feat(bench): self-contained Docker Compose setup

Build benchmark binary inside container via multi-stage
Dockerfile. All-in-one: docker compose run bench.

.github/actions/swap/action.yml

@@ -0,0 +1,44 @@
+name: 'Set Swap Space'
+description: 'Add moar swap'
+branding:
+  icon: 'crop'
+  color: 'orange'
+inputs:
+  swap-size-gb:
+    description: 'Swap space to create, in Gigabytes.'
+    required: false
+    default: '10'
+runs:
+  using: "composite"
+  steps:
+    - name: Swap space report before modification
+      shell: bash
+      run: |
+        echo "Memory and swap:"
+        free -h
+        echo
+        swapon --show
+        echo
+    - name: Set Swap
+      shell: bash
+      run: |
+          export SWAP_FILE=$(swapon --show=NAME | tail -n 1)
+          echo "Swap file: $SWAP_FILE"
+          if [ -z "$SWAP_FILE" ]; then
+            SWAP_FILE=/opt/swapfile
+          else
+            sudo swapoff $SWAP_FILE
+            sudo rm $SWAP_FILE
+          fi
+          sudo fallocate -l ${{ inputs.swap-size-gb }}G $SWAP_FILE
+          sudo chmod 600 $SWAP_FILE
+          sudo mkswap $SWAP_FILE
+          sudo swapon $SWAP_FILE
+    - name: Swap space report after modification
+      shell: bash
+      run: |
+        echo "Memory and swap:"
+        free -h
+        echo
+        swapon --show
+        echo

.github/workflows/build.yml

@@ -10,62 +10,25 @@ on:
   pull_request:
 
 jobs:
-  build:
-    name: build-${{ matrix.os }}-${{ matrix.ghc }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - os: ubuntu-20.04
-            platform_name: 20_04-x86-64
-            ghc: "8.10.7"
-          - os: ubuntu-20.04
-            platform_name: 20_04-x86-64
-            ghc: "9.6.3"
-          - os: ubuntu-22.04
-            platform_name: 22_04-x86-64
-            ghc: "9.6.3"
+
+# =============================
+#       Create release
+# =============================
+
+# Create release, but only if it's triggered by tag push.
+# On pull requests/commits push, this job will always complete.
+
+  maybe-release:
+    runs-on: ubuntu-latest
     steps:
       - name: Clone project
+        if: startsWith(github.ref, 'refs/tags/v')
         uses: actions/checkout@v3
 
-      - name: Setup Haskell
-        uses: haskell-actions/setup@v2
-        with:
-          ghc-version: ${{ matrix.ghc }}
-          cabal-version: "3.10.1.0"
-
-      - name: Cache dependencies
-        uses: actions/cache@v2
-        with:
-          path: |
-            ~/.cabal/store
-            dist-newstyle
-          key: ${{ matrix.os }}-${{ hashFiles('cabal.project', 'simplexmq.cabal') }}
-
-      - name: Build
-        shell: bash
-        run: cabal build --enable-tests
-
-      - name: Test
-        timeout-minutes: 40
-        shell: bash
-        run: cabal test --test-show-details=direct
-
-      - name: Prepare binaries
-        if: startsWith(github.ref, 'refs/tags/v')
-        shell: bash
-        run: |
-          mv $(cabal list-bin smp-server) smp-server-ubuntu-${{ matrix.platform_name}}
-          mv $(cabal list-bin ntf-server) ntf-server-ubuntu-${{ matrix.platform_name}}
-          mv $(cabal list-bin xftp-server) xftp-server-ubuntu-${{ matrix.platform_name}}
-          mv $(cabal list-bin xftp) xftp-ubuntu-${{ matrix.platform_name}}
-
       - name: Build changelog
-        if: startsWith(github.ref, 'refs/tags/v') && matrix.os == 'ubuntu-22.04'
         id: build_changelog
-        uses: mikepenz/release-changelog-builder-action@v1
+        if: startsWith(github.ref, 'refs/tags/v')
+        uses: simplex-chat/release-changelog-builder-action@v5
         with:
           configuration: .github/changelog_conf.json
           failOnError: true
@@ -75,8 +38,8 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Create release
-        if: startsWith(github.ref, 'refs/tags/v') && matrix.ghc != '8.10.7'
-        uses: softprops/action-gh-release@v1
+        if: startsWith(github.ref, 'refs/tags/v')
+        uses: simplex-chat/action-gh-release@v2
         with:
           body: |
             See full changelog [here](https://github.com/simplex-chat/simplexmq/blob/master/CHANGELOG.md).
@@ -86,10 +49,241 @@ jobs:
           prerelease: true
           files: |
             LICENSE
-            smp-server-ubuntu-${{ matrix.platform_name}}
-            ntf-server-ubuntu-${{ matrix.platform_name}}
-            xftp-server-ubuntu-${{ matrix.platform_name}}
-            xftp-ubuntu-${{ matrix.platform_name}}
           fail_on_unmatched_files: true
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+# =============================
+#        Main build job
+# =============================
+
+  build:
+    name: "ubuntu-${{ matrix.os }}-${{ matrix.arch }}, GHC: ${{ matrix.ghc }}"
+    needs: maybe-release
+    env:
+      apps: "smp-server xftp-server ntf-server xftp"
+    runs-on: ${{ matrix.runner }}
+    services:
+      postgres:
+        image: postgres:15
+        env:
+          POSTGRES_HOST_AUTH_METHOD: trust # Allows passwordless access
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          # Maps tcp port 5432 on service container to the host
+          - 5432:5432
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: 22.04
+            os_underscore: 22_04
+            arch: x86-64
+            runner: "ubuntu-22.04"
+            ghc: "8.10.7"
+            should_run: ${{ !(github.ref == 'refs/heads/stable' || startsWith(github.ref, 'refs/tags/v')) }}
+          - os: 22.04
+            os_underscore: 22_04
+            arch: x86-64
+            runner: "ubuntu-22.04"
+            ghc: "9.6.3"
+            should_run: true
+          - os: 24.04
+            os_underscore: 24_04
+            arch: x86-64
+            runner: "ubuntu-24.04"
+            ghc: "9.6.3"
+            should_run: true
+          - os: 22.04
+            os_underscore: 22_04
+            arch: aarch64
+            runner: "ubuntu-22.04-arm"
+            ghc: "9.6.3"
+            should_run: true
+          - os: 24.04
+            os_underscore: 24_04
+            arch: aarch64
+            runner: "ubuntu-24.04-arm"
+            ghc: "9.6.3"
+            should_run: true
+    steps:
+      - name: Clone project
+        if: matrix.should_run == true
+        uses: actions/checkout@v3
+
+      - name: Set up Docker Buildx
+        if: matrix.should_run == true
+        uses: simplex-chat/docker-setup-buildx-action@v3
+
+      - name: Setup swap
+        if: matrix.ghc == '8.10.7' && matrix.should_run == true
+        uses: ./.github/actions/swap
+        with:
+          swap-size-gb: 20
+
+      - name: Install PostgreSQL 15 client tools
+        if: matrix.os == '22.04' && matrix.should_run == true
+        shell: bash
+        run: |
+          # Import the repository signing key
+          sudo install -d /usr/share/postgresql-common/pgdg
+          sudo curl -o /usr/share/postgresql-common/pgdg/apt.postgresql.org.asc --fail https://www.postgresql.org/media/keys/ACCC4CF8.asc
+          # Add the PostgreSQL APT repository
+          sudo sh -c 'echo "deb [signed-by=/usr/share/postgresql-common/pgdg/apt.postgresql.org.asc] https://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
+          # Update repository and install postgresql tools
+          sudo apt update
+          sudo apt -y install postgresql-client-15
+
+      - name: Build and cache Docker image
+        if: matrix.should_run == true
+        uses: simplex-chat/docker-build-push-action@v6
+        with:
+          context: .
+          load: true
+          file: Dockerfile.build
+          tags: build/${{ matrix.os }}:latest
+          build-args: |
+            TAG=${{ matrix.os }}
+            GHC=${{ matrix.ghc }}
+
+      - name: Cache dependencies
+        if: matrix.should_run == true
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cabal/store
+            dist-newstyle
+          key: ubuntu-${{ matrix.os }}-${{ matrix.arch }}-ghc${{ matrix.ghc }}-${{ hashFiles('cabal.project', 'simplexmq.cabal') }}
+
+      - name: Start container
+        if: matrix.should_run == true
+        shell: bash
+        run: |
+          docker run -t -d \
+            --device /dev/fuse \
+            --cap-add SYS_ADMIN \
+            --security-opt apparmor:unconfined \
+            --name builder \
+            -v ~/.cabal:/root/.cabal \
+            -v /home/runner/work/_temp:/home/runner/work/_temp \
+            -v ${{ github.workspace }}:/project \
+            build/${{ matrix.os }}:latest
+
+      - name: Build smp-server (postgresql) and tests
+        if: matrix.should_run == true
+        shell: docker exec -t builder sh -eu {0}
+        run: |
+          chmod -fR 777 ~/.cabal ./dist-newstyle || :; git config --global --add safe.directory '*'
+          cabal clean
+          cabal update
+          cabal build --jobs=$(nproc) --enable-tests -fserver_postgres
+          mkdir -p /out
+          for i in smp-server simplexmq-test; do
+            bin=$(find /project/dist-newstyle -name "$i" -type f -executable)
+            chmod +x "$bin"
+            mv "$bin" /out/
+          done
+          strip /out/smp-server
+
+      - name: Copy simplexmq-test from container
+        if: matrix.should_run == true
+        shell: bash
+        run: |
+          docker cp builder:/out/simplexmq-test .
+
+      - name: Copy smp-server (postgresql) from container and prepare it
+        if: startsWith(github.ref, 'refs/tags/v') && matrix.should_run == true
+        id: prepare-postgres
+        shell: bash
+        run: |
+          name="smp-server-postgres-ubuntu-${{ matrix.os_underscore }}-${{ matrix.arch }}"
+          docker cp builder:/out/smp-server $name
+
+          path="${{ github.workspace }}/$name"
+          echo "bin=$path" >> $GITHUB_OUTPUT
+
+          hash="SHA2-256($name)= $(openssl sha256 $path | cut -d' ' -f 2)"
+          printf 'hash=%s' "$hash" >> $GITHUB_OUTPUT
+
+      - name: Build everything else (standard)
+        if: matrix.should_run == true
+        shell: docker exec -t builder sh -eu {0}
+        run: |
+          cabal build --jobs=$(nproc)
+          mkdir -p /out
+          for i in ${{ env.apps }}; do
+            bin=$(find /project/dist-newstyle -name "$i" -type f -executable)
+            strip "$bin"
+            chmod +x "$bin"
+            mv "$bin" /out/
+          done
+
+      - name: Copy binaries from container and prepare them
+        id: prepare-regular
+        if: startsWith(github.ref, 'refs/tags/v') && matrix.should_run == true
+        shell: bash
+        run: |
+          docker cp builder:/out .
+
+          printf 'bins<<EOF\n' > bins.output
+          printf 'hashes<<EOF\n' > hashes.output
+          for i in ${{ env.apps }}; do
+            name="$i-ubuntu-${{ matrix.os_underscore }}-${{ matrix.arch }}"
+
+            mv ./out/$i ./$name
+
+            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: Upload binaries
+        if: startsWith(github.ref, 'refs/tags/v') && matrix.should_run == true
+        uses: simplex-chat/action-gh-release@v2
+        with:
+          append_body: true
+          prerelease: true
+          fail_on_unmatched_files: true
+          body: |
+            ${{ steps.prepare-regular.outputs.hashes }}
+            ${{ steps.prepare-postgres.outputs.hash }}
+          files: |
+            ${{ steps.prepare-regular.outputs.bins }}
+            ${{ steps.prepare-postgres.outputs.bin }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Test
+        if: matrix.should_run == true && matrix.arch == 'x86-64'
+        timeout-minutes: 120
+        shell: bash
+        env:
+          PGHOST: localhost
+        run: |
+          i=1
+          attempts=1
+          ${{ (github.ref == 'refs/heads/stable' || startsWith(github.ref, 'refs/tags/v')) }} && attempts=3
+          while [ "$i" -le "$attempts" ]; do
+            if ./simplexmq-test; then
+              break
+            else
+              echo "Attempt $i failed, retrying..."
+              i=$((i + 1))
+              sleep 1
+            fi
+          done
+          if [ "$i" -gt "$attempts" ]; then
+            echo "All "$attempts" attempts failed."
+            exit 1
+          fi

.github/workflows/docker-image.yml

@@ -14,22 +14,22 @@ jobs:
       matrix:
         include:
           - app: smp-server
-            app_port: 5223
+            app_port: "443 5223"
           - app: xftp-server
-            app_port: 443 
+            app_port: 443
     steps:
       - name: Clone project
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Log in to Docker Hub
-        uses: docker/login-action@v2
+        uses: simplex-chat/docker-login-action@v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_PASSWORD }}
 
       - name: Extract metadata for Docker image
         id: meta
-        uses: docker/metadata-action@v4
+        uses: simplex-chat/docker-metadata-action@v5
         with:
           images: ${{ secrets.DOCKERHUB_USERNAME }}/${{ matrix.app }}
           flavor: |
@@ -39,9 +39,17 @@ jobs:
             type=semver,pattern=v{{major}}.{{minor}}
             type=semver,pattern=v{{major}}
 
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
       - name: Build and push Docker image
-        uses: docker/build-push-action@v4
+        uses: simplex-chat/docker-build-push-action@v6
         with:
+          context: .
+          platforms: linux/amd64,linux/arm64
           push: true
           build-args: |
             APP=${{ matrix.app }}

.github/workflows/reproduce-schedule.yml

@@ -0,0 +1,45 @@
+name: Reproduce latest release
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 2 * * *' # every day at 02:00 night
+
+jobs:
+  reproduce:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Get latest release
+        shell: bash
+        run: |
+          curl --proto '=https' \
+               --tlsv1.2 \
+               -sSf -L \
+               'https://api.github.com/repos/simplex-chat/simplexmq/releases/latest' \
+               2>/dev/null | \
+          grep -i "tag_name" | \
+          awk -F \" '{print "TAG="$4}' >> $GITHUB_ENV
+
+      - name: Execute reproduce script
+        run: |
+          ${GITHUB_WORKSPACE}/scripts/simplexmq-reproduce-builds.sh "$TAG" || :
+
+      - name: Check if build has been reproduced
+        env:
+          url: ${{ secrets.STATUS_SIMPLEX_WEBHOOK_URL }}
+          user: ${{ secrets.STATUS_SIMPLEX_WEBHOOK_USER }}
+          pass: ${{ secrets.STATUS_SIMPLEX_WEBHOOK_PASS }}
+        run: |
+          if [ -f "${GITHUB_WORKSPACE}/${TAG}-simplexmq/_sha256sums" ]; then
+            exit 0
+          else
+            curl --proto '=https' --tlsv1.2 -sSf \
+              -u "${user}:${pass}" \
+              -H 'Content-Type: application/json' \
+              -d '{"title": "👾 GitHub: Runner", "description": "⛔️ '"$TAG"' did not reproduce."}' \
+              "$url"
+            exit 1
+          fi

.gitignore

@@ -11,3 +11,4 @@ cabal.project.local~
 .hpc/
 *.tix
 .coverage
+

2026-02-04-xftp-web-persistent-connections.md

@@ -0,0 +1,53 @@
+# XFTPClientAgent Pattern
+
+## TOC
+1. Executive Summary
+2. Changes: client.ts
+3. Changes: agent.ts
+4. Changes: test/browser.test.ts
+5. Verification
+
+## Executive Summary
+
+Add `XFTPClientAgent` — a per-server connection pool matching the Haskell pattern. The agent caches `XFTPClient` instances by server URL. All orchestration functions (`uploadFile`, `downloadFile`, `deleteFile`) take `agent` as first parameter and use `getXFTPServerClient(agent, server)` instead of calling `connectXFTP` directly. Connections stay open on success; the caller creates and closes the agent.
+
+`connectXFTP` and `closeXFTP` stay exported (used by `XFTPWebTests.hs` Haskell tests). The `browserClients` hack, per-function `connections: Map`, and `getOrConnect` are deleted.
+
+## Changes: client.ts
+
+**Add** after types section: `XFTPClientAgent` interface, `newXFTPAgent`, `getXFTPServerClient`, `closeXFTPServerClient`, `closeXFTPAgent`.
+
+**Delete**: `browserClients` Map and all `isNode` browser-cache checks in `connectXFTP` and `closeXFTP`.
+
+**Revert `closeXFTP`** to unconditional `c.transport.close()` (browser transport.close() is already a no-op).
+
+`connectXFTP` stays exported (backward compat) but becomes a raw low-level function — no caching.
+
+## Changes: agent.ts
+
+**Imports**: replace `connectXFTP`/`closeXFTP` with `getXFTPServerClient`/`closeXFTPAgent` etc.
+
+**Re-export** from agent.ts: `newXFTPAgent`, `closeXFTPAgent`, `XFTPClientAgent`.
+
+**`uploadFile`**: add `agent: XFTPClientAgent` as first param. Replace `connectXFTP` → `getXFTPServerClient`. Remove `finally { closeXFTP }`. Pass `agent` to `uploadRedirectDescription`.
+
+**`uploadRedirectDescription`**: change from `(client, server, innerFd)` to `(agent, server, innerFd)`. Get client via `getXFTPServerClient`.
+
+**`downloadFile`**: add `agent` param. Delete local `connections: Map`. Replace `getOrConnect` → `getXFTPServerClient`. Remove finally cleanup. Pass `agent` to `downloadWithRedirect`.
+
+**`downloadWithRedirect`**: add `agent` param. Same replacements. Remove try/catch cleanup. Recursive call passes `agent`.
+
+**`deleteFile`**: add `agent` param. Same pattern.
+
+**Delete**: `getOrConnect` function entirely.
+
+## Changes: test/browser.test.ts
+
+Create agent before operations, pass to upload/download, close in finally.
+
+## Verification
+
+1. `npx vitest --run` — browser round-trip test passes
+2. No remaining `browserClients`, `getOrConnect`, or per-function `connections: Map` locals
+3. `connectXFTP` and `closeXFTP` still exported (XFTPWebTests.hs compat)
+4. All orchestration functions take `agent` as first param

