text
 optDisabled = optDisabled' . isNothing

src/Simplex/Messaging/Server/MsgStore/Journal.hs

@@ -353,6 +353,8 @@ instance QueueStoreClass (JournalQueue s) (QStore s) where
   {-# INLINE getCreateService #-}
   setQueueService = withQS setQueueService
   {-# INLINE setQueueService #-}
+  setQueueServices = withQS setQueueServices
+  {-# INLINE setQueueServices #-}
   getQueueNtfServices = withQS (getQueueNtfServices @(JournalQueue s))
   {-# INLINE getQueueNtfServices #-}
   getServiceQueueCountHash = withQS (getServiceQueueCountHash @(JournalQueue s))

src/Simplex/Messaging/Server/MsgStore/Postgres.hs

@@ -41,7 +41,7 @@ import Data.List (intersperse)
 import qualified Data.Map.Strict as M
 import Data.Text (Text)
 import Data.Time.Clock.System (SystemTime (..))
-import Database.PostgreSQL.Simple (Binary (..), Only (..), (:.) (..))
+import Database.PostgreSQL.Simple (Binary (..), In (..), Only (..), (:.) (..))
 import qualified Database.PostgreSQL.Simple as DB
 import qualified Database.PostgreSQL.Simple.Copy as DB
 import Database.PostgreSQL.Simple.SqlQQ (sql)
@@ -246,6 +246,25 @@ instance MsgStoreClass PostgresMsgStore where
   tryPeekMsg ms q = isolateQueue ms q "tryPeekMsg" $ tryPeekMsg_ q ()
   {-# INLINE tryPeekMsg #-}
 
+  tryPeekMsgs :: PostgresMsgStore -> [PostgresQueue] -> ExceptT ErrorType IO (M.Map RecipientId Message)
+  tryPeekMsgs _ms [] = pure M.empty
+  tryPeekMsgs ms qs =
+    uninterruptibleMask_ $
+      withDB' "tryPeekMsgs" (queueStore_ ms) $ \db ->
+        M.fromList . map toRcvMsg <$>
+          DB.query
+            db
+            [sql|
+              SELECT DISTINCT ON (recipient_id)
+                recipient_id, msg_id, msg_ts, msg_quota, msg_ntf_flag, msg_body
+              FROM messages
+              WHERE recipient_id IN ?
+              ORDER BY recipient_id, message_id ASC
+            |]
+            (Only (In (map recipientId' qs)))
+    where
+      toRcvMsg (Only rId :. msg) = (rId, toMessage msg)
+
   tryDelMsg :: PostgresMsgStore -> PostgresQueue -> MsgId -> ExceptT ErrorType IO (Maybe Message)
   tryDelMsg ms q msgId =
     uninterruptibleMask_ $

src/Simplex/Messaging/Server/MsgStore/Types.hs

@@ -41,7 +41,9 @@ import Control.Monad.Trans.Except
 import Data.Functor (($>))
 import Data.Int (Int64)
 import Data.Kind
-import Data.Maybe (fromMaybe)
+import Data.Map.Strict (Map)
+import qualified Data.Map.Strict as M
+import Data.Maybe (catMaybes, fromMaybe)
 import Data.Text (Text)
 import Data.Time.Clock.System (SystemTime (systemSeconds))
 import Simplex.Messaging.Protocol
@@ -91,6 +93,9 @@ class (Monad (StoreMonad s), QueueStoreClass (StoreQueue s) (QueueStore s)) => M
   tryPeekMsg :: s -> StoreQueue s -> ExceptT ErrorType IO (Maybe Message)
   tryPeekMsg st q = snd <$$> withPeekMsgQueue st q "tryPeekMsg" pure
   {-# INLINE tryPeekMsg #-}
+  
+  tryPeekMsgs :: s -> [StoreQueue s] -> ExceptT ErrorType IO (Map RecipientId Message)
+  tryPeekMsgs st qs = M.fromList . catMaybes <$> mapM (\q -> (recipientId q,) <$$> tryPeekMsg st q) qs
 
   tryDelMsg :: s -> StoreQueue s -> MsgId -> ExceptT ErrorType IO (Maybe Message)
   tryDelMsg st q msgId' =