CHANGELOG.md

@@ -1,3 +1,274 @@
+# 6.4.4
+
+Servers:
+- fix server pages when source code is not specified.
+- include commit SHA in printed version and in web page (#1608).
+
+SMP server:
+- support short SimpleX addresses in server information page (#1600).
+- wrap all queries in transactions (#1603).
+
+SMP agent:
+- chat relay address type for short links (#1602).
+- extend xrcp certificate validity 1 hour in the past, to allow out of sync clocks (#1601).
+
+# 6.4.3
+
+SMP agent:
+- fix some connection errors by updating contact request server hosts to match server in short link (#1597).
+
+SMP server:
+- support short link URI as queue identifier in control port commands (#1596).
+
+# 6.4.2
+
+SMP server:
+- fix memory leak when connection interrupts straight after client connects.
+- do not include repeated queue blocking into stats/quota.
+
+XFTP server:
+- prometheus metrics
+
+# 6.4.1
+
+SMP protocol:
+- create notification credentials via NEW command that creates the queue (#1586)
+
+SMP server:
+- control port session improvements (#1591)
+- additional stat counter for ntf credentials created together with the queue (#1589)
+
+# 6.4.0
+
+SMP protocol (server/client):
+- support associated queue data and short connection links (see [RFC](./rfcs/2025-03-16-smp-queues.md)).
+- service certificates to optimize subscriptions.
+
+SMP agent:
+- support retries for interactive connection handshakes.
+- use web port 443 by default for preset servers.
+- use static RNG function to avoid creating dynamic C stubs when generating sntrup keys (it was detected as Dynamic Code Loading in GrapheneOS).
+- different timeouts for interactive and background operations.
+
+Ntf server:
+- PostgreSQL storage.
+- Prometheus metrics.
+- use service certificates.
+- fix repeat token registration.
+
+# 6.3.2
+
+Servers:
+- enable store log by default (#1501).
+
+SMP server:
+- reduce memory usage (#1498)
+
+SMP agent:
+- handle client/agent version downgrades after connection was established (#1508).
+
+# 6.3.1
+
+Servers:
+- handle ECONNABORTED error on client connections.
+- reproducible builds.
+- blocking records for content moderation.
+- update script (simplex-servers-update) downloads scripts from the specified or the latest stable tag.
+
+SMP server:
+- support for PostgreSQL database for queue records for higher traffic servers.
+- fix old clients sending messages to new servers (#1443)
+- remove empty journals when opening message queues and expiring idle queues (#1456, #1458).
+- additional start options (#1465):
+  - `maintenance` to run all start/stop operations without starting server.
+  - `skip-warnings` to ignore the last corrupted line in store log (can happen on abnormal termination).
+
+Ntf server:
+- record date of last token activity, to allow expiring inactive tokens.
+- additional token invalidation reasons in logs.
+
+SMP agent:
+- store message sent to multiple connections only once, to reduce storage when sending to groups (#1453).
+- encrypt messages on delivery, to reduce database writes (#1446).
+- don't block method calls on congested sockets for better concurrency (#1454).
+- check notification token status on client connection.
+- option to skip SQLite vacuum on migrations.
+
+# 6.3.0
+
+SMP agent: fix joining connection after failure by using the same ratchet.
+
+# 6.2.2
+
+SMP server:
+- add optional Prometheus metrics (#1411).
+
+Build:
+- remove three modules from client library.
+
+# 6.2.0
+
+Version 6.2.0.7
+
+Build:
+- client_library flag to build only used modules in the clients, remove package yaml
+
+SMP server:
+- journal storage for messages (BETA).
+- prevent race condition when deleting queue and to avoid "orphan" messages (#1395).
+
+SMP agent:
+- support SMP and XFTP server roles (storage/proxy) and operators (#1343).
+- treat blocked STM and other critical errors that offer restart as temporary for message delivery (#1405).
+- fix inconsistent state after app restart while accepting contact request (#1412).
+
+# 6.1.3
+
+SMP server: fix restoring notification credentials.
+
+# 6.1.2
+
+Servers: more reliable restoring of state.
+
+SMP server: reduced memory usage and faster start.
+
+Notifications: compensate for iOS notifications being dropped by Apple while device is offline (#1378):
+- Ntf server: send multiple SMP notifications in one iOS notification.
+- Agent: get multiple messages for one iOS notification.
+
+# 6.1.1
+
+SMP:
+- stop server faster (#1371)
+- add STORE error (#1372)
+
+# 6.1.0
+
+Version 6.1.0.7
+
+SMP server and client:
+- transport block encryption (#1317).
+
+Agent:
+- batch and optimize iOS notifications processing (#1308, #1311, #1313, #1316, #1330, #1331, #1333, #1337, #1346).
+- allow receiving multiple messages from single iOS notification (#1355, #1362).
+- prepare connection to accept to avoid race condition with events (#1365).
+- transport isolation mode "Session" (default) to use new SOCKS credentials when client restarts or SOCKS proxy configuration changes (#1321).
+
+Ntf server:
+- control port (#1354).
+- enable pings on ntf subscriptions, to resubscribe on reconnection (#1353).
+
+SMP server:
+- support multiple server ports (#1319).
+- support serving HTTPS and SMP transport on the same port (#1326, #1327).
+- persist iOS notifications to avoid losing them when Ntf server is offline (#1336, #1339, #1350).
+- fix lost notification subscriptions (#1347).
+- reject SKEY with different key earlier, at verification step (#1366).
+- pass server information via CLI during server initialization (#1356).
+- show version on server page (#1341).
+- explicit graceful shutdown on SIGINT (#1360).
+
+XRCP (remote access protocol):
+- use SHA3-256 in hybrid key agreement (#1302).
+- session encryption with forward secrecy (#1328).
+
+# 6.0.5
+
+SMP agent:
+- support generic SOCKS proxy (without isolate-by-auth).
+- reduce max message sizes
+
+# 6.0.4
+
+SMP server:
+- better performance/memory: fewer map updates on re-subscriptions (#1297), split and reduce STM transactions (#1294)
+- send DELD when subscribed queue is deleted (#1312)
+- add created/updated/used date to queues to manage expiration (#1306)
+
+XFTP server: truncate file creation time to 1 hour (#1310)
+
+Servers:
+- bind control port only to 127.0.0.1 for better security in case of firewall misconfiguration (#1280)
+- reduce memory used for period stats (#1298)
+
+Agent: process last notification from list (#1307)
+- report receive file error with redirected file ID, when redirect is present (#1304)
+- special error when deleted user record is not in database (#1303)
+- fix race when sending a message to the deleted connection (#1296)
+- support for multiple messages in a single notification
+
+Ntf server:
+- only use SOCKS proxy for servers without public address (#1314)
+
+# 6.0.3
+
+Agent:
+- fix possible stuck queue rotation (#1290).
+
+SMP server:
+- batch END responses when subscribed client switches to reduce server and client traffic.
+- reduce STM transactions for better performance.
+- add stats for END events and for SUB/DEL event batches.
+- remove "expensive" stats to save memory.
+
+# 6.0.2
+
+SMP agent:
+- fix stuck connection commands when a server is not responding.
+- store query errors, reduce slow query threshold to 1ms.
+
+Notification server:
+- reduce PING interval to 1 minute.
+- fix subscriptions disabled on race condition (only mark subscriptions with END status when received via the active connection).
+
+# 6.0.1
+
+SMP agent:
+- support changing user of the new connection.
+- do not start delivery workers when there are no messages to deliver.
+- enable notifications for all connections.
+- combine database transactions when subscribing.
+
+SMP server:
+- safe compacting of store log.
+- fix possible race when creating client that might lead to memory leak.
+
+Dependencies: upgrade tls to 1.9
+
+# 6.0.0
+
+Version 6.0.0.8
+
+Agent:
+- enabled fast handshake support.
+- batch-send multiple messages in each connection.
+- resume subscriptions as soon as agent moves to foreground or as network connection resumes.
+- "known" servers to determine whether to use SMP proxy.
+- retry on SMP proxy NO_SESSION error.
+- fixes to notification subscriptions.
+- persistent server statistics.
+- better concurrency.
+
+SMP server:
+- reduce threads usage.
+- additional statistics.
+- improve disabling inactive clients.
+- additional control port commands for monitoring.
+
+Notification server:
+- support onion-only SMP servers.
+
+# 5.8.2
+
+Agent:
+- fast handshake support (disabled).
+- new statistics api.
+
+SMP server:
+- fast handshake support (SKEY command).
+- minor changes to reduce memory usage.
+
 # 5.8.1
 
 Agent:

Dockerfile

@@ -1,15 +1,20 @@
-ARG TAG=22.04
+# syntax=docker/dockerfile:1.7.0-labs
+ARG TAG=24.04
 
 FROM ubuntu:${TAG} AS build
 
 ### Build stage
 
 # Install curl and git and simplexmq dependencies
-RUN apt-get update && apt-get install -y curl git build-essential libgmp3-dev zlib1g-dev llvm-12 llvm-12-dev libnuma-dev libssl-dev
+RUN apt-get update && apt-get install -y curl git build-essential libgmp3-dev zlib1g-dev llvm-18 llvm-18-dev libnuma-dev libssl-dev
 
 # Specify bootstrap Haskell versions
 ENV BOOTSTRAP_HASKELL_GHC_VERSION=9.6.3
-ENV BOOTSTRAP_HASKELL_CABAL_VERSION=3.10.1.0
+ENV BOOTSTRAP_HASKELL_CABAL_VERSION=3.12.1.0
+
+# Do not install Stack
+ENV BOOTSTRAP_HASKELL_INSTALL_NO_STACK=true
+ENV BOOTSTRAP_HASKELL_INSTALL_NO_STACK_HOOK=true
 
 # Install ghcup
 RUN curl --proto '=https' --tlsv1.2 -sSf https://get-ghcup.haskell.org | BOOTSTRAP_HASKELL_NONINTERACTIVE=1 sh
@@ -21,26 +26,42 @@ ENV PATH="/root/.cabal/bin:/root/.ghcup/bin:$PATH"
 RUN ghcup set ghc "${BOOTSTRAP_HASKELL_GHC_VERSION}" && \
     ghcup set cabal "${BOOTSTRAP_HASKELL_CABAL_VERSION}"
 
-COPY . /project
+# Copy only the source code
+COPY apps /project/apps/
+COPY cbits /project/cbits/
+COPY src /project/src/
+
+COPY cabal.project Setup.hs simplexmq.cabal LICENSE /project
+
 WORKDIR /project
 
+# Debug
+#ARG CACHEBUST=1
+
+#ADD --chmod=755 https://github.com/MShekow/directory-checksum/releases/download/v1.4.6/directory-checksum_1.4.6_linux_amd64 /usr/local/bin/directory-checksum
+#RUN directory-checksum --max-depth 2 .
+
+# Set build arguments and check if they exist
 ARG APP
-ARG APP_PORT
-RUN if [ -z "$APP" ] || [ -z "$APP_PORT" ]; then printf "Please spcify \$APP and \$APP_PORT build-arg.\n"; exit 1; fi
+RUN if [ -z "$APP" ]; then printf "Please spcify \$APP build-arg.\n"; exit 1; fi
 
 # Compile app
 RUN cabal update
 RUN cabal build exe:$APP
 
+# Copy scripts
+COPY scripts /project/scripts/
+
 # Create new path containing all files needed
 RUN mkdir /final
 WORKDIR /final
 
 # Strip the binary from debug symbols to reduce size
-RUN bin=$(find /project/dist-newstyle -name "$APP" -type f -executable) && \
+RUN bin="$(find /project/dist-newstyle -name "$APP" -type f -executable)" && \
     mv "$bin" ./ && \
     strip ./"$APP" &&\
-    mv /project/scripts/docker/entrypoint-"$APP" ./entrypoint
+    mv /project/scripts/docker/entrypoint-"$APP" ./entrypoint &&\
+    mv /project/scripts/main/simplex-servers-stopscript ./simplex-servers-stopscript
 
 ### Final stage
 FROM ubuntu:${TAG}
@@ -53,6 +74,8 @@ COPY --from=build /final /usr/local/bin/
 
 # Open app listening port
 ARG APP_PORT
+RUN if [ -z "$APP_PORT" ]; then printf "Please spcify \$APP_PORT build-arg.\n"; exit 1; fi
+
 EXPOSE $APP_PORT
 
 # simplexmq requires using SIGINT to correctly preserve undelivered messages and restore them on restart

Dockerfile.build

@@ -0,0 +1,31 @@
+# syntax=docker/dockerfile:1.7.0-labs
+ARG TAG=24.04
+FROM ubuntu:${TAG} AS build
+
+### Build stage
+
+ARG GHC=9.6.3
+ARG CABAL=3.14.1.1
+
+# Install curl, git and and simplexmq dependencies
+RUN apt-get update && apt-get install -y curl libpq-dev git sqlite3 libsqlite3-dev build-essential libgmp3-dev zlib1g-dev llvm llvm-dev libnuma-dev libssl-dev
+
+# Specify bootstrap Haskell versions
+ENV BOOTSTRAP_HASKELL_GHC_VERSION=${GHC}
+ENV BOOTSTRAP_HASKELL_CABAL_VERSION=${CABAL}
+
+# Do not install Stack
+ENV BOOTSTRAP_HASKELL_INSTALL_NO_STACK=true
+ENV BOOTSTRAP_HASKELL_INSTALL_NO_STACK_HOOK=true
+
+# Install ghcup
+RUN curl --proto '=https' --tlsv1.2 -sSf https://get-ghcup.haskell.org | BOOTSTRAP_HASKELL_NONINTERACTIVE=1 sh
+
+# Adjust PATH
+ENV PATH="/root/.cabal/bin:/root/.ghcup/bin:$PATH"
+
+# Set both as default
+RUN ghcup set ghc "${GHC}" && \
+    ghcup set cabal "${CABAL}"
+
+WORKDIR /project

README.md

@@ -1,6 +1,6 @@
 # SimpleXMQ
 
-[![GitHub build](https://github.com/simplex-chat/simplexmq/workflows/build/badge.svg)](https://github.com/simplex-chat/simplexmq/actions?query=workflow%3Abuild)
+[![GitHub build](https://github.com/simplex-chat/simplexmq/actions/workflows/build.yml/badge.svg)](https://github.com/simplex-chat/simplexmq/actions/workflows/build.yml)
 [![GitHub release](https://img.shields.io/github/v/release/simplex-chat/simplexmq)](https://github.com/simplex-chat/simplexmq/releases)
 
 📢 SimpleXMQ v1 is released - with many security, privacy and efficiency improvements, new functionality - see [release notes](https://github.com/simplex-chat/simplexmq/releases/tag/v1.0.0).
@@ -116,7 +116,7 @@ On Linux, you can deploy smp and xftp server using Docker. This will download im
 2. Run your Docker container.
 