src/Simplex/Messaging/Server/Names.hs

@@ -0,0 +1,84 @@
+{-# LANGUAGE LambdaCase #-}
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE ScopedTypeVariables #-}
+{-# LANGUAGE StrictData #-}
+
+module Simplex.Messaging.Server.Names
+  ( NamesConfig (..),
+    RpcAuth (..),
+    NamesEnv (..),
+    newNamesEnv,
+    closeNamesEnv,
+    pingEndpoint,
+    resolveName,
+  )
+where
+
+import qualified Control.Exception as E
+import Control.Logger.Simple (logError)
+import Data.Bifunctor (first)
+import Data.Maybe (fromMaybe)
+import qualified Data.Text as T
+import Simplex.Messaging.Protocol (NameErrorType (..), NameRecord)
+import Simplex.Messaging.Server.Names.HttpResolver
+  ( ResolverEnv,
+    ResolverError (..),
+    RpcAuth (..),
+    closeResolverEnv,
+    healthHttp,
+    newResolverEnv,
+    resolveHttp,
+  )
+import Simplex.Messaging.SimplexName (SimplexDomain, fullDomainName)
+import System.Timeout (timeout)
+
+data NamesConfig = NamesConfig
+  { resolverEndpoint :: String,
+    resolverAuth :: Maybe RpcAuth,
+    resolverTimeoutMs :: Int,
+    resolverMaxResponseBytes :: Int
+  }
+  deriving (Show)
+
+data NamesEnv = NamesEnv
+  { config :: NamesConfig,
+    resolverEnv :: ResolverEnv
+  }
+
+newNamesEnv :: NamesConfig -> IO NamesEnv
+newNamesEnv config = do
+  resolverEnv <- newResolverEnv (resolverEndpoint config) (resolverAuth config) (resolverTimeoutMs config) (resolverMaxResponseBytes config)
+  pure NamesEnv {config, resolverEnv}
+
+closeNamesEnv :: NamesEnv -> IO ()
+closeNamesEnv NamesEnv {resolverEnv} = closeResolverEnv resolverEnv
+
+pingEndpoint :: NamesEnv -> IO (Either ResolverError ())
+pingEndpoint NamesEnv {resolverEnv, config} =
+  fromMaybe (Left ResolverTimeout) <$> timeout (resolverTimeoutMs config * 1000) (healthHttp resolverEnv)
+
+resolveName :: NamesEnv -> SimplexDomain -> IO (Either NameErrorType NameRecord)
+resolveName env d = do
+  r <- E.try (timeout (resolverTimeoutMs (config env) * 1000) (fetch env d))
+  case r of
+    Right result -> pure (fromMaybe (Left (RESOLVER "timeout")) result)
+    Left e
+      | Just (_ :: E.SomeAsyncException) <- E.fromException e -> E.throwIO e
+      | otherwise -> do
+          logError $ "[NAMES] resolver fetch raised " <> T.pack (E.displayException e)
+          pure (Left (RESOLVER "resolver error"))
+
+fetch :: NamesEnv -> SimplexDomain -> IO (Either NameErrorType NameRecord)
+fetch NamesEnv {resolverEnv} d =
+  first mapResolverError <$> resolveHttp resolverEnv (fullDomainName d)
+
+mapResolverError :: ResolverError -> NameErrorType
+mapResolverError = \case
+  HttpStatusErr 404 -> NOT_FOUND
+  HttpStatusErr 400 -> NOT_FOUND
+  HttpStatusErr code -> RESOLVER ("HTTP " <> T.pack (show code))
+  HttpFailure _ -> RESOLVER "transport failure"
+  BodyTooLarge -> RESOLVER "response too large"
+  InvalidJson _ -> RESOLVER "invalid response"
+  ResolverTimeout -> RESOLVER "timeout"