    - `smp-server`
-   
+
      You must change **your_ip_or_domain**. `-e "pass=password"` is optional variable to password-protect your `smp` server:
      ```sh
      docker run -d \
@@ -129,7 +129,7 @@ On Linux, you can deploy smp and xftp server using Docker. This will download im
      ```
 
    - `xftp-server`
-   
+
      You must change **your_ip_or_domain** and **maximum_storage**.
      ```sh
      docker run -d \
@@ -149,8 +149,15 @@ On Linux, you can deploy smp and xftp server using Docker. This will download im
 You can install and setup servers automatically using our script:
 
 ```sh
-curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/simplex-chat/simplexmq/stable/install.sh -o simplex-server-install.sh \
-&& if echo 'b8cf2be103f21f9461d9a500bcd3db06ab7d01d68871b07f4bd245195cbead1d simplex-server-install.sh' | sha256sum -c; then chmod +x ./simplex-server-install.sh && ./simplex-server-install.sh; rm ./simplex-server-install.sh; else echo "SHA-256 checksum is incorrect!" && rm ./simplex-server-install.sh; fi
+curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/simplex-chat/simplexmq/stable/install.sh -o simplex-server-install.sh &&\
+if echo '53fcdb4ceab324316e2c4cda7e84dbbb344f32550a65975a7895425e5a1be757 simplex-server-install.sh' | sha256sum -c; then
+  chmod +x ./simplex-server-install.sh
+  ./simplex-server-install.sh
+  rm ./simplex-server-install.sh
+else
+  echo "SHA-256 checksum is incorrect!"
+  rm ./simplex-server-install.sh
+fi
 ```
 
 ### Build from source
@@ -180,7 +187,7 @@ On Linux, you can build smp server using Docker.
 3. Run your Docker container.
 
    - `smp-server`
-   
+
      You must change **your_ip_or_domain**. `-e "pass=password"` is optional variable to password-protect your `smp` server:
      ```sh
      docker run -d \
@@ -193,7 +200,7 @@ On Linux, you can build smp server using Docker.
      ```
 
    - `xftp-server`
-   
+
      You must change **your_ip_or_domain** and **maximum_storage**.
      ```sh
      docker run -d \
@@ -208,14 +215,17 @@ On Linux, you can build smp server using Docker.
 
 #### Using your distribution
 
-1. Install [Haskell GHCup](https://www.haskell.org/ghcup/), GHC 8.10.7 and cabal:
+1. Install dependencies and build tools (`GHC`, `cabal` and dev libs):
 
    ```sh
-   curl --proto '=https' --tlsv1.2 -sSf https://get-ghcup.haskell.org | sh
-   ghcup install ghc 8.10.7
-   ghcup install cabal
-   ghcup set ghc 8.10.7
-   ghcup set cabal
+   # On Ubuntu. Depending on your distribution, use your package manager to determine package names.
+   sudo apt-get update && apt-get install -y build-essential curl libffi-dev libffi7 libgmp3-dev libgmp10 libncurses-dev libncurses5 libtinfo5 pkg-config zlib1g-dev libnuma-dev libssl-dev
+   export BOOTSTRAP_HASKELL_GHC_VERSION=9.6.3
+   export BOOTSTRAP_HASKELL_CABAL_VERSION=3.10.3.0
+   curl --proto '=https' --tlsv1.2 -sSf https://get-ghcup.haskell.org | BOOTSTRAP_HASKELL_NONINTERACTIVE=1 sh
+   ghcup set ghc "${BOOTSTRAP_HASKELL_GHC_VERSION}"
+   ghcup set cabal "${BOOTSTRAP_HASKELL_CABAL_VERSION}"
+   source ~/.ghcup/env
    ```
 
 2. Build the project:
@@ -224,10 +234,20 @@ On Linux, you can build smp server using Docker.
    git clone https://github.com/simplex-chat/simplexmq
    cd simplexmq
    git checkout stable
-   # On Ubuntu. Depending on your distribution, use your package manager to determine package names.
-   apt-get update && apt-get install -y build-essential libgmp3-dev zlib1g-dev
    cabal update
-   cabal install
+   cabal build exe:smp-server exe:xftp-server
+   ```
+
+3. List compiled binaries:
+
+   `smp-server`
+   ```sh
+   cabal list-bin exe:smp-server
+   ```
+
+   `xftp-server`
+   ```sh
+   cabal list-bin exe:xftp-server
    ```
 
 - Initialize SMP server with `smp-server init [-l] -n <fqdn>` or `smp-server init [-l] --ip <ip>` - depending on how you initialize it, either FQDN or IP will be used for server's address.

apps/common/Web/Embedded.hs

@@ -0,0 +1,15 @@
+{-# LANGUAGE TemplateHaskell #-}
+
+module Web.Embedded where
+
+import Data.FileEmbed (embedDir, embedFile)
+import Simplex.Messaging.Server.Web (EmbeddedContent (..))
+
+embeddedContent :: EmbeddedContent
+embeddedContent =
+  EmbeddedContent
+    { indexHtml = $(embedFile "apps/common/Web/static/index.html"),
+      linkHtml = $(embedFile "apps/common/Web/static/link.html"),
+      mediaContent = $(embedDir "apps/common/Web/static/media/"),
+      wellKnown = $(embedDir "apps/common/Web/static/.well-known/")
+    }

apps/common/Web/static/.well-known/apple-app-site-association

@@ -0,0 +1,49 @@
+{
+  "applinks": {
+    "details": [
+      {
+        "appIDs": [
+          "5NN7GUYB6T.chat.simplex.app"
+        ],
+        "components": [
+          {
+            "/": "/contact/*"
+          },
+          {
+            "/": "/contact"
+          },
+          {
+            "/": "/invitation/*"
+          },
+          {
+            "/": "/invitation"
+          },
+          {
+            "/": "/a/*"
+          },
+          {
+            "/": "/a"
+          },
+          {
+            "/": "/c/*"
+          },
+          {
+            "/": "/c"
+          },
+          {
+            "/": "/g/*"
+          },
+          {
+            "/": "/g"
+          },
+          {
+            "/": "/i/*"
+          },
+          {
+            "/": "/i"
+          }
+        ]
+      }
+    ]
+  }
+}

apps/common/Web/static/.well-known/assetlinks.json

@@ -0,0 +1,16 @@
+[
+    {
+        "relation": [
+            "delegate_permission/common.handle_all_urls"
+        ],
+        "target": {
+            "namespace": "android_app",
+            "package_name": "chat.simplex.app",
+            "sha256_cert_fingerprints": [
+                "5E:3E:DC:C2:00:FB:A8:D5:F4:88:F3:CA:4C:32:5B:05:78:C5:6A:9C:03:A1:CC:B5:92:9C:D7:5C:7E:57:E2:4D",
+                "3C:52:C4:FD:3C:AD:1C:07:C9:B0:0A:70:80:E3:58:FA:B9:FE:FC:B8:AF:5A:EC:14:77:65:F1:6D:0F:21:AD:85",
+                "AE:C1:95:DC:FD:46:14:BD:3A:91:EC:26:D1:D5:14:C8:75:71:C5:CC:8D:CF:48:08:3F:92:83:14:3C:A2:B9:A6"
+            ]
+        }
+    }
+]

apps/common/Web/static/index.html

@@ -105,6 +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>
+              <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>
             </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>
@@ -221,9 +228,16 @@
               Public information
             </h2>
             <table id="public-info">
+              <tr class="text-grey-black dark:text-white text-base">
+                <td>Server version:</td>
+                <td>${version}<x-commit> / <a href="${commitSourceCode}/commit/${commit}" target="_blank">${shortCommit}</a></x-commit></td>
+              </tr>
               <tr class="text-grey-black dark:text-white text-base">
                 <td>Source code:</td>
-                <td><a href="${sourceCode}" target="_blank">${sourceCode}</a></td>
+                <td>
+                  <x-sourceCode><a href="${sourceCode}" target="_blank">${sourceCode}</a></x-sourceCode>
+                  <x-noSourceCode>add to ${iniFileName} (required by <a href="https://github.com/simplex-chat/simplexmq/blob/stable/LICENSE" target="_blank">AGPLv3</a>)</x-noSourceCode>
+                </td>
               </tr>
               <x-website>
                 <tr class="text-grey-black dark:text-white text-base">
@@ -291,6 +305,12 @@
                   <td>${hostingEntity} (${hostingCountry})</td>
                 </tr>
               </x-hosting>
+              <x-hostingType>
+                <tr class="text-grey-black dark:text-white text-base">
+                  <td>Hosting type:</td>
+                  <td>${hostingType}</td>
+                </tr>
+              </x-hostingType>
               <x-serverCountry>
                 <tr class="text-grey-black dark:text-white text-base">
                   <td>Server country:</td>
@@ -304,6 +324,7 @@
             <h2 class="text-[30px] mb-[20px] leading-[28px] text-[#606C71] dark:text-white font-bold max-w-[475px]">
               Configuration</h2>
             <table id="config">
+              <x-smpConfig>
               <tr class="text-grey-black dark:text-white text-base">
                 <td>Persistence:</td>
                 <td>${persistence}</td>
@@ -324,6 +345,25 @@
                 <td>Basic auth enabled:</td>
                 <td>${basicAuthEnabled}</td>
               </tr>
+              </x-smpConfig>
+              <x-xftpConfig>
+              <tr class="text-grey-black dark:text-white text-base">
+                <td>File expiration:</td>
+                <td>${fileExpiration}</td>
+              </tr>
+              <tr class="text-grey-black dark:text-white text-base">
+                <td>Stats enabled:</td>
+                <td>${statsEnabled}</td>
+              </tr>
+              <tr class="text-grey-black dark:text-white text-base">
+                <td>New uploads allowed:</td>
+                <td>${newUploadsAllowed}</td>
+              </tr>
+              <tr class="text-grey-black dark:text-white text-base">
+                <td>Basic auth enabled:</td>
+                <td>${basicAuthEnabled}</td>
+              </tr>
+              </x-xftpConfig>
             </table>
           </div>
         </div>

apps/common/Web/static/link.html

@@ -142,8 +142,7 @@
     class="hidden xl:block h-screen pt-[66px] bg-white dark:bg-gradient-radial-mobile dark:lg:bg-gradient-radial">
     <div class="container m-auto h-full flex items-center justify-between px-5">
       <div class="flex flex-col items-start justify-center w-full">
-        <h1 class="text-[38px] leading-[43px] font-bold max-w-[500px] mb-[30px] primary-header-contact">You received a
-          1-time link to connect on SimpleX Chat</h1>
+        <h1 class="text-[38px] leading-[43px] font-bold max-w-[500px] mb-[30px] primary-header-contact">This is a one-time link of the SimpleX&nbsp;network user</h1>
         <h2
           class="text-[20px] leading-[28px] text-[#606C71] dark:text-white font-bold max-w-[475px] mb-[80px] secondary-header-contact">
           Scan the QR code with the SimpleX Chat app on your phone or tablet.</h2>
@@ -184,10 +183,8 @@
     class="block xl:hidden pt-[106px] py-[90px] bg-white dark:bg-gradient-radial-mobile dark:lg:bg-gradient-radial">
     <div class="container m-auto px-5">
       <div class="flex flex-col items-center">
-        <h1 class="text-[28px] font-bold text-center max-w-[602px] mb-[40px] primary-header-contact">You received a
-          1-time link to connect on SimpleX Chat</h1>
-        <p class="text-[20px] leading-[28px] text-grey-black dark:text-white font-medium mb-[30px]">To make a
-          connection:</p>
+        <h1 class="text-[28px] font-bold text-center max-w-[602px] mb-[40px] primary-header-contact">This is a one-time link of the SimpleX&nbsp;network user</h1>
+        <p class="text-[20px] leading-[28px] text-grey-black dark:text-white font-medium mb-[30px]">To make a connection:</p>
         <div
           class="flex flex-col justify-center items-center p-4 w-full max-w-[468px] min-h-[131px] rounded-[30px] border-[1px] border-[#A8B0B4] dark:border-white border-opacity-60 mb-6 relative">
           <p class="text-xl font-medium text-grey-black dark:text-white mb-4">Install SimpleX app</p>
@@ -506,13 +503,17 @@
     const url = window.location.href
     const messageElements = document.getElementsByClassName('primary-header-contact')
 
-    if (url.includes('/invitation')) {
-      for (let element of messageElements) {
-        element.textContent = 'You received a 1-time link to connect on SimpleX Chat'
-      }
-    } else {
-      for (let element of messageElements) {
-        element.textContent = 'You received an address to connect on SimpleX Chat'
+    for (let element of messageElements) {
+      if (url.includes('/g') || url.includes('&data=%7B%22groupLinkId%22%3A')) {
+        element.innerHTML = 'This is a public group address on SimpleX&nbsp;network'
+      } else if (url.includes('/a') || url.includes('/contact')) {
+        element.innerHTML = 'This is a public address of the SimpleX&nbsp;network user'
+      } else if (url.includes('/i') || url.includes('/invitation')) {
+        element.innerHTML = 'This is a one-time link of the SimpleX&nbsp;network user'
+      } else if (url.includes('/c')) {
+        element.innerHTML = 'This is a public channel address on SimpleX&nbsp;network'
+      } else if (url.includes('/r')) {
+        element.innerHTML = 'This is a chat relay address on SimpleX&nbsp;network'
       }
     }
   </script>

apps/common/Web/static/media/contact.js

@@ -20,7 +20,18 @@
     parsedURI.pathname = "/" + action
     connURI = parsedURI.toString()
     console.log("connection URI: ", connURI)
-    mobileConnURIanchor.href = "simplex:" + parsedURI.pathname + parsedURI.hash
+    const hash = parsedURI.hash
+    const hostname = parsedURI.hostname
+    let appURI = "simplex:" + parsedURI.pathname
+    appURI += action.length > 1 // not short link
+              ? hash
+              : !hash.includes("?") // otherwise add server hostname
+              ? hash + "?h=" + hostname // no parameters
+              : !hash.includes("?h=") && !hash.includes("&h=")
+              ? hash + "&h=" + hostname // no "h" parameter
+              : hash.replace(/([?&])h=([^&]+)/, `$1h=${hostname},$2`) // add as the first hostname to "h" parameter
+    mobileConnURIanchor.href = appURI
+    console.log("app URI: ", appURI)
     connURIel.innerText = "/c " + connURI
     for (const connQRCode of connQRCodes) {
       try {

apps/ntf-server/Main.hs

@@ -15,7 +15,6 @@ logCfg = LogConfig {lc_file = Nothing, lc_stderr = True}
 
 main :: IO ()
 main = do
-  setLogLevel LogDebug -- change to LogError in production
   cfgPath <- getEnvPath "NTF_SERVER_CFG_PATH" defaultCfgPath
   logPath <- getEnvPath "NTF_SERVER_LOG_PATH" defaultLogPath
   withGlobalLogging logCfg $ ntfServerCLI cfgPath logPath

apps/smp-server/Main.hs

@@ -2,8 +2,9 @@ module Main where
 
 import Control.Logger.Simple
 import Simplex.Messaging.Server.CLI (getEnvPath)
-import Simplex.Messaging.Server.Main
-import qualified Static
+import Simplex.Messaging.Server.Main (smpServerCLI_)
+import Simplex.Messaging.Server.Web (serveStaticFiles, attachStaticFiles)
+import SMPWeb (smpGenerateSite)
 
 defaultCfgPath :: FilePath
 defaultCfgPath = "/etc/opt/simplex"
@@ -16,7 +17,6 @@ logCfg = LogConfig {lc_file = Nothing, lc_stderr = True}
 
 main :: IO ()
 main = do
-  setLogLevel LogDebug
   cfgPath <- getEnvPath "SMP_SERVER_CFG_PATH" defaultCfgPath
   logPath <- getEnvPath "SMP_SERVER_LOG_PATH" defaultLogPath
-  withGlobalLogging logCfg $ smpServerCLI_ Static.generateSite Static.serveStaticFiles cfgPath logPath
+  withGlobalLogging logCfg $ smpServerCLI_ smpGenerateSite serveStaticFiles attachStaticFiles cfgPath logPath

apps/smp-server/SMPWeb.hs

@@ -0,0 +1,43 @@
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+
+module SMPWeb
+  ( smpGenerateSite,
+    serverInformation,
+  ) where
+
+import Data.ByteString (ByteString)
+import Data.String (fromString)
+import Web.Embedded (embeddedContent)
+import Simplex.Messaging.Encoding.String (strEncode)
+import Simplex.Messaging.Server.Information
+import Simplex.Messaging.Server.Main (simplexmqSource)
+import qualified Simplex.Messaging.Server.Web as Web
+import Simplex.Messaging.Server.Web (render, serverInfoSubsts, timedTTLText)
+import Simplex.Messaging.Transport.Client (TransportHost (..))
+
+smpGenerateSite :: ServerInformation -> Maybe TransportHost -> FilePath -> IO ()
+smpGenerateSite si onionHost path =
+  Web.generateSite embeddedContent (serverInformation si onionHost) smpLinkPages path
+
+smpLinkPages :: [String]
+smpLinkPages = ["contact", "invitation", "a", "c", "g", "r", "i"]
+
+serverInformation :: ServerInformation -> Maybe TransportHost -> ByteString
+serverInformation ServerInformation {config, information} onionHost = render (Web.indexHtml embeddedContent) substs
+  where
+    substs = [("smpConfig", Just "y"), ("xftpConfig", Nothing)] <> substConfig <> serverInfoSubsts simplexmqSource information <> [("onionHost", strEncode <$> onionHost), ("iniFileName", Just "smp-server.ini")]
+    substConfig =
+      [ ( "persistence",
+          Just $ case persistence config of
+            SPMMemoryOnly -> "In-memory only"
+            SPMQueues -> "Queues"
+            SPMMessages -> "Queues and messages"
+        ),
+        ("messageExpiration", Just $ maybe "Never" (fromString . timedTTLText) $ messageExpiration config),
+        ("statsEnabled", Just . yesNo $ statsEnabled config),
+        ("newQueuesAllowed", Just . yesNo $ newQueuesAllowed config),
+        ("basicAuthEnabled", Just . yesNo $ basicAuthEnabled config)
+      ]
+    yesNo True = "Yes"
+    yesNo False = "No"

apps/smp-server/static/contact/index.html

@@ -1 +0,0 @@
-../link.html

apps/smp-server/static/invitation/index.html

@@ -1 +0,0 @@
-../link.html

apps/smp-server/web/Static.hs

@@ -1,176 +0,0 @@
-{-# LANGUAGE LambdaCase #-}
-{-# LANGUAGE NamedFieldPuns #-}
-{-# LANGUAGE OverloadedStrings #-}
-
-module Static where
-
-import Control.Logger.Simple
-import Control.Monad
-import Data.ByteString (ByteString)
-import qualified Data.ByteString as B
-import Data.Maybe (fromMaybe)
-import Data.String (fromString)
-import Data.Text.Encoding (encodeUtf8)
-import Network.Wai.Application.Static as S
-import Network.Wai.Handler.Warp as W
-import qualified Network.Wai.Handler.WarpTLS as W
-import Simplex.Messaging.Encoding.String (strEncode)
-import Simplex.Messaging.Server.Information
-import Simplex.Messaging.Server.Main (EmbeddedWebParams (..), WebHttpsParams (..))
-import Simplex.Messaging.Transport.Client (TransportHost (..))
-import Simplex.Messaging.Util (tshow)
-import Static.Embedded as E
-import System.Directory (createDirectoryIfMissing)
-import System.FilePath
-import UnliftIO.Concurrent (forkFinally)
-
-serveStaticFiles :: EmbeddedWebParams -> IO ()
-serveStaticFiles EmbeddedWebParams {webStaticPath, webHttpPort, webHttpsParams} = do
-  forM_ webHttpPort $ \port -> flip forkFinally (\e -> logError $ "HTTP server crashed: " <> tshow e) $ do
-    logInfo $ "Serving static site on port " <> tshow port
-    W.runSettings (mkSettings port) (S.staticApp $ S.defaultFileServerSettings webStaticPath)
-  forM_ webHttpsParams $ \WebHttpsParams {port, cert, key} -> flip forkFinally (\e -> logError $ "HTTPS server crashed: " <> tshow e) $ do
-    logInfo $ "Serving static site on port " <> tshow port <> " (TLS)"
-    W.runTLS (W.tlsSettings cert key) (mkSettings port) (S.staticApp $ S.defaultFileServerSettings webStaticPath)
-  where
-    mkSettings port = setPort port defaultSettings
-
-generateSite :: ServerInformation -> Maybe TransportHost -> FilePath -> IO ()
-generateSite si onionHost sitePath = do
-  createDirectoryIfMissing True sitePath
-  B.writeFile (sitePath </> "index.html") $ serverInformation si onionHost
-  createDirectoryIfMissing True $ sitePath </> "media"
-  forM_ E.mediaContent $ \(path, bs) -> B.writeFile (sitePath </> "media" </> path) bs
-  createDirectoryIfMissing True $ sitePath </> "contact"
-  B.writeFile (sitePath </> "contact" </> "index.html") E.linkHtml
-  createDirectoryIfMissing True $ sitePath </> "invitation"
-  B.writeFile (sitePath </> "invitation" </> "index.html") E.linkHtml
-  logInfo $ "Generated static site contents at " <> tshow sitePath
-
-serverInformation :: ServerInformation -> Maybe TransportHost -> ByteString
-serverInformation ServerInformation {config, information} onionHost = render E.indexHtml substs
-  where
-    substs = substConfig <> maybe [] substInfo information <> [("onionHost", strEncode <$> onionHost)]
-    substConfig =
-      [ ( "persistence",
-          Just $ case persistence config of
-            SPMMemoryOnly -> "In-memory only"
-            SPMQueues -> "Queues"
-            SPMMessages -> "Queues and messages"
-        ),
-        ("messageExpiration", Just $ maybe "Never" (fromString . timedTTLText) $ messageExpiration config),
-        ("statsEnabled", Just . yesNo $ statsEnabled config),
-        ("newQueuesAllowed", Just . yesNo $ newQueuesAllowed config),
-        ("basicAuthEnabled", Just . yesNo $ basicAuthEnabled config)
-      ]
-    yesNo True = "Yes"
-    yesNo False = "No"
-    substInfo spi =
-      concat
-        [ basic,
-          maybe [("usageConditions", Nothing), ("usageAmendments", Nothing)] conds (usageConditions spi),
-          maybe [("operator", Nothing)] operatorE (operator spi),
-          maybe [("admin", Nothing)] admin (adminContacts spi),
-          maybe [("complaints", Nothing)] complaints (complaintsContacts spi),
-          maybe [("hosting", Nothing)] hostingE (hosting spi),
-          server
-        ]
-      where
-        basic =
-          [ ("sourceCode", Just . encodeUtf8 $ sourceCode spi),
-            ("website", encodeUtf8 <$> website spi)
-          ]
-        conds ServerConditions {conditions, amendments} =
-          [ ("usageConditions", Just $ encodeUtf8 conditions),
-            ("usageAmendments", encodeUtf8 <$> amendments)
-          ]
-        operatorE Entity {name, country} =
-          [ ("operator", Just ""),
-            ("operatorEntity", Just $ encodeUtf8 name),
-            ("operatorCountry", encodeUtf8 <$> country)
-          ]
-        admin ServerContactAddress {simplex, email, pgp} =
-          [ ("admin", Just ""),
-            ("adminSimplex", strEncode <$> simplex),
-            ("adminEmail", encodeUtf8 <$> email),
-            ("adminPGP", encodeUtf8 . pkURI <$> pgp),
-            ("adminPGPFingerprint", encodeUtf8 . pkFingerprint <$> pgp)
-          ]
-        complaints ServerContactAddress {simplex, email, pgp} =
-          [ ("complaints", Just ""),
-            ("complaintsSimplex", strEncode <$> simplex),
-            ("complaintsEmail", encodeUtf8 <$> email),
-            ("complaintsPGP", encodeUtf8 . pkURI <$> pgp),
-            ("complaintsPGPFingerprint", encodeUtf8 . pkFingerprint <$> pgp)
-          ]
-        hostingE Entity {name, country} =
-          [ ("hosting", Just ""),
-            ("hostingEntity", Just $ encodeUtf8 name),
-            ("hostingCountry", encodeUtf8 <$> country)
-          ]
-        server =
-          [ ("serverCountry", fmap encodeUtf8 $ serverCountry =<< information)
-          ]
-
--- Copy-pasted from simplex-chat Simplex.Chat.Types.Preferences
-{-# INLINE timedTTLText #-}
-timedTTLText :: (Integral i, Show i) => i -> String
-timedTTLText 0 = "0 sec"
-timedTTLText ttl = do
-  let (m', s) = ttl `quotRem` 60
-      (h', m) = m' `quotRem` 60
-      (d', h) = h' `quotRem` 24
-      (mm, d) = d' `quotRem` 30
-  unwords $
-    [mms mm | mm /= 0]
-      <> [ds d | d /= 0]
-      <> [hs h | h /= 0]
-      <> [ms m | m /= 0]
-      <> [ss s | s /= 0]
-  where
-    ss s = show s <> " sec"
-    ms m = show m <> " min"
-    hs 1 = "1 hour"
-    hs h = show h <> " hours"
-    ds 1 = "1 day"
-    ds 7 = "1 week"
-    ds 14 = "2 weeks"
-    ds d = show d <> " days"
-    mms 1 = "1 month"
-    mms mm = show mm <> " months"
-
--- | Rewrite source with provided substitutions
-render :: ByteString -> [(ByteString, Maybe ByteString)] -> ByteString
-render src = \case
-  [] -> src
-  (label, content') : rest -> render (section_ label content' src) rest
-
--- | Rewrite section content inside @<x-label>...</x-label>@ markers.
--- Markers are always removed when found. Closing marker is mandatory.
--- If content is absent, whole section is removed.
--- Section content is delegated to `item_`. If no sections found, the whole source is delegated.
-section_ :: ByteString -> Maybe ByteString -> ByteString -> ByteString
-section_ label content' src =
-  case B.breakSubstring startMarker src of
-    (_, "") -> item_ label (fromMaybe "" content') src -- no section, just replace items
-    (before, afterStart') ->
-      -- found section start, search for end too
-      case B.breakSubstring endMarker $ B.drop (B.length startMarker) afterStart' of
-        (_, "") -> error $ "missing section end: " <> show endMarker
-        (inside, next') ->
-          let next = B.drop (B.length endMarker) next'
-           in case content' of
-                Nothing -> before <> next -- collapse section
-                Just content -> before <> item_ label content inside <> section_ label content' next
-  where
-    startMarker = "<x-" <> label <> ">"
-    endMarker = "</x-" <> label <> ">"
-
--- | Replace all occurences of @${label}@ with provided content.
-item_ :: ByteString -> ByteString -> ByteString -> ByteString
-item_ label content' src =
-  case B.breakSubstring marker src of
-    (done, "") -> done
-    (before, after') -> before <> content' <> item_ label content' (B.drop (B.length marker) after')
-  where
-    marker = "${" <> label <> "}"

apps/smp-server/web/Static/Embedded.hs

@@ -1,15 +0,0 @@
-{-# LANGUAGE TemplateHaskell #-}
-
-module Static.Embedded where
-
-import Data.FileEmbed (embedDir, embedFile)
-import Data.ByteString (ByteString)
-
-indexHtml :: ByteString
-indexHtml = $(embedFile "apps/smp-server/static/index.html")
-
-linkHtml :: ByteString
-linkHtml = $(embedFile "apps/smp-server/static/link.html")
-
-mediaContent :: [(FilePath, ByteString)]
-mediaContent = $(embedDir "apps/smp-server/static/media/")

apps/xftp-server/Main.hs

@@ -1,8 +1,10 @@
 module Main where
 
 import Control.Logger.Simple
+import Simplex.FileTransfer.Server.Main (xftpServerCLI_)
 import Simplex.Messaging.Server.CLI (getEnvPath)
-import Simplex.FileTransfer.Server.Main
+import Simplex.Messaging.Server.Web (serveStaticFiles)
+import XFTPWeb (xftpGenerateSite)
 
 defaultCfgPath :: FilePath
 defaultCfgPath = "/etc/opt/simplex-xftp"
@@ -18,4 +20,4 @@ main = do
   setLogLevel LogDebug -- change to LogError in production
   cfgPath <- getEnvPath "XFTP_SERVER_CFG_PATH" defaultCfgPath
   logPath <- getEnvPath "XFTP_SERVER_LOG_PATH" defaultLogPath
-  withGlobalLogging logCfg $ xftpServerCLI cfgPath logPath
+  withGlobalLogging logCfg $ xftpServerCLI_ xftpGenerateSite serveStaticFiles cfgPath logPath

apps/xftp-server/XFTPWeb.hs

@@ -0,0 +1,67 @@
+{-# LANGUAGE NamedFieldPuns #-}
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+module XFTPWeb
+  ( xftpGenerateSite,
+    xftpServerInformation,
+  ) where
+
+import Control.Monad (forM_)
+import qualified Data.ByteString.Char8 as B
+import Data.ByteString (ByteString)
+import Data.FileEmbed (embedDir, embedFile)
+import Data.Maybe (isJust)
+import Data.String (fromString)
+import Web.Embedded (embeddedContent)
+import Simplex.FileTransfer.Server.Env (XFTPServerConfig (..))
+import Simplex.Messaging.Encoding.String (strEncode)
+import Simplex.Messaging.Server.Expiration (ExpirationConfig (..))
+import Simplex.Messaging.Server.Information (ServerPublicInfo)
+import Simplex.Messaging.Server.Main (simplexmqSource)
+import qualified Simplex.Messaging.Server.Web as Web
+import Simplex.Messaging.Server.Web (render, serverInfoSubsts, timedTTLText)
+import Simplex.Messaging.Transport.Client (TransportHost (..))
+import System.Directory (createDirectoryIfMissing)
+import System.FilePath ((</>))
+
+xftpWebContent :: [(FilePath, ByteString)]
+xftpWebContent = $(embedDir "apps/xftp-server/static/xftp-web-bundle/")
+
+xftpMediaContent :: [(FilePath, ByteString)]
+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 cfg info onionHost path = do
+  let substs = xftpSubsts cfg info onionHost
+  Web.generateSite embeddedContent (render (Web.indexHtml embeddedContent) substs) [] path
+  let xftpDir = path </> "xftp-web-bundle"
+      mediaDir = path </> "media"
+      fileDir = path </> "file"
+  filePage xftpDir xftpWebContent
+  filePage mediaDir xftpMediaContent
+  createDirectoryIfMissing True fileDir
+  B.writeFile (fileDir </> "index.html") $ render xftpFilePageHtml substs
+  where
+    filePage dir content_ = do
+      createDirectoryIfMissing True dir
+      forM_ content_ $ \(fp, content) -> B.writeFile (dir </> fp) content
+
+xftpServerInformation :: XFTPServerConfig -> 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 {fileExpiration, logStatsInterval, allowNewFiles, newFileBasicAuth} information onionHost =
+  [("smpConfig", Nothing), ("xftpConfig", Just "y")] <> substConfig <> serverInfoSubsts simplexmqSource information <> [("onionHost", strEncode <$> onionHost), ("iniFileName", Just "file-server.ini")]
+  where
+    substConfig =
+      [ ("fileExpiration", Just $ maybe "Never" (fromString . timedTTLText . ttl) fileExpiration),
+        ("statsEnabled", Just . yesNo $ isJust logStatsInterval),
+        ("newUploadsAllowed", Just . yesNo $ allowNewFiles),
+        ("basicAuthEnabled", Just . yesNo $ isJust newFileBasicAuth)
+      ]
+    yesNo True = "Yes"
+    yesNo False = "No"