src/Simplex/Messaging/Server/Names/HttpResolver.hs

@@ -0,0 +1,144 @@
+{-# LANGUAGE LambdaCase #-}
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE ScopedTypeVariables #-}
+{-# LANGUAGE StrictData #-}
+
+-- | HTTP transport for the public-namespace resolver.
+--
+-- The Python REST resolver (see scripts/resolver/snrc-resolve.py) exposes
+--
+--   GET /resolve/<name>   -> 200 with a NameRecord JSON document
+--                            404 / 400 for unknown names / TLDs
+--                            502 for upstream RPC failures
+--   GET /health           -> 200 when the resolver process is ready
+--
+-- Boundary properties:
+--   * Response body read with `brReadSome maxResponseBytes` — adversarial
+--     endpoints cannot exhaust memory with multi-GB bodies.
+--   * `redirectCount = 0` — a compromised resolver cannot bounce credentials
+--     to a private-IP target (SSRF amplification on top of the URL validation
+--     performed at config load in Server.Main.validateUrl).
+--   * Authorization header attached only when configured.
+module Simplex.Messaging.Server.Names.HttpResolver
+  ( RpcAuth (..),
+    ResolverEnv,
+    ResolverError (..),
+    newResolverEnv,
+    closeResolverEnv,
+    resolveHttp,
+    healthHttp,
+  )
+where
+
+import qualified Control.Exception as E
+import qualified Data.Aeson as J
+import Data.Bifunctor (first)
+import qualified Data.ByteArray.Encoding as BAE
+import Data.ByteString.Char8 (ByteString)
+import qualified Data.ByteString.Char8 as B
+import qualified Data.ByteString.Lazy as BL
+import Data.Text (Text)
+import Data.Text.Encoding (encodeUtf8)
+import Network.HTTP.Client
+  ( HttpException,
+    Manager,
+    ManagerSettings (..),
+    brReadSome,
+    parseRequest,
+    redirectCount,
+    requestHeaders,
+    responseBody,
+    responseStatus,
+    responseTimeoutMicro,
+    withResponse,
+  )
+import qualified Network.HTTP.Client as HC
+import Network.HTTP.Client.TLS (tlsManagerSettings)
+import qualified Network.HTTP.Types as HT
+import Network.HTTP.Types.URI (urlEncode)
+import Simplex.Messaging.Names.Record (NameRecord)
+
+data RpcAuth = AuthBearer Text | AuthBasic Text Text
+
+-- | Redacts the bearer token / basic-auth password so an accidental
+-- `show` / `tshow` on NamesConfig never lands secrets in logs.
+instance Show RpcAuth where
+  show (AuthBearer _) = "AuthBearer <redacted>"
+  show (AuthBasic u _) = "AuthBasic " <> show u <> " <redacted>"
+
+data ResolverEnv = ResolverEnv
+  { manager :: Manager,
+    baseUrl :: String,
+    authHdr :: [HT.Header],
+    timeoutMicro :: Int,
+    maxResponseBytes :: Int
+  }
+
+data ResolverError
+  = HttpFailure HttpException
+  | HttpStatusErr Int
+  | BodyTooLarge
+  | InvalidJson String
+  | ResolverTimeout
+  deriving (Show)
+
+newResolverEnv :: String -> Maybe RpcAuth -> Int -> Int -> IO ResolverEnv
+newResolverEnv baseUrl auth_ timeoutMs maxResponseBytes = do
+  manager <- HC.newManager tlsManagerSettings {managerConnCount = 10}
+  pure
+    ResolverEnv
+      { manager,
+        baseUrl,
+        authHdr = maybe [] (pure . authHeader) auth_,
+        timeoutMicro = timeoutMs * 1000,
+        maxResponseBytes
+      }
+
+-- | http-client's `closeManager` is a deprecated no-op since 0.5; the
+-- manager is released by the GC finalizer on its internal state. Hook kept
+-- as a future-cleanup seam.
+closeResolverEnv :: ResolverEnv -> IO ()
+closeResolverEnv _ = pure ()
+
+authHeader :: RpcAuth -> HT.Header
+authHeader = \case
+  AuthBearer tok -> ("Authorization", "Bearer " <> encodeUtf8 tok)
+  AuthBasic u p ->
+    let encoded = BAE.convertToBase BAE.Base64 (encodeUtf8 u <> ":" <> encodeUtf8 p) :: ByteString
+     in ("Authorization", "Basic " <> encoded)
+
+-- | GET <baseUrl>/resolve/<percent-encoded name>, decoding the 200 body
+-- directly into a NameRecord in one pass (no intermediate Aeson Value). The
+-- name is percent-encoded (every non-unreserved byte per RFC 3986): the
+-- resolver expects raw labels, so slashes/punctuation must not alter the path.
+resolveHttp :: ResolverEnv -> Text -> IO (Either ResolverError NameRecord)
+resolveHttp env name =
+  (>>= first InvalidJson . J.eitherDecodeStrict . BL.toStrict)
+    <$> httpGet env ("/resolve/" <> B.unpack (urlEncode True (encodeUtf8 name)))
+
+-- | GET <baseUrl>/health; success = reachable with status < 400. The body is
+-- size-capped but NOT decoded — the probe only checks reachability.
+healthHttp :: ResolverEnv -> IO (Either ResolverError ())
+healthHttp env = (() <$) <$> httpGet env "/health"
+
+-- | GET <baseUrl><path>, returning the response body bytes on status < 400
+-- within the size cap. Redirects are disabled and Authorization is attached
+-- only when configured.
+httpGet :: ResolverEnv -> String -> IO (Either ResolverError BL.ByteString)
+httpGet ResolverEnv {manager, baseUrl, authHdr, timeoutMicro, maxResponseBytes} path = do
+  req0 <- parseRequest (baseUrl <> path)
+  let req =
+        req0
+          { redirectCount = 0,
+            requestHeaders = ("Accept", "application/json") : authHdr,
+            HC.responseTimeout = responseTimeoutMicro timeoutMicro
+          }
+  result <- E.try $ withResponse req manager $ \res -> do
+    let status = HT.statusCode (responseStatus res)
+    if status >= 400
+      then pure (Left (HttpStatusErr status))
+      else do
+        bs <- brReadSome (responseBody res) (maxResponseBytes + 1)
+        pure $ if BL.length bs > fromIntegral maxResponseBytes then Left BodyTooLarge else Right bs
+  pure (either (Left . HttpFailure) id result)