apps/xftp-server/static/media/xftp-protocol-dark.svg

@@ -0,0 +1,115 @@
+<svg width="440" height="520" viewBox="-20 0 440 520" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <!-- Sender browser -->
+  <rect x="120" y="16" width="160" height="56" rx="10" stroke="#70F0F9" stroke-width="1.5"/>
+  <text x="200" y="40" text-anchor="middle" font-family="system-ui, sans-serif" font-size="13" font-weight="600" fill="#70F0F9">Sender's browser</text>
+  <text x="200" y="56" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" fill="rgba(112,240,249,0.7)">encrypts file</text>
+
+  <!-- Arrow down from sender to chunks -->
+  <line x1="200" y1="72" x2="200" y2="120" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+
+  <!-- Chunks row -->
+  <rect x="112" y="120" width="176" height="40" rx="8" fill="none" stroke="#70F0F9" stroke-width="1" stroke-dasharray="4 3"/>
+  <text x="200" y="145" text-anchor="middle" font-family="system-ui, sans-serif" font-size="12" fill="#70F0F9">encrypted chunks</text>
+
+  <!-- Arrows from chunks to routers -->
+  <line x1="152" y1="160" x2="80" y2="220" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+  <line x1="200" y1="160" x2="200" y2="220" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+  <line x1="248" y1="160" x2="320" y2="220" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+
+  <!-- Router 1 (SimpleX) -->
+  <rect x="20" y="220" width="120" height="56" rx="6" fill="none" stroke="#70F0F9" stroke-width="1.5"/>
+  <g transform="translate(28, 227)">
+    <rect width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <rect y="6" width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <rect y="12" width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <circle cx="11" cy="2" r="1" fill="#70F0F9"/>
+    <circle cx="11" cy="8" r="1" fill="#70F0F9"/>
+    <circle cx="11" cy="14" r="1" fill="#70F0F9"/>
+  </g>
+  <text x="80" y="244" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" font-weight="600" fill="#70F0F9">SimpleX</text>
+  <text x="80" y="258" text-anchor="middle" font-family="system-ui, sans-serif" font-size="9" fill="rgba(112,240,249,0.7)">XFTP router</text>
+
+  <!-- Router 2 (Flux) -->
+  <rect x="155" y="220" width="90" height="56" rx="6" fill="none" stroke="#70F0F9" stroke-width="1.5"/>
+  <g transform="translate(163, 227)">
+    <rect width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <rect y="6" width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <rect y="12" width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <circle cx="11" cy="2" r="1" fill="#70F0F9"/>
+    <circle cx="11" cy="8" r="1" fill="#70F0F9"/>
+    <circle cx="11" cy="14" r="1" fill="#70F0F9"/>
+  </g>
+  <text x="200" y="244" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" font-weight="600" fill="#70F0F9">Flux</text>
+  <text x="200" y="258" text-anchor="middle" font-family="system-ui, sans-serif" font-size="9" fill="rgba(112,240,249,0.7)">XFTP router</text>
+
+  <!-- Router 3 (SimpleX) -->
+  <rect x="260" y="220" width="120" height="56" rx="6" fill="none" stroke="#70F0F9" stroke-width="1.5"/>
+  <g transform="translate(268, 227)">
+    <rect width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <rect y="6" width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <rect y="12" width="14" height="4" rx="1" fill="rgba(112,240,249,0.5)"/>
+    <circle cx="11" cy="2" r="1" fill="#70F0F9"/>
+    <circle cx="11" cy="8" r="1" fill="#70F0F9"/>
+    <circle cx="11" cy="14" r="1" fill="#70F0F9"/>
+  </g>
+  <text x="320" y="244" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" font-weight="600" fill="#70F0F9">SimpleX</text>
+  <text x="320" y="258" text-anchor="middle" font-family="system-ui, sans-serif" font-size="9" fill="rgba(112,240,249,0.7)">XFTP router</text>
+
+  <!-- Arrows from routers down -->
+  <line x1="80" y1="276" x2="152" y2="336" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+  <line x1="200" y1="276" x2="200" y2="336" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+  <line x1="320" y1="276" x2="248" y2="336" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+
+  <!-- Re-encrypt label -->
+  <text x="330" y="310" text-anchor="start" font-family="system-ui, sans-serif" font-size="10" fill="rgba(112,240,249,0.7)">re-encrypted</text>
+  <text x="330" y="322" text-anchor="start" font-family="system-ui, sans-serif" font-size="10" fill="rgba(112,240,249,0.7)">per recipient</text>
+
+  <!-- Chunks row (download) -->
+  <rect x="112" y="336" width="176" height="40" rx="8" fill="none" stroke="#70F0F9" stroke-width="1" stroke-dasharray="4 3"/>
+  <text x="200" y="361" text-anchor="middle" font-family="system-ui, sans-serif" font-size="12" fill="#70F0F9">encrypted chunks</text>
+
+  <!-- Arrow down to recipient -->
+  <line x1="200" y1="376" x2="200" y2="424" stroke="#70F0F9" stroke-width="1.5" marker-end="url(#arrowC)"/>
+
+  <!-- Recipient browser -->
+  <rect x="120" y="424" width="160" height="56" rx="10" stroke="#70F0F9" stroke-width="1.5"/>
+  <text x="200" y="448" text-anchor="middle" font-family="system-ui, sans-serif" font-size="13" font-weight="600" fill="#70F0F9">Recipient's browser</text>
+  <text x="200" y="464" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" fill="rgba(112,240,249,0.7)">decrypts file</text>
+
+  <!-- Key path (dashed, side) -->
+  <path d="M120 44 L8 44 L8 452 L120 452" stroke="#70F0F9" stroke-width="1.5" stroke-dasharray="6 4" fill="none" marker-end="url(#arrowC)"/>
+  <text x="-6" y="240" text-anchor="middle" font-family="system-ui, sans-serif" font-size="10" fill="#70F0F9" transform="rotate(-90 -6 240)">key in URL fragment - never sent to page server or data router</text>
+
+
+  <!-- Closed padlock: encryption (between sender and chunks) -->
+  <g transform="translate(192, 88)">
+    <path d="M4,7 V4 C4,1.2 12,1.2 12,4 V7" stroke="#60a5fa" stroke-width="1.5" fill="none" stroke-linecap="round"/>
+    <rect x="2" y="7" width="12" height="9" rx="2" fill="#60a5fa"/>
+    <circle cx="8" cy="12" r="1.2" fill="#0B2A59"/>
+  </g>
+
+  <!-- Open padlock: decryption (between chunks and recipient) -->
+  <g transform="translate(192, 392)">
+    <path d="M4,7 V4 C4,1.2 12,1.2 12,4 V2" stroke="#60a5fa" stroke-width="1.5" fill="none" stroke-linecap="round"/>
+    <rect x="2" y="7" width="12" height="9" rx="2" fill="#60a5fa"/>
+    <circle cx="8" cy="12" r="1.2" fill="#0B2A59"/>
+  </g>
+
+  <!-- Key icon on dashed line -->
+  <g transform="translate(8, 410)">
+    <circle cx="0" cy="0" r="6" stroke="#FBBF24" stroke-width="2" fill="#FBBF24"/>
+    <circle cx="0" cy="0" r="2" fill="#0B2A59"/>
+    <line x1="6" y1="0" x2="16" y2="0" stroke="#FBBF24" stroke-width="2"/>
+    <line x1="14" y1="0" x2="14" y2="4" stroke="#FBBF24" stroke-width="2"/>
+    <line x1="11" y1="0" x2="11" y2="3.5" stroke="#FBBF24" stroke-width="2"/>
+  </g>
+
+  <!-- Annotation: no shared IDs -->
+  <text x="200" y="510" text-anchor="middle" font-family="system-ui, sans-serif" font-size="10" fill="rgba(112,240,249,0.7)">Each file fragment uses unique anonymous credentials - no shared identifiers</text>
+
+  <defs>
+    <marker id="arrowC" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="6" markerHeight="6" orient="auto-start-reverse">
+      <path d="M 0 0 L 10 5 L 0 10 z" fill="#70F0F9"/>
+    </marker>
+  </defs>
+</svg>

apps/xftp-server/static/media/xftp-protocol.svg

@@ -0,0 +1,130 @@
+<svg width="440" height="520" viewBox="-20 0 440 520" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <!-- Sender browser -->
+  <rect x="120" y="16" width="160" height="56" rx="10" fill="url(#gBox)" stroke="#606C71" stroke-width="1.5"/>
+  <text x="200" y="40" text-anchor="middle" font-family="system-ui, sans-serif" font-size="13" font-weight="600" fill="#fff">Sender's browser</text>
+  <text x="200" y="56" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" fill="rgba(255,255,255,0.8)">encrypts file</text>
+
+  <!-- Arrow down from sender to chunks -->
+  <line x1="200" y1="72" x2="200" y2="120" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+
+  <!-- Chunks row -->
+  <rect x="112" y="120" width="176" height="40" rx="8" fill="#f0f7ff" stroke="#0053D0" stroke-width="1" stroke-dasharray="4 3"/>
+  <text x="200" y="145" text-anchor="middle" font-family="system-ui, sans-serif" font-size="12" fill="#0053D0">encrypted chunks</text>
+
+  <!-- Arrows from chunks to routers -->
+  <line x1="152" y1="160" x2="80" y2="220" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+  <line x1="200" y1="160" x2="200" y2="220" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+  <line x1="248" y1="160" x2="320" y2="220" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+
+  <!-- Router 1 (SimpleX) -->
+  <rect x="20" y="220" width="120" height="56" rx="6" fill="#f0f4f8" stroke="#606C71" stroke-width="1.5"/>
+  <g transform="translate(28, 227)">
+    <rect width="14" height="4" rx="1" fill="#606C71"/>
+    <rect y="6" width="14" height="4" rx="1" fill="#606C71"/>
+    <rect y="12" width="14" height="4" rx="1" fill="#606C71"/>
+    <circle cx="11" cy="2" r="1" fill="#53C1FF"/>
+    <circle cx="11" cy="8" r="1" fill="#53C1FF"/>
+    <circle cx="11" cy="14" r="1" fill="#53C1FF"/>
+  </g>
+  <text x="80" y="244" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" font-weight="600" fill="#3F484B">SimpleX</text>
+  <text x="80" y="258" text-anchor="middle" font-family="system-ui, sans-serif" font-size="9" fill="#606C71">XFTP router</text>
+
+  <!-- Router 2 (Flux) -->
+  <rect x="155" y="220" width="90" height="56" rx="6" fill="#f0f4f8" stroke="#606C71" stroke-width="1.5"/>
+  <g transform="translate(163, 227)">
+    <rect width="14" height="4" rx="1" fill="#606C71"/>
+    <rect y="6" width="14" height="4" rx="1" fill="#606C71"/>
+    <rect y="12" width="14" height="4" rx="1" fill="#606C71"/>
+    <circle cx="11" cy="2" r="1" fill="#53C1FF"/>
+    <circle cx="11" cy="8" r="1" fill="#53C1FF"/>
+    <circle cx="11" cy="14" r="1" fill="#53C1FF"/>
+  </g>
+  <text x="200" y="244" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" font-weight="600" fill="#3F484B">Flux</text>
+  <text x="200" y="258" text-anchor="middle" font-family="system-ui, sans-serif" font-size="9" fill="#606C71">XFTP router</text>
+
+  <!-- Router 3 (SimpleX) -->
+  <rect x="260" y="220" width="120" height="56" rx="6" fill="#f0f4f8" stroke="#606C71" stroke-width="1.5"/>
+  <g transform="translate(268, 227)">
+    <rect width="14" height="4" rx="1" fill="#606C71"/>
+    <rect y="6" width="14" height="4" rx="1" fill="#606C71"/>
+    <rect y="12" width="14" height="4" rx="1" fill="#606C71"/>
+    <circle cx="11" cy="2" r="1" fill="#53C1FF"/>
+    <circle cx="11" cy="8" r="1" fill="#53C1FF"/>
+    <circle cx="11" cy="14" r="1" fill="#53C1FF"/>
+  </g>
+  <text x="320" y="244" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" font-weight="600" fill="#3F484B">SimpleX</text>
+  <text x="320" y="258" text-anchor="middle" font-family="system-ui, sans-serif" font-size="9" fill="#606C71">XFTP router</text>
+
+  <!-- Arrows from routers down -->
+  <line x1="80" y1="276" x2="152" y2="336" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+  <line x1="200" y1="276" x2="200" y2="336" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+  <line x1="320" y1="276" x2="248" y2="336" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+
+  <!-- Re-encrypt label -->
+  <text x="330" y="310" text-anchor="start" font-family="system-ui, sans-serif" font-size="10" fill="#606C71">re-encrypted</text>
+  <text x="330" y="322" text-anchor="start" font-family="system-ui, sans-serif" font-size="10" fill="#606C71">per recipient</text>
+
+  <!-- Chunks row (download) -->
+  <rect x="112" y="336" width="176" height="40" rx="8" fill="#f0f7ff" stroke="#0053D0" stroke-width="1" stroke-dasharray="4 3"/>
+  <text x="200" y="361" text-anchor="middle" font-family="system-ui, sans-serif" font-size="12" fill="#0053D0">encrypted chunks</text>
+
+  <!-- Arrow down to recipient -->
+  <line x1="200" y1="376" x2="200" y2="424" stroke="#606C71" stroke-width="1.5" marker-end="url(#arrowG)"/>
+
+  <!-- Recipient browser -->
+  <rect x="120" y="424" width="160" height="56" rx="10" fill="url(#gBox)" stroke="#606C71" stroke-width="1.5"/>
+  <text x="200" y="448" text-anchor="middle" font-family="system-ui, sans-serif" font-size="13" font-weight="600" fill="#fff">Recipient's browser</text>
+  <text x="200" y="464" text-anchor="middle" font-family="system-ui, sans-serif" font-size="11" fill="rgba(255,255,255,0.8)">decrypts file</text>
+
+  <!-- Key path (dashed, side) -->
+  <path d="M120 44 L8 44 L8 452 L120 452" stroke="#0053D0" stroke-width="1.5" stroke-dasharray="6 4" fill="none" marker-end="url(#arrowB)"/>
+  <text x="-6" y="240" text-anchor="middle" font-family="system-ui, sans-serif" font-size="10" fill="#0053D0" transform="rotate(-90 -6 240)">key in URL fragment - never sent to page server or data router</text>
+
+
+  <!-- Closed padlock: encryption (between sender and chunks) -->
+  <g transform="translate(192, 88)">
+    <path d="M4,7 V4 C4,1.2 12,1.2 12,4 V7" stroke="#0053D0" stroke-width="1.5" fill="none" stroke-linecap="round"/>
+    <rect x="2" y="7" width="12" height="9" rx="2" fill="#0053D0"/>
+    <circle cx="8" cy="12" r="1.2" fill="#fff"/>
+  </g>
+
+  <!-- Open padlock: decryption (between chunks and recipient) -->
+  <g transform="translate(192, 392)">
+    <path d="M4,7 V4 C4,1.2 12,1.2 12,4 V2" stroke="#0053D0" stroke-width="1.5" fill="none" stroke-linecap="round"/>
+    <rect x="2" y="7" width="12" height="9" rx="2" fill="#0053D0"/>
+    <circle cx="8" cy="12" r="1.2" fill="#fff"/>
+  </g>
+
+  <!-- Key icon on dashed line -->
+  <g transform="translate(8, 410)">
+    <circle cx="0" cy="0" r="6" stroke="#D97706" stroke-width="2" fill="#D97706"/>
+    <circle cx="0" cy="0" r="2" fill="#fff"/>
+    <line x1="6" y1="0" x2="16" y2="0" stroke="#D97706" stroke-width="2"/>
+    <line x1="14" y1="0" x2="14" y2="4" stroke="#D97706" stroke-width="2"/>
+    <line x1="11" y1="0" x2="11" y2="3.5" stroke="#D97706" stroke-width="2"/>
+  </g>
+
+  <!-- Annotation: no shared IDs -->
+  <text x="200" y="510" text-anchor="middle" font-family="system-ui, sans-serif" font-size="10" fill="#606C71">Each file fragment uses unique anonymous credentials - no shared identifiers</text>
+
+  <defs>
+    <linearGradient id="gBox" x1="120" y1="16" x2="280" y2="72" gradientUnits="userSpaceOnUse">
+      <stop stop-color="#0053D0"/>
+      <stop offset="1" stop-color="#53C1FF"/>
+    </linearGradient>
+    <linearGradient id="gSrv1" x1="20" y1="220" x2="140" y2="276" gradientUnits="userSpaceOnUse">
+      <stop stop-color="#0053D0"/>
+      <stop offset="1" stop-color="#53C1FF"/>
+    </linearGradient>
+    <linearGradient id="gSrv2" x1="155" y1="220" x2="245" y2="276" gradientUnits="userSpaceOnUse">
+      <stop stop-color="#0053D0"/>
+      <stop offset="1" stop-color="#53C1FF"/>
+    </linearGradient>
+    <marker id="arrowG" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="6" markerHeight="6" orient="auto-start-reverse">
+      <path d="M 0 0 L 10 5 L 0 10 z" fill="#606C71"/>
+    </marker>
+    <marker id="arrowB" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="6" markerHeight="6" orient="auto-start-reverse">
+      <path d="M 0 0 L 10 5 L 0 10 z" fill="#0053D0"/>
+    </marker>
+  </defs>
+</svg>

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

@@ -0,0 +1,145 @@
+#app, [data-xftp-app] {
+  font-family: system-ui, -apple-system, sans-serif;
+  color: #333;
+  width: 100%;
+  max-width: 480px;
+  padding: 16px;
+  box-sizing: border-box;
+  --xftp-ring-fg: #3b82f6;
+}
+
+:is(#app, [data-xftp-app]) .card {
+  background: #fff;
+  border-radius: 12px;
+  padding: 32px 24px;
+  box-shadow: 0 1px 3px rgba(0,0,0,.1);
+  text-align: center;
+}
+
+:is(#app, [data-xftp-app]) h1 {
+  font-size: 1.25rem;
+  font-weight: 600;
+  margin-bottom: 24px;
+}
+
+:is(#app, [data-xftp-app]) .stage { margin-top: 16px; }
+
+/* Drop zone */
+:is(#app, [data-xftp-app]) .drop-zone {
+  border: 2px dashed #ccc;
+  border-radius: 8px;
+  padding: 32px 16px;
+  transition: border-color .15s, background .15s;
+}
+:is(#app, [data-xftp-app]) .drop-zone.drag-over {
+  border-color: #3b82f6;
+  background: #eff6ff;
+}
+
+/* Buttons */
+:is(#app, [data-xftp-app]) .btn {
+  display: inline-block;
+  padding: 10px 24px;
+  border: none;
+  border-radius: 6px;
+  background: #3b82f6;
+  color: #fff;
+  font-size: .9rem;
+  font-weight: 500;
+  cursor: pointer;
+  transition: background .15s;
+}
+:is(#app, [data-xftp-app]) .btn:hover { background: #2563eb; }
+:is(#app, [data-xftp-app]) .btn-secondary { background: #6b7280; }
+:is(#app, [data-xftp-app]) .btn-secondary:hover { background: #4b5563; }
+
+/* Hints */
+:is(#app, [data-xftp-app]) .hint { color: #999; font-size: .85rem; margin-top: 8px; }
+:is(#app, [data-xftp-app]) .expiry { margin-top: 12px; }
+
+/* Progress */
+:is(#app, [data-xftp-app]) .progress-ring { display: block; margin: 0 auto 12px; }
+:is(#app, [data-xftp-app]) #upload-status,
+:is(#app, [data-xftp-app]) #dl-status { font-size: .9rem; color: #666; margin-bottom: 12px; }
+
+/* Share link row */
+:is(#app, [data-xftp-app]) .link-row {
+  display: flex;
+  gap: 8px;
+  margin-top: 12px;
+}
+:is(#app, [data-xftp-app]) .link-row input {
+  flex: 1;
+  padding: 8px 10px;
+  border: 1px solid #ccc;
+  border-radius: 6px;
+  font-size: .85rem;
+  background: #f9fafb;
+}
+
+/* Upload link */
+:is(#app, [data-xftp-app]) .upload-link {
+  margin-top: 12px;
+  color: #3b82f6;
+  font-size: .9rem;
+  text-decoration: none;
+  cursor: pointer;
+}
+:is(#app, [data-xftp-app]) .upload-link:not([hidden]) {
+  display: inline-block;
+}
+:is(#app, [data-xftp-app]) .upload-link:hover { text-decoration: underline; }
+
+/* Messages */
+:is(#app, [data-xftp-app]) .success { color: #16a34a; font-weight: 600; }
+:is(#app, [data-xftp-app]) .error { color: #dc2626; font-weight: 500; margin-bottom: 12px; }
+
+/* Security note */
+:is(#app, [data-xftp-app]) .security-note {
+  margin-top: 20px;
+  padding: 12px;
+  background: #f0fdf4;
+  border-radius: 6px;
+  font-size: .8rem;
+  color: #555;
+  text-align: left;
+}
+:is(#app, [data-xftp-app]) .security-note p + p { margin-top: 6px; }
+:is(#app, [data-xftp-app]) .security-note a { color: #3b82f6; text-decoration: none; }
+:is(#app, [data-xftp-app]) .security-note a:hover { text-decoration: underline; }
+
+/* ── Dark mode ─────────────────────────────────── */
+.dark :is(#app, [data-xftp-app]) {
+  color: #e5e7eb;
+  --xftp-ring-bg: #374151;
+  --xftp-ring-fg: #60a5fa;
+  --xftp-ring-text: #e5e7eb;
+  --xftp-ring-done: #4ade80;
+}
+.dark :is(#app, [data-xftp-app]) .card {
+  background: #1f2937;
+  box-shadow: 0 1px 3px rgba(0,0,0,.4);
+}
+.dark :is(#app, [data-xftp-app]) .drop-zone { border-color: #4b5563; }
+.dark :is(#app, [data-xftp-app]) .drop-zone.drag-over {
+  border-color: #60a5fa;
+  background: rgba(59,130,246,.15);
+}
+.dark :is(#app, [data-xftp-app]) .btn-secondary { background: #4b5563; }
+.dark :is(#app, [data-xftp-app]) .btn-secondary:hover { background: #374151; }
+.dark :is(#app, [data-xftp-app]) .hint { color: #9ca3af; }
+.dark :is(#app, [data-xftp-app]) #upload-status,
+.dark :is(#app, [data-xftp-app]) #dl-status { color: #9ca3af; }
+.dark :is(#app, [data-xftp-app]) .link-row input {
+  background: #374151;
+  border-color: #4b5563;
+  color: #e5e7eb;
+}
+.dark :is(#app, [data-xftp-app]) .success { color: #4ade80; }
+.dark :is(#app, [data-xftp-app]) .error { color: #f87171; }
+.dark :is(#app, [data-xftp-app]) .security-note {
+  background: rgba(34,197,94,.1);
+  color: #d1d5db;
+}
+.dark :is(#app, [data-xftp-app]) .upload-link { color: #60a5fa; }
+.dark :is(#app, [data-xftp-app]) .security-note a { color: #60a5fa; }

bench/ClientSim.hs

@@ -0,0 +1,133 @@
+{-# 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

@@ -0,0 +1,25 @@
+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

@@ -0,0 +1,243 @@
+{-# 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

@@ -0,0 +1,113 @@
+{-# 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

@@ -0,0 +1,46 @@
+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

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

bench/run.sh

@@ -0,0 +1,60 @@
+#!/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

cabal.project

@@ -4,6 +4,15 @@ packages: .
 -- packages: . ../http2
 -- packages: . ../network-transport
 
+-- uncomment two sections below to run tests with coverage
+-- package *
+   -- coverage: True
+   -- library-coverage: True
+
+-- package attoparsec
+   -- coverage: False
+   -- library-coverage: False
+
 index-state: 2023-12-12T00:00:00Z
 
 package cryptostore
@@ -28,3 +37,17 @@ source-repository-package
     type: git
     location: https://github.com/simplex-chat/sqlcipher-simple.git
     tag: a46bd361a19376c5211f1058908fc0ae6bf42446
+
+-- waiting for published warp-tls-3.4.7
+source-repository-package
+    type: git
+    location: https://github.com/yesodweb/wai.git
+    tag: ec5e017d896a78e787a5acea62b37a4e677dec2e
+    subdir: warp-tls
+
+-- backported fork due http-5.0
+source-repository-package
+    type: git
+    location: https://github.com/simplex-chat/wai.git
+    tag: 2f6e5aa5f05ba9140ac99e195ee647b4f7d926b0
+    subdir: warp

contributing/CODE.md

@@ -0,0 +1,104 @@
+# Coding and building
+
+This file provides guidance on coding style and approaches and on building the code.
+
+## Code Security
+
+When designing code and planning implementations:
+- Apply adversarial thinking, and consider what may happen if one of the communicating parties is malicious.
+- Formulate an explicit threat model for each change - who can do which undesirable things and under which circumstances.
+
+## Code Quality Standards
+
+Haskell client and server code serves as system specification, not just implementation — we use type-driven design to reflect the business domain in types. Quality, conciseness, and clarity of Haskell code are critical.
+
+## Code Style, Formatting and Approaches
+
+The project uses **fourmolu** for Haskell code formatting. Configuration is in `fourmolu.yaml`.
+
+**Key formatting rules:**
+- 2-space indentation
+- Trailing function arrows, commas, and import/export style
+- Record brace without space: `{field = value}`
+- Single newline between declarations
+- Never use unicode symbols
+- Inline `let` style with right-aligned `in`
+
+**Format code before committing:**
+
+```bash
+# Format a single file
+fourmolu -i src/Simplex/Messaging/Protocol.hs
+```
+
+Some files that use CPP language extension cannot be formatted as a whole, so individual code fragments need to be formatted.
+
+**Follow existing code patterns:**
+- Match the style of surrounding code
+- Use qualified imports with short aliases (e.g., `import qualified Data.ByteString.Char8 as B`)
+- Use record syntax for types with multiple fields
+- Prefer explicit pattern matching over partial functions
+
+**Comments policy:**
+- Avoid redundant comments that restate what the code already says
+- Only comment on non-obvious design decisions or tricky implementation details
+- Function names and type signatures should be self-documenting
+- Do not add comments like "wire format encoding" (Encoding class is always wire format) or "check if X" when the function name already says that
+- Assume a competent Haskell reader
+
+**Diff and refactoring:**
+- Avoid unnecessary changes and code movements
+- Never do refactoring unless it substantially reduces cost of solving the current problem, including the cost of refactoring
+- Aim to minimize the code changes - do what is minimally required to solve users' problems
+
+**Document and code structure:**
+- **Never move existing code or sections around** - add new content at appropriate locations without reorganizing existing structure.
+- When adding new sections to documents, continue the existing numbering scheme.
+- Minimize diff size - prefer small, targeted changes over reorganization.
+
+**Code analysis and review:**
+- Trace data flows end-to-end: from origin, through storage/parameters, to consumption. Flag values that are discarded and reconstructed from partial data (e.g. extracted from a URI missing original fields) — this is usually a bug.
+- Read implementations of called functions, not just signatures — if duplication involves a called function, check whether decomposing it resolves the duplication.
+- Do not save time on analysis. Read every function in the data flow even when the interface seems clear — wrong assumptions about internals are the main source of missed bugs.
+
+### Haskell Extensions
+- `StrictData` enabled by default
+- Use STM for safe concurrency
+- Assume concurrency in PostgreSQL queries
+- Comprehensive warning flags with strict pattern matching
+
+## Build Commands
+
+```bash
+# Standard build
+cabal build
+
+# Fast build
+cabal build --ghc-options -O0
+
+# Build specific executables
+cabal build exe:smp-server exe:xftp-server exe:ntf-server exe:xftp
+
+# Build with PostgreSQL server support
+cabal build -fserver_postgres
+
+# Client-only library build (no server code)
+cabal build -fclient_library
+
+# Find binary location
+cabal list-bin exe:smp-server
+```
+
+### Cabal Flags
+
+- `swift`: Enable Swift JSON format
+- `client_library`: Build without server code
+- `client_postgres`: Use PostgreSQL instead of SQLite for agent persistence
+- `server_postgres`: PostgreSQL support for server queue/notification store
+
+## External Dependencies
+
+Custom forks specified in `cabal.project`:
+- `aeson`, `hs-socks` (SimpleX forks)
+- `direct-sqlcipher`, `sqlcipher-simple` (encrypted SQLite)
+- `warp`, `warp-tls` (HTTP server)

contributing/PROJECT.md

@@ -0,0 +1,105 @@
+# SimpleXMQ repository
+
+This file provides guidance on the project structure to help working with code in this repository.
+
+## Project Overview
+
+SimpleXMQ is a Haskell message broker implementing unidirectional (simplex) queues for privacy-preserving messaging. 
+
+Key components:
+
+- **SimpleX Messaging Protocol**: SMP protocol definition and encodings ([code](../src/Simplex/Messaging/Protocol.hs), [transport code](../src/Simplex/Messaging/Transport.hs), [spec](../protocol/simplex-messaging.md)).
+- **SMP Server**: Message broker with TLS, in-memory queues, optional persistence ([main code](../src/Simplex/Messaging/Server.hs), [all code files](../src/Simplex/Messaging/Server/), [executable](../apps/smp-server/)). For proxying SMP commands the server uses [lightweight SMP client](../src/Simplex/Messaging/Client/Agent.hs).
+- **SMP Client**: Functional API with STM-based message delivery ([code](../src/Simplex/Messaging/Client.hs)).
+- **SMP Agent**: High-level duplex connections via multiple simplex queues with E2E encryption ([code](../src/Simplex/Messaging/Agent.hs)). Implements Agent-to-agent protocol ([code](../src/Simplex/Messaging/Agent/Protocol.hs), [spec](../protocol/agent-protocol.md)) via intermediary agent client ([code](../src/Simplex/Messaging/Agent/Client.hs)).
+- **XFTP**: SimpleX File Transfer Protocol, server and CLI client ([code](../src/Simplex/FileTransfer/), [spec](../protocol/xftp.md)).
+- **XRCP**: SimpleX Remote Control Protocol ([code](`../src/Simplex/RemoteControl/`), [spec](../protocol/xrcp.md)).
+- **Notifications**: Push notifications server requires PostgreSQL ([code](../src/Simplex/Messaging/Notifications), [executable](../apps/ntf-server/)). Client protocol is used for clients to communicate with the server ([code](../src/Simplex/Messaging/Notifications/Protocol.hs), [spec](../protocol/push-notifications.md)). For subscribing to SMP notifications the server uses [lightweight SMP client](../src/Simplex/Messaging/Client/Agent.hs).
+
+## Architecture
+
+For general overview see `../protocol/overview-tjr.md`.
+
+SMP Protocol Layers:
+
+```
+TLS Transport → SMP Protocol → Agent Protocol → Application protocol
+```
+
+XFTP Protocol Layers:
+
+```
+TLS Transport (HTTP2 encoding) → XFTP Protocol → Out-of-band file descriptions
+```
+
+## Key Patterns
+
+1. **Persistence**: All queue state managed via Software Transactional Memory or via PostgreSQL
+   - `Simplex.Messaging.Server.MsgStore.STM` - in-memory messages
+   - `Simplex.Messaging.Server.QueueStore.STM` - in-memory queue state
+   - `Simplex.Messaging.Server.MsgStore.Postgres` - message storage
+   - `Simplex.Messaging.Server.QueueStore.Postgres` - queue storage
+
+2. **Append-Only Store Log**: Optional persistence via journal for in-memory storage
+   - `Simplex.Messaging.Server.StoreLog` - queue creation log
+   - Compacted on restart
+
+3. **Agent Storage**:
+   - SQLite (default) or PostgreSQL
+   - Migrations in `src/Simplex/Messaging/Agent/Store/{SQLite,Postgres}/Migrations/`
+
+4. **Protocol Versioning**: All layers support version negotiation
+   - `Simplex.Messaging.Version` - version range utilities
+
+5. **Double Ratchet E2E**: Per-connection encryption
+   - `Simplex.Messaging.Crypto.Ratchet`
+   - SNTRUP761 post-quantum KEM (`src/Simplex/Messaging/Crypto/SNTRUP761/`)
+
+## Source Layout
+
+```
+src/Simplex/
+├── Messaging/
+│   ├── Agent.hs          # Main agent (~210KB)
+│   ├── Server.hs         # SMP server (~130KB)
+│   ├── Client.hs         # Client API (~65KB)
+│   ├── Protocol.hs       # Protocol types (~77KB)
+│   ├── Crypto.hs         # E2E encryption (~52KB)
+│   ├── Transport.hs      # Transport encoding over TLS
+│   ├── Agent/Store/      # SQLite/Postgres persistence
+│   ├── Server/           # Server internals (QueueStore, MsgStore, Control)
+│   └── Notifications/    # Push notification system
+├── FileTransfer/         # XFTP implementation for file transfers
+└── RemoteControl/        # XRCP implementation for device discovery & control
+```
+
+## Protocol Documentation
+
+- `protocol/overview-tjr.md`: SMP protocols stack overview
+- `protocol/simplex-messaging.md`: SMP protocol spec (v19)
+- `protocol/agent-protocol.md`: Agent protocol spec (v7)
+- `protocol/xftp.md`: File transfer protocol
+- `protocol/xrcp.md`: Remote control protocol
+- `rfcs/`: Design RFCs for features
+
+## Testing
+
+```bash
+# Run all tests
+cabal test --test-show-details=streaming
+
+# Run specific test group (uses HSpec)
+cabal test --test-option=--match="/Core tests/Encryption tests/"
+
+# Run single test
+cabal test --test-option=--match="/SMP client agent/functional API/"
+```
+
+Tests require PostgreSQL running on `localhost:5432` when using `-fserver_postgres` or `-fclient_postgres`.
+
+Test files are in `tests/` with structure:
+- `Test.hs`: Main runner
+- `AgentTests/`: Agent protocol and connection tests
+- `CoreTests/`: Crypto, encoding, storage tests
+- `ServerTests.hs`: SMP server tests
+- `XFTPServerTests.hs`: File transfer tests

contributing/README.md

@@ -0,0 +1,23 @@
+# Contributing to SimpleX repositories
+
+## Focus on user problems
+
+We do not make code changes to improve code - any change must address a specific user problem or request.
+
+## Discuss the plans as early as possible
+
+Please discuss the problem you want to solve and your detailed implementation plan with the project team prior to contributing, to avoid wasted time and additional changes. Acceptance of your contribution depends on your willingness and ability to iterate the proposed contribution to achieve the required quality level, coding style, test coverage, and alignment with user requirements as they are understood by the project team.
+
+## Follow project structure, coding style and approaches
+
+./PROJECT.md has information about the structure of this `simplexmq` repository.
+
+./CODE.md has details about general requirements common for `simplexmq` and `simplex-chat` repositories.
+
+This files can be used with LLM prompts, e.g. if you use Claude Code you can create CLAUDE.md file in project root importing content from these files:
+
+```markdown
+@README.md
+@contributing/PROJECT.md
+@contributing/CODE.md
+```

docs/plans/memory-analysis-results.md

@@ -0,0 +1,100 @@
+## 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

@@ -0,0 +1,225 @@
+## 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`.

install.sh

@@ -2,10 +2,6 @@
 set -eu
 
 # Links to scripts/configs
-bin="https://github.com/simplex-chat/simplexmq/releases/latest/download"
-bin_smp="$bin/smp-server-ubuntu-20_04-x86-64"
-bin_xftp="$bin/xftp-server-ubuntu-20_04-x86-64"
-
 scripts="https://raw.githubusercontent.com/simplex-chat/simplexmq/stable/scripts/main"
 scripts_systemd_smp="$scripts/smp-server.service"
 scripts_systemd_xftp="$scripts/xftp-server.service"
@@ -26,6 +22,8 @@ path_conf_var="/var/opt"
 path_conf_smp="$path_conf_etc/simplex $path_conf_var/simplex"
 path_conf_xftp="$path_conf_etc/simplex-xftp $path_conf_var/simplex-xftp /srv/xftp"
 
+path_conf_info="$path_conf_etc/simplex-info"
+
 path_systemd="/etc/systemd/system"
 path_systemd_smp="$path_systemd/smp-server.service"
 path_systemd_xftp="$path_systemd/xftp-server.service"
@@ -56,7 +54,7 @@ ${GRN}1.${NC} Install latest binaries from GitHub releases:
 ${GRN}2.${NC} Create server directories:
     - smp: ${YLW}${path_conf_smp}${NC}
     - xftp: ${YLW}${path_conf_xftp}${NC}
-${GRN}3.${NC} Setup user for each server:
+${GRN}3.${NC} Setup user for server:
     - xmp: ${YLW}${user_smp}${NC}
     - xftp: ${YLW}${user_xftp}${NC}
 ${GRN}4.${NC} Create systemd services:
@@ -65,7 +63,12 @@ ${GRN}4.${NC} Create systemd services:
 ${GRN}5.${NC} Install stopscript (systemd), update and uninstallation script:
     - all: ${YLW}${path_bin_update}${NC}, ${YLW}${path_bin_uninstall}${NC}, ${YLW}${path_bin_stopscript}${NC}
 
-Press ${GRN}ENTER${NC} to continue or ${RED}Ctrl+C${NC} to cancel installation"
+Press:
+  - ${GRN}1${NC} to install smp server
+  - ${GRN}2${NC} to install xftp server
+  - ${RED}Ctrl+C${NC} to cancel installation
+  
+Selection: "
 
 end="Installtion is complete!
 