src/Simplex/Messaging/Server/Prometheus.hs

@@ -52,13 +52,14 @@ data RealTimeMetrics = RealTimeMetrics
 data RTSubscriberMetrics = RTSubscriberMetrics
   { subsCount :: Int,
     subClientsCount :: Int,
-    subServicesCount :: Int
+    subServicesCount :: Int,
+    subServiceSubsCount :: Int64
   }
 
 {-# FOURMOLU_DISABLE\n#-}
 prometheusMetrics :: ServerMetrics -> RealTimeMetrics -> UTCTime -> Text
 prometheusMetrics sm rtm ts =
-  time <> queues <> subscriptions <> messages <> ntfMessages <> ntfs <> relays <> services <> info
+  time <> queues <> subscriptions <> messages <> ntfMessages <> ntfs <> relays <> services <> names <> info
   where
     ServerMetrics {statsData, activeQueueCounts = ps, activeNtfCounts = psNtf, entityCounts, rtsOptions} = sm
     RealTimeMetrics
@@ -127,7 +128,8 @@ prometheusMetrics sm rtm ts =
         _rcvServicesSubDuplicate,
         _qCount,
         _msgCount,
-        _ntfCount
+        _ntfCount,
+        _rslvStats
       } = statsData
     time =
       "# Recorded at: " <> T.pack (iso8601Show ts) <> "\n\
@@ -391,13 +393,13 @@ prometheusMetrics sm rtm ts =
       \# TYPE simplex_smp_ntf_services_queues_count gauge\n\
       \simplex_smp_ntf_services_queues_count " <> mshow (ntfServiceQueuesCount entityCounts) <> "\n# ntfServiceQueuesCount\n\
       \\n\
-      \# HELP simplex_smp_rcv_services_sub_msg The count of subscribed service queues with messages.\n\
-      \# TYPE simplex_smp_rcv_services_sub_msg counter\n\
-      \simplex_smp_rcv_services_sub_msg " <> mshow _rcvServicesSubMsg <> "\n# rcvServicesSubMsg\n\
+      \# HELP simplex_smp_rcv_services_sub_msg_count The count of subscribed service queues with messages.\n\
+      \# TYPE simplex_smp_rcv_services_sub_msg_count counter\n\
+      \simplex_smp_rcv_services_sub_msg_count " <> mshow _rcvServicesSubMsg <> "\n# rcvServicesSubMsg\n\
       \\n\
-      \# HELP simplex_smp_rcv_services_sub_duplicate The count of duplicate subscribed service queues.\n\
-      \# TYPE simplex_smp_rcv_services_sub_duplicate counter\n\
-      \simplex_smp_rcv_services_sub_duplicate " <> mshow _rcvServicesSubDuplicate <> "\n# rcvServicesSubDuplicate\n\
+      \# HELP simplex_smp_rcv_services_sub_duplicate_count The count of duplicate subscribed service queues.\n\
+      \# TYPE simplex_smp_rcv_services_sub_duplicate_count counter\n\
+      \simplex_smp_rcv_services_sub_duplicate_count " <> mshow _rcvServicesSubDuplicate <> "\n# rcvServicesSubDuplicate\n\
       \\n"
         <> showServices _rcvServices "rcv" "receiving"
         <> showServices _ntfServices "ntf" "notification"
@@ -458,6 +460,31 @@ prometheusMetrics sm rtm ts =
       \# TYPE simplex_smp_" <> pfx <> "_services_sub_fewer_total gauge\n\
       \simplex_smp_" <> pfx <> "_services_sub_fewer_total " <> mshow (_srvSubFewerTotal ss) <> "\n# " <> pfx <> ".srvSubFewerTotal\n\
       \\n"
+    names =
+      let NameResolverStatsData {_rslvReqs, _rslvSucc, _rslvNotFound, _rslvResolverErrs, _rslvDisabled} = _rslvStats
+       in "# Names\n\
+          \# -----\n\
+          \\n\