@@ -76,27 +79,79 @@ Please checkout our server guides:
 To uninstall with full clean-up, simply run: ${YLW}sudo /usr/local/bin/simplex-servers-uninstall${NC}
 "
 
+set_version() {
+  ver="${VER:-latest}"
+
+  case "$ver" in 
+    latest)
+      bin="https://github.com/simplex-chat/simplexmq/releases/latest/download"
+      remote_version="$(curl --proto '=https' --tlsv1.2 -sSf -L https://api.github.com/repos/simplex-chat/simplexmq/releases/latest | grep -i "tag_name" | awk -F \" '{print $4}')"
+      ;;
+    *)
+      bin="https://github.com/simplex-chat/simplexmq/releases/download/${ver}"
+      remote_version="${ver}"
+      ;;
+  esac
+}
+
+os_test() {
+ . /etc/os-release
+
+ case "$VERSION_ID" in
+  20.04|22.04) : ;;
+  24.04) VERSION_ID='22.04' ;;
+  *) printf "${RED}Unsupported Ubuntu version!${NC}\nPlease file Github issue with request to support Ubuntu %s: https://github.com/simplex-chat/simplexmq/issues/new\n" "$VERSION_ID" && exit 1 ;;
+ esac
+
+ version="$(printf '%s' "$VERSION_ID" | tr '.' '_')"
+ arch="$(uname -p)"
+
+ case "$arch" in
+  x86_64) arch="$(printf '%s' "$arch" | tr '_' '-')" ;;
+  *)  printf "${RED}Unsupported architecture!${NC}\nPlease file Github issue with request to support %s architecture: https://github.com/simplex-chat/simplexmq/issues/new" "$arch" && exit 1 ;;
+ esac
+
+ bin_smp="$bin/smp-server-ubuntu-${version}-${arch}"
+ bin_xftp="$bin/xftp-server-ubuntu-${version}-${arch}"
+}
+
 setup_bins() {
- curl --proto '=https' --tlsv1.2 -sSf -L "$bin_smp" -o "$path_bin_smp" && chmod +x "$path_bin_smp"
- curl --proto '=https' --tlsv1.2 -sSf -L "$bin_xftp" -o "$path_bin_xftp" && chmod +x "$path_bin_xftp"
+ eval "bin=\$bin_${1}"
+ eval "path=\$path_bin_${1}"
+
+ curl --proto '=https' --tlsv1.2 -sSf -L "$bin" -o "$path" && chmod +x "$path"
+
+ unset bin path
 }
 
 setup_users() {
- useradd -M "$user_smp" 2> /dev/null || true
- useradd -M "$user_xftp" 2> /dev/null || true
+ eval "user=\$user_${1}"
+
+ useradd -M "$user" 2> /dev/null || true
+
+ unset user
 }
 
 setup_dirs() {
  # Unquoted varibles, so field splitting can occur
- mkdir -p $path_conf_smp
- chown "$user_smp":"$user_smp" $path_conf_smp
- mkdir -p $path_conf_xftp
- chown "$user_xftp":"$user_xftp" $path_conf_xftp
+ eval "path_conf=\$path_conf_${1}"
+ eval "user=\$user_${1}"
+
+ mkdir -p $path_conf
+ mkdir -p $path_conf_info
+ printf "local_version_%s='%s'\n" "$1" "$remote_version" >> "$path_conf_info/release"
+ chown -R "$user":"$user" $path_conf
+
+ unset path_conf user
 }
 
 setup_systemd() {
- curl --proto '=https' --tlsv1.2 -sSf -L "$scripts_systemd_smp" -o "$path_systemd_smp"
- curl --proto '=https' --tlsv1.2 -sSf -L "$scripts_systemd_xftp" -o "$path_systemd_xftp"
+ eval "scripts_systemd=\$scripts_systemd_${1}"
+ eval "path_systemd=\$path_systemd_${1}"
+
+ curl --proto '=https' --tlsv1.2 -sSf -L "$scripts_systemd" -o "$path_systemd"
+
+ unset scripts_systemd path_systemd
 }
 
 setup_scripts() {
@@ -110,32 +165,61 @@ checks() {
   printf "This script is intended to be run with root privileges. Please re-run script using sudo."
   exit 1
  fi
+ 
+ set_version
+ os_test
+
+ mkdir -p $path_conf_info  
 }
 
 main() {
  checks
  
- printf "%b\n%b\n" "${BLU}$logo${NC}" "$welcome"
+ printf "%b\n%b" "${BLU}$logo${NC}" "$welcome"
  read ans
 
+ case "$ans" in
+  1) setup='smp' ;;
+  2) setup='xftp' ;;
+  *) printf 'Installation aborted.\n' && exit 0 ;;
+ esac
+
  printf "Installing binaries..."
- setup_bins
+ 
+ for i in $setup; do
+  setup_bins "$i"
+ done
+ 
  printf "${GRN} Done!${NC}\n"
 
  printf "Creating users..."
- setup_users
+
+ for i in $setup; do
+  setup_users "$i"
+ done
+
  printf "${GRN} Done!${NC}\n"
  
  printf "Creating directories..."
- setup_dirs
+
+ for i in $setup; do
+  setup_dirs "$i"
+ done
+
  printf "${GRN} Done!${NC}\n"
 
  printf "Creating systemd services..."
- setup_systemd
+
+ for i in $setup; do
+  setup_systemd "$i"
+ done
+
  printf "${GRN} Done!${NC}\n"
 
  printf "Installing stopscript, update and uninstallation script..."
+
  setup_scripts
+
  printf "${GRN} Done!${NC}\n"
 
  printf "%b" "$end"

notes-flow.txt

@@ -1,23 +0,0 @@
-common:
-  corrId - random BS, used as CbNonce
-  entityId - p2r tlsUniq
-
-# setup
-s->p: "proxy", uri, auth?
-  # unless connected
-  p->r: "p_handshake"
-  p<-r: "r_key", tls-signed dh pub
-s<-r: "r_key", tls-signed dh pub # reply entityId contains tlsUniq
-
-# working
-s ; generate random dh priv, make shared secret
-s->p: s2r("forward", random dh pub, SEND command blob)
-  p->r: p2r("forward", random dh pub, s2r("forward", ...)))
-    r->c@ "msg", ...
-  p<-r: p2r("r_res", s2r("ok" / "error", error))
-s<-p@ s2r("ok" / "error", error)
-
-# expired
-  p<-r@ p2r("error", "key expired")
-s<-p@ "error", "key expired"
-s ; reconnect

package.yaml

@@ -1,211 +0,0 @@
-name: simplexmq
-version: 5.8.1.0
-synopsis: SimpleXMQ message broker
-description: |
-  This package includes <./docs/Simplex-Messaging-Server.html server>,
-  <./docs/Simplex-Messaging-Client.html client> and
-  <./docs/Simplex-Messaging-Agent.html agent> for SMP protocols:
-  .
-  * <https://github.com/simplex-chat/simplexmq/blob/master/protocol/simplex-messaging.md SMP protocol>
-  * <https://github.com/simplex-chat/simplexmq/blob/master/protocol/agent-protocol.md SMP agent protocol>
-  .
-  See <https://github.com/simplex-chat/simplex-chat terminal chat prototype> built with SimpleXMQ broker.
-
-homepage: https://github.com/simplex-chat/simplexmq#readme
-license: AGPL-3
-author: simplex.chat
-maintainer: chat@simplex.chat
-copyright: 2020-2022 simplex.chat
-category: Chat, Network, Web, System, Cryptography
-extra-source-files:
-  - README.md
-  - CHANGELOG.md
-  - cbits/sha512.h
-  - cbits/sntrup761.h
-  - apps/smp-server/static/*.html
-  - apps/smp-server/static/media/*
-
-dependencies:
-  - aeson == 2.2.*
-  - ansi-terminal >= 0.10 && < 0.12
-  - asn1-encoding == 0.9.*
-  - asn1-types == 0.3.*
-  - async == 2.2.*
-  - attoparsec == 0.14.*
-  - base >= 4.14 && < 5
-  - base64-bytestring >= 1.0 && < 1.3
-  - case-insensitive == 1.2.*
-  - composition == 1.0.*
-  - constraints >= 0.12 && < 0.14
-  - containers == 0.6.*
-  - crypton == 0.34.*
-  - crypton-x509 == 1.7.*
-  - crypton-x509-store == 1.6.*
-  - crypton-x509-validation == 1.6.*
-  - cryptostore == 0.3.*
-  - data-default == 0.7.*
-  - direct-sqlcipher == 2.3.*
-  - directory == 1.3.*
-  - filepath == 1.4.*
-  - hourglass == 0.2.*
-  - http-types == 0.12.*
-  - http2 >= 4.2.2 && < 4.3
-  - ini == 0.4.1
-  - iproute == 1.7.*
-  - iso8601-time == 0.1.*
-  - memory == 0.18.*
-  - mtl >= 2.3.1 && < 3.0
-  - network >= 3.1.2.7 && < 3.2
-  - network-info >= 0.2 && < 0.3
-  - network-transport == 0.5.6
-  - network-udp >= 0.0 && < 0.1
-  - optparse-applicative >= 0.15 && < 0.17
-  - process == 1.6.*
-  - random >= 1.1 && < 1.3
-  - simple-logger == 0.1.*
-  - socks == 0.6.*
-  - sqlcipher-simple == 0.4.*
-  - stm == 2.5.*
-  - temporary == 1.3.*
-  - time == 1.12.*
-  - time-manager == 0.0.*
-  - tls >= 1.7.0 && < 1.8
-  - transformers == 0.6.*
-  - unliftio == 0.2.*
-  - unliftio-core == 0.2.*
-  - websockets == 0.12.*
-  - yaml == 0.11.*
-  - zstd == 0.1.3.*
-
-flags:
-  swift:
-    description: Enable swift JSON format
-    manual: True
-    default: False
-  use_crypton:
-    description: Use crypton etc. in cryptostore
-    manual: True
-    default: True
-
-# cpp-options:
-#   - -Dslow_servers
-
-when:
-  - condition: flag(swift)
-    cpp-options:
-      - -DswiftJSON
-  - condition: impl(ghc >= 9.6.2)
-    dependencies:
-      - bytestring == 0.11.*
-      - template-haskell == 2.20.*
-      - text >= 2.0.1 && < 2.2
-  - condition: impl(ghc < 9.6.2)
-    dependencies:
-      - bytestring == 0.10.*
-      - template-haskell == 2.16.*
-      - text >= 1.2.3.0 && < 1.3
-
-library:
-  source-dirs: src
-  c-sources:
-    - cbits/sha512.c
-    - cbits/sntrup761.c
-  include-dirs: cbits
-  extra-libraries: crypto
-
-executables:
-  smp-server:
-    source-dirs:
-    - apps/smp-server
-    - apps/smp-server/web
-    main: Main.hs
-    dependencies:
-      - file-embed
-      - simplexmq
-      - wai-app-static
-      - warp
-      - warp-tls
-    ghc-options:
-      - -threaded
-      - -rtsopts
-
-  ntf-server:
-    source-dirs: apps/ntf-server
-    main: Main.hs
-    dependencies:
-      - simplexmq
-    ghc-options:
-      - -threaded
-      - -rtsopts
-
-  xftp-server:
-    source-dirs: apps/xftp-server
-    main: Main.hs
-    dependencies:
-      - simplexmq
-    ghc-options:
-      - -threaded
-      - -rtsopts
-
-  xftp:
-    source-dirs: apps/xftp
-    main: Main.hs
-    dependencies:
-      - simplexmq
-    ghc-options:
-      - -threaded
-      - -rtsopts
-
-tests:
-  simplexmq-test:
-    source-dirs: tests
-    main: Test.hs
-    dependencies:
-      - simplexmq
-      - deepseq == 1.4.*
-      - generic-random == 1.5.*
-      - hspec == 2.11.*
-      - hspec-core == 2.11.*
-      - HUnit == 1.6.*
-      - QuickCheck == 2.14.*
-      - silently == 1.2.*
-      - main-tester == 0.2.*
-      - timeit == 2.0.*
-    ghc-options:
-      - -threaded
-      - -rtsopts
-      - -with-rtsopts=-A64M
-      - -with-rtsopts=-N1
-
-ghc-options:
-  # - -haddock
-  - -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-unused-packages
-  - -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-methods
-  - -Werror=tabs
-  - -Wredundant-constraints
-  - -Wincomplete-record-updates
-  - -Wunused-type-patterns
-  - -O2
-
-default-extensions:
-  - StrictData