+          \# HELP simplex_smp_names_reqs Total RSLV requests forwarded to this server.\n\
+          \# TYPE simplex_smp_names_reqs counter\n\
+          \simplex_smp_names_reqs " <> mshow _rslvReqs <> "\n# rslvReqs\n\
+          \\n\
+          \# HELP simplex_smp_names_success NameRecord successfully resolved and returned.\n\
+          \# TYPE simplex_smp_names_success counter\n\
+          \simplex_smp_names_success " <> mshow _rslvSucc <> "\n# rslvSucc\n\
+          \\n\
+          \# HELP simplex_smp_names_not_found Name not registered (resolver returned 404 / 400).\n\
+          \# TYPE simplex_smp_names_not_found counter\n\
+          \simplex_smp_names_not_found " <> mshow _rslvNotFound <> "\n# rslvNotFound\n\
+          \\n\
+          \# HELP simplex_smp_names_resolver_errs Resolver backend errors (HTTP 5xx, transport, decode, or timeout).\n\
+          \# TYPE simplex_smp_names_resolver_errs counter\n\
+          \simplex_smp_names_resolver_errs " <> mshow _rslvResolverErrs <> "\n# rslvResolverErrs\n\
+          \\n\
+          \# HELP simplex_smp_names_disabled RSLV requests rejected because no resolver is configured (names role off).\n\
+          \# TYPE simplex_smp_names_disabled counter\n\
+          \simplex_smp_names_disabled " <> mshow _rslvDisabled <> "\n# rslvDisabled\n\
+          \\n"
     info =
       "# Info\n\
       \# ----\n\
@@ -517,6 +544,10 @@ prometheusMetrics sm rtm ts =
       \# TYPE simplex_smp_subscribtion_services_total gauge\n\
       \simplex_smp_subscribtion_services_total " <> mshow (subServicesCount smpSubs) <> "\n# smp.subServicesCount\n\
       \\n\
+      \# HELP simplex_smp_subscribtion_service_subs_total Total queues subscribed via services\n\
+      \# TYPE simplex_smp_subscribtion_service_subs_total gauge\n\
+      \simplex_smp_subscribtion_service_subs_total " <> mshow (subServiceSubsCount smpSubs) <> "\n# smp.subServiceSubsCount\n\
+      \\n\
       \# HELP simplex_smp_subscription_ntf_total Total notification subscripbtions (from ntf server)\n\
       \# TYPE simplex_smp_subscription_ntf_total gauge\n\
       \simplex_smp_subscription_ntf_total " <> mshow (subsCount ntfSubs) <> "\n# ntf.subsCount\n\
@@ -529,6 +560,10 @@ prometheusMetrics sm rtm ts =
       \# TYPE simplex_smp_subscribtion_nts_services_total gauge\n\
       \simplex_smp_subscribtion_nts_services_total " <> mshow (subServicesCount ntfSubs) <> "\n# ntf.subServicesCount\n\
       \\n\
+      \# HELP simplex_smp_subscription_ntf_service_subs_total Total queues subscribed via NTF services\n\
+      \# TYPE simplex_smp_subscription_ntf_service_subs_total gauge\n\
+      \simplex_smp_subscription_ntf_service_subs_total " <> mshow (subServiceSubsCount ntfSubs) <> "\n# ntf.subServiceSubsCount\n\
+      \\n\
       \# HELP simplex_smp_loaded_queues_queue_count Total loaded queues count (all queues for memory/journal storage)\n\
       \# TYPE simplex_smp_loaded_queues_queue_count gauge\n\
       \simplex_smp_loaded_queues_queue_count " <> mshow (loadedQueueCount loadedCounts) <> "\n# loadedCounts.loadedQueueCount\n\

src/Simplex/Messaging/Server/QueueStore/Postgres.hs

@@ -91,7 +91,7 @@ import Simplex.Messaging.SystemTime
 import Simplex.Messaging.TMap (TMap)
 import qualified Simplex.Messaging.TMap as TM
 import Simplex.Messaging.Transport (SMPServiceRole (..))
-import Simplex.Messaging.Util (eitherToMaybe, firstRow, ifM, maybeFirstRow, maybeFirstRow', tshow, (<$$>))
+import Simplex.Messaging.Util (eitherToMaybe, firstRow, ifM, maybeFirstRow, maybeFirstRow', tshow, (<$$>), ($>>=))
 import System.Exit (exitFailure)
 import System.IO (IOMode (..), hFlush, stdout)
 import UnliftIO.STM
@@ -504,6 +504,32 @@ instance StoreQueueClass q => QueueStoreClass q (PostgresQueueStore q) where
         atomically $ writeTVar (queueRec sq) $ Just q'
         withLog "setQueueService" st $ \sl -> logQueueService sl rId party serviceId
 
+  setQueueServices :: (PartyI p, ServiceParty p) => PostgresQueueStore q -> SParty p -> Maybe ServiceId -> [q] -> IO (Either ErrorType (M.Map RecipientId (Either ErrorType ())))
+  setQueueServices _ _ _ [] = pure $ Right M.empty
+  setQueueServices st party serviceId qs = E.uninterruptibleMask_ $ runExceptT $ do
+    updated <- S.fromList <$> withDB' "setQueueServices" st (\db ->
+      map fromOnly <$> DB.query db updateQuery (serviceId, In (map recipientId qs)))
+    results <- liftIO $ forM qs $ \sq -> do
+      let rId = recipientId sq
+      (rId,) <$> if S.member rId updated
+        then readQueueRecIO (queueRec sq) $>>= \q -> do
+          atomically $ writeTVar (queueRec sq) $ Just $ updateRec q
+          withLog "setQueueServices" st $ \sl -> logQueueService sl rId party serviceId
+          pure $ Right ()
+        else pure $ Left AUTH
+    pure $ M.fromList results
+    where
+      updateQuery = case party of
+        SRecipientService ->
+          "UPDATE msg_queues SET rcv_service_id = ? WHERE recipient_id IN ? AND deleted_at IS NULL RETURNING recipient_id"
+        SNotifierService ->
+          "UPDATE msg_queues SET ntf_service_id = ? WHERE recipient_id IN ? AND notifier_id IS NOT NULL AND deleted_at IS NULL RETURNING recipient_id"
+      updateRec q = case party of
+        SRecipientService -> q {rcvServiceId = serviceId}
+        SNotifierService -> case notifier q of
+          Just nc -> q {notifier = Just nc {ntfServiceId = serviceId}}
+          Nothing -> q
+
   getQueueNtfServices :: PostgresQueueStore q -> [(NotifierId, a)] -> IO (Either ErrorType ([(Maybe ServiceId, [(NotifierId, a)])], [(NotifierId, a)]))
   getQueueNtfServices st ntfs = E.uninterruptibleMask_ $ runExceptT $ do
     snIds <-

src/Simplex/Messaging/Server/QueueStore/STM.hs

@@ -178,10 +178,13 @@ instance StoreQueueClass q => QueueStoreClass q (STMQueueStore q) where
         _ -> pure $ Left AUTH
         where
           addLink = do
-            let !q' = q {queueData = Just (lnkId, d)}
-            writeTVar qr $ Just q'
-            TM.insert lnkId rId $ links st
-            pure $ Right ()
+            TM.lookup lnkId (links st) >>= \case
+              Just rId' | rId' /= rId -> pure $ Left AUTH
+              _ -> do
+                let !q' = q {queueData = Just (lnkId, d)}
+                writeTVar qr $ Just q'
+                TM.insert lnkId rId $ links st
+                pure $ Right ()
 
   deleteQueueLinkData :: STMQueueStore q -> q -> IO (Either ErrorType ())
   deleteQueueLinkData st sq =
@@ -337,6 +340,10 @@ instance StoreQueueClass q => QueueStoreClass q (STMQueueStore q) where
         mapM_ (removeServiceQueue st serviceSel qId) prevSrvId
         mapM_ (addServiceQueue st serviceSel qId) serviceId
 
+  setQueueServices st party serviceId qs = Right . M.fromList <$> mapM setQueue qs
+    where
+      setQueue sq = (recipientId sq,) <$> setQueueService st sq party serviceId
+
   getQueueNtfServices :: STMQueueStore q -> [(NotifierId, a)] -> IO (Either ErrorType ([(Maybe ServiceId, [(NotifierId, a)])], [(NotifierId, a)]))
   getQueueNtfServices st ntfs = do
     ss <- readTVarIO (services st)