plans/done/2024-09-01-smp-message-storage.md

@@ -0,0 +1,180 @@
+
+# SMP router message storage
+
+## Problem
+
+Currently SMP routers store all queues in router memory. As the traffic grows, so does the number of undelivered messages. What is worse, Haskell is not avoiding heap fragmentation when messages are allocated and then de-allocated - undelivered messages use ByteString and GC cannot move them around, as they use pinned memory.
+
+## Possible solutions
+
+### Solution 1: solve only GC fragmentation problem
+
+Move from ByteString to some other primitive to store messages in memory long term, e.g. ShortByteString, or manage allocation/de-allocation of stored messages manually in some other way.
+
+Pros: the simplest solution that avoids substantial re-engineering of the router.
+
+Cons:
+- not a long term solution, as memory growth still has limits.
+- may be ineffective, as it introduces additional copying of bytes.
+
+### Solution 2: move message storage to hard drive
+
+Use files or RocksDB to store messages.
+
+Pros:
+- much lower memory usage.
+- no message loss in case of abnormal router termination (important until clients have delivery redundancy).
+- this is a long term solution, and at some point it might need to be done anyway.
+
+Cons:
+- substantial re-engineering costs and risks.
+- metadata privacy. Currently we only save undelivered messages when router is restarted, with this approach all messages will be stored for some time. this argument is limited, as hosting providers of VMs can make memory snapshots too, on the other hand they are harder to analyze than files. On another hand, with this approach messages will be stored for a shorter time.
+
+#### RocksDB and other key-value stores
+
+The downside of any key-value stores is that they don't seem to have efficient primitives for sequential delivery. While sequential delivery can be modelled with linked lists, they would require 1 key insert (on send), 3 key updates (1 update to update queue data on send, 1 update of the last message to point to the next, 1 update on delivery or message expiration) and 1 key deletion (on delivery or message expiration) for each delivered message.
+
+This might result in substantial write amplification and compacting costs.
+
+In general, tree structures that are efficient for quick lookups and updates, given approximately fixed value size, are inefficient for modelling queues.
+
+#### Files
+
+The upside of files is that they are well suited for sequential delivery and don't result in the same churn, with careful design, as trees do.
+
+The downside of filesystem is that it does not scale well with the large number of files in a folder, so queues will have to be spread across multiple folders, following tree-like structure.
+
+I could not find an available library that efficiently models sequential delivery in highly concurrent environment.
+
+A possible design could be the following.
+
+##### Queue folder and files
+
+Each message queue is stored in its own folder (see below on folder locations). Folder would contain these files:
+
+- `messages.abcd.log` - the file that is used to read messages from, sequentially
+- `messages.efgh.log` - the optional file that is used to write messages, in case it is different from read file.
+- `queue.log` - append-only file where the last line represents the current queue state
+- `queue.timestamp.log` - previous states of queue.log file
+
+Each line in "queue.log" file has this syntax
+
+```abnf
+queueLogLine =
+    %s"read_file=" base64
+    %s"read_msg=" digits
+    %s"read_byte=" digits
+    %s"write_file=" base64
+    %s"write_msg=" digits
+```
+
+When queue is first requested by the router:
+
+```c
+if queue folder exists:
+    read queue state from last line of queue.log
+    if queue.log contained more than one line: // compaction
+        copy queue.log to queue.timestamp.log
+        write one line queue state to queue.log
+else:
+    create queue folder
+    create messages.abcd.log (abcd is some random string)
+    read_msg = 0
+    read_byte = 0
+    create queue.log with one line: "read_file=abcd read_msg=0 read_byte=0 write_files=abcd write_msg=0"
+open read_file in ReadMode and seek to read_byte position
+nextReadByte = read_byte
+nextReadMsg = read_msg
+open write_file in AppendMode
+```
+
+When message is added to the queue (assumes that queue state is loaded to router memory, if not the previous section will be done first):
+
+```c
+if write_msg > max_queue_messages:
+    return quota error
+else if write_msg = max_queue_messages:
+    add quota_exceeded message to write_file
+    update queue state: write_msg += 1
+    append updated queue state to queue.log
+else
+    // It is required that `max_queue_messages < max_file_messages`,
+    // so that we never need more than one additional write file.
+    if write_msg >= max_file_messages: // queue file rotation
+        create messages.efgh.log // efgh is some random string
+        update queue state: write_file=efgh write_msg=0 // read file remains the same as it was
+        append updated queue state to queue.log
+        copy queue.log to queue.timestamp.log
+        // `old` needs to be defined to limit the number and storage duration,
+        // preserving not more than N files, and not more than M days files, "and then some"
+        // (that is if the queue has high churn, we have file from M days before in any case, for any debugging).
+        delete `old` `queue.timestamp.log` files
+        write one line queue state to queue.log // compaction
+
+    add message to write_file
+    update queue state: write_msg += 1
+    append updated queue state to queue.log
+```
+
+The above algorithm assumes `max_queue_messages < than max_file_messages`, so that we never need more than one write file.
+
+When message is delivered, it is simply read from the read queue, queue state does not change yet:
+
+```c
+if nextReadMsg > read_msg:
+    deliver cached message, no need to read it again
+else
+    read message from read_file handle
+    nextReadMsg = read_msg + 1
+    nextReadByte = current position in file
+```
+
+When message delivery is acknowledged, the read queue needs to be advanced, and possibly switched to read from the current write queue:
+
+```c
+if nextReadByte == read_byte:
+    return error // nothing was delivered
+else if nextReadByte = EOF:
+    // end of file is reached, possibly some other condition,
+    // but it should allow changing max_file_messages on server restart
+    currReadFile = read_file
+    read_file = write_file
+    read_msg = 0
+    read_byte = 0
+    append updated queue state to queue.log
+    delete currReadFile
+else
+    read_msg += 1
+    read_byte = nextReadByte
+    // `seek` should not be necessary, as the handle is already at nextReadByte position here
+    // seek to read_byte
+    append updated queue state to queue.log
+```
+
+The above algorithm delegates the problem of compaction and fragmentation management to file system, that is very optimized for such scenarios.
+
+Also, read and write files will grow to almost a constant size, so the space they used may be re-used.
+
+An important consideration is that writes to queue.log and message.log files and queue state modifications have to be sequential, without concurrency - it can be managed with the usual locks.
+
+##### Queue folders structure
+
+Most Linux systems use EXT4 filesystem where the file lookup time scales linearly to the number of files. While alternatives with logarithmic lookup time exist (XFS), they may be very complex to configure on the existing systems.
+
+So storing all queue folders in one folder won't scale.
+
+To solve this problem we could use recipient queue ID in base64url format not as a folder name, but as a folder path, splitting it to path fragments of some length. The number of fragments can be configurable and migration to a different fragment size can be supported as the number of queues on a given router grows.
+
+Currently, queue ID is 24 bytes random number, thus allowing 2^192 possible queue IDs. If we assume that a router must hold 1b queues, it means that we have ~2^162 possible addresses for each existing queue. 24 bytes in base64 is 32 characters that can be split into say 8 fragments with 4 characters each, so that queue folder path for queue with ID `abcdefghijklmnopqrstuvwxyz012345` would be:
+
+`/var/opt/simplex/messages/abcd/efgh/ijkl/mnop/qrst/uvwx/yz01/2345`
+
+The maximum theoretic number of the folders on the 1st level is 64^4, or 2^24 ~ 16m - this is probably still a large number of subfolders for EXT4. Given that addresses are random, all the possible combinations in the first folder can be used with a large number of queues.
+
+So we could use an unequal split of path, two letters each and the last being long:
+
+`/var/opt/simplex/messages/ab/cd/ef/ghijklmnopqrstuvwxyz012345`
+
+The first three levels in this case can have 4096 subfolders each, and it gives 68b possible subfolders (64^2^3), so the last level will be sparse in case of 1b queues on the router. So we could make it 4 levels with 2 letters to never think about it, accounting for a large variance of the random numbers distribution:
+
+`/var/opt/simplex/messages/ab/cd/ef/gh/ijklmnopqrstuvwxyz012345`

plans/done/2024-09-15-shared-port.md

@@ -0,0 +1,162 @@
+
+# Sharing protocol ports with HTTPS
+
+Some networks block all ports other than web ports, including port 5223 used for SMP protocol by default. Running SMP routers on a common web port 443 would allow them to work on more networks. The routers would need to provide an HTTPS page for browsers (and probes).
+
+## Problem
+
+Browsers and tools rely on system CA bundles instead of certificate pinning.
+The crypto parameters used by HTTPS are different from what the protocols use.
+Public certificate providers like LetsEncrypt can only sign specific types of keys and Ed25519 isn't one of them.
+
+This means a router should distinguish browser and protocol clients and adjust its behavior to match.
+
+## Solution
+
+`tls` package has a server hook that allows producing a different set of `TLS.Credentials` according to a client-provided "Server Name Indication" extension.
+
+Since LE certificates are only handed out to domain names, TLS client will be sending the SNI.
+However client transports are constructed over connected sockets and the SNI wouldn't be present unless explicitly requested.
+When a client sends SNI, then it's a browser and web credentials should be used.
+Otherwise it's a protocol client to be offered the self-signed ca, cert and key.
+
+When a transport colocated with a HTTPS, its ALPN list should be extended with `h2 http/1.1`.
+The browsers will send it, and it should be checked before running transport client.
+If HTTP ALPN is detected, then the client connection is served with HTTP `Application` instead (the same "router information" page).
+
+If some client connects to router IP, doesn't send SNI and doesn't send ALPN, it will look like a pre-handshake client.
+In that case a router will send its handshake first.
+This can be mitigated by delaying its handshake and letting the probe to issue its HTTP request.
+
+## Implementation plan
+
+An unmodified client should be able to use protocols on port 443 right away.
+
+The switchover happens inside `runTransportServerState` before `runClient`:
+
+```haskell
+runServer (tcpPort, ATransport t) = do
+  -- ...
+  runTransportServerState_ ss started tcpPort serverParams tCfg $ \socket h -> do -- expose raw socket for warp-tls internals to attach
+    negotiated <- getSessionALPN
+    if allowHTTP t && isHTTP negotiated -- only attempt the switch for the TLS transport
+      then runHTTP socket (tlsContext h)-- ... collect data and produce values needed to run WAI Application
+      else runClient serverSignKey t h `runReaderT` env -- performs serverHandshake etc as usual
+```
+
+The web app and router live outside, so `runHttp` has to be provided by the `runSMPServer` caller.
+Additonally, Warp is using its `InternalInfo` object that's scoped to `withII` bracket.
+
+```haskell
+  runServer ini = do
+    -- ...
+
+    runWebServer ini ServerInformation {config, information} $ if sharedHttps then Nothing else webHttpsParams -- suppress serving https
+    if sharedHttps
+      then withRunHTTP staticFilesPath \attachStatic -> runSMPServer cfg (Just attachStatic) -- provide wrapped application runner
+      else runSMPServer cfg Nothing
+```
+
+### Upstream
+
+The implementation relies on a few modification to upstream code:
+- `warp-tls`: The library provides `httpOverTls`, but it wants to do handshake itself.
+  Since we have to do the handshake to switch on ALPN, the setup function has to be split.
+  This is a resonable change that may be upstreamed and nothing blocks us from using the recent version.
+- `warp`: Only the re-export of `serveConnection` is needed.
+  Unfortunately the most recent `warp` version can't be used right away due to dependency cascade around `http-5` and `auto-update-2`.
+  So a fork containing the backported re-export has to be used until the dependencies are refreshed.
+### TLS.ServerParams
+
+When a router has port sharing enabled, a new set of TLS params is loaded and combined with transport params:
+
+```haskell
+newEnv config = do
+  -- ...
+  tlsServerParams <- loadTLSServerParams caCertificateFile certificateFile privateKeyFile (alpn transportConfig)
+  sharedServerParams <- forM ((,) <$> sharedHttpsCredentials config <*> alpn transportConfig) $ \((chain, key), alpn) ->
+    let ca = Nothing -- It is possible to provide CA certificate, but it is typical for web server to use combined certificate chains
+    loadHTTPSServerParams tlsServerParams ca chain key alpn
+```
+
+`loadHTTPSServerParams` extends params with:
+1. `onALPNClientSuggest` hook gets `["h2", "http/1.1"]` added to the ALPN list which is now required.
+2. `onServerNameIndication` hook added, which upon detecting client SNI prepends the web credentials.
+3. `sharedCredentials = T.Credentials []` should be done to prevent transport credentials confusing browsers.
+    But that aborts key exchange somewhere in tls internals, so disabled for now.
+    As a workaround, another set of dummy credentials can be provided in the hope that any sane browser would reject them.
+    Like, RC4 ciphers, "impossible" digest combination, etc.
+
+### supportedParameters
+
+TLS certificate chains provided by LetsEncrypt use ECDSA/P256 and that requires extending `supportedParameters` with things disabled in transports:
+
+```haskell
+    browserCiphers =
+      [ TE.cipher_TLS13_AES128CCM8_SHA256
+      , TE.cipher_ECDHE_ECDSA_AES128CCM8_SHA256
+      , TE.cipher_ECDHE_ECDSA_AES256CCM8_SHA256
+      ]
+    browserGroups =
+      [ T.P256
+      ]
+    browserSigs =
+      [ (T.HashSHA256, T.SignatureECDSA),
+        (T.HashSHA384, T.SignatureECDSA)
+      ]
+```
+
+This may not be enough for other certificate providers.
+
+## Configuration
+
+> XXX: This is for the current implementation and should be updated.
+
+Web certificate chain is picked up from the WEB section:
+
+```ini
+[TRANSPORT]
+port: 443
+
+[WEB]
+https: 443
+cert: /etc/opt/simplex/web.cert
+key: /etc/opt/simplex/web.key
+
+# Alternatively, with a proper access configuration, the paths can point to the LE creds directly:
+# cert: /etc/letsencrypt/live/smp.hostname.tld/fullchain.pem
+# key: /etc/letsencrypt/live/smp.hostname.tld/privkey.pem
+```
+
+When `TRANSPORT.port` matches `WEB.https` the transport router becomes shared.
+
+Perhaps a more desirable option would be explicit configuration resulting in additional transported to run:
+
+```ini
+[TRANSPORT]
+port: 5223 ; pure protocol transport
+# control_port: 5224
+shared_port: 443 ; variant 1: register in TRANSPORT
+
+[WEB]
+https: 443
+cert: /etc/opt/simplex/web.cert
+key: /etc/opt/simplex/web.key
+# transport: on ; variant 2:
+```
+
+## Caveats
+
+Serving static files and the protocols together may pose a problem for those who currently use dedicated web servers as they should switch to embedded http handlers.
+
+As before, using embedded HTTP server is increasing attack surface.
+
+Users who want to run everything on a single host will have to add an extra IP address and bind routers to specific IPs instead of 0.0.0.0.
+An amalgamated router binary can be provided that would contain both SMP and XFTP routers, where transport will dispatch connections by handshake ALPN.
+
+## Alternative: Use transports routable with reverse-proxies
+
+An "industrial" reverse proxy may do the ALPN routing, serving HTTP by itself and delegating `smp` and `xftp` to protocol servers.
+Same with the `websockets`.
+
+Since this in effect does TLS termination, the protocol routers will have to rely on credentials from protocol handshakes.

plans/done/2024-11-25-journal-expiration.md

@@ -0,0 +1,16 @@
+
+# Expiring messages in journal storage
+
+## Problem
+
+The journal storage routers recently migrated to do not delete delivered or expired messages, they only update pointers to journal file lines. The messages are actually deleted when the whole journal file is deleted (when fully deleted or fully expired).
+
+The problem is that in case the queue stops receiving the new messages then writing of messages won't switch to the new journal file, and the current journal file containing delivered or expired messages would never be deleted.
+
+## Solution
+
+Remove current journal file and update queue_state.log during message expiration of "idle" queue (that is, without any new messages received or delivered within 3 hours) in case when:
+- the queue is "empty" after the expiration
+- the queue contains only quota marker(s), in which case move them to a new journal file and update the queue_state accordingly. Quota markers can be kept indefinitely to prevent writing the new messages to the dormant queues that reached capacity, so it's important to handle this case.
+
+Also remove current journal file when the queue is opened in case it is empty (as it would not be ever expired in case it remains empty), and also update queue_state.log

plans/done/2026-02-17-fix-subq-deadlock.md

@@ -0,0 +1,416 @@
+
+# Fix subQ deadlock: blocking writeTBQueue inside connLock
+
+## Problem
+
+Users report that message reception silently and permanently stops across all connections, with no error alerts. The app appears functional but no messages arrive. Recovery requires restart.
+
+Root cause: a deadlock between worker threads holding `connLock` and the `agentSubscriber` (sole `subQ` reader).
+
+### The deadlock mechanism
+
+`subQ` (`TBQueue ATransmission`, capacity 4096 on mobile / 1024 on desktop) is the single pipeline between the agent layer and the chat layer. The `agentSubscriber` thread (`Commands.hs:4373`) is its **sole reader**.
+
+Three code sites hold `connLock` and call blocking `writeTBQueue subQ` without a fullness check. When `subQ` is full, these block while holding the lock. If `agentSubscriber` simultaneously needs the same `connLock` (via `sendMessagesB_` → `withConnLocks`), it blocks too — creating a circular wait:
+
+- **Worker**: holds `connLock(X)`, waits for `subQ` space (needs `agentSubscriber` to read)
+- **agentSubscriber**: sole `subQ` reader, waits for `connLock(X)` (needs worker to release)
+- **Result**: permanent silent deadlock — no exception, no alert, all connections blocked
+
+### Confirmed deadlock scenarios
+
+**Scenario 1**: Delivery worker during queue rotation test
+
+```
+Delivery worker:                    agentSubscriber (sole subQ reader):
+  withConnLock(X) [2187]              readTBQueue subQ → processAgentMessageConn
+  ...DB operations...                 → sendPendingGroupMessages (on CON/SENT/QCONT)
+  notify → writeTBQueue subQ [2238]   → batchSendConnMessages → deliverMessagesB
+  [BLOCKED — subQ full]               → withAgent sendMessagesB [synchronous]
+                                      → sendMessagesB_ → withConnLocks({..X..}) [1708]
+                                      [BLOCKED — connLock(X) held]
+```
+
+**Scenario 2**: Async command worker during message ACK with notification
+
+```
+Async cmd worker:                   agentSubscriber (sole subQ reader):
+  tryWithLock "ICAck" [1930→1824]     readTBQueue subQ → processAgentMessageConn
+  → withConnLock(X)                   → sendPendingGroupMessages
+  → ack → ackQueueMessage [1899]      → sendMessagesB_ → withConnLocks({..X..})
+  → sendMsgNtf [2381]                [BLOCKED — connLock(X) held]
+  → writeTBQueue subQ [2386]
+  [BLOCKED — subQ full]
+```
+
+**Scenario 3**: Synchronous `ackMessage'` API (same mechanism as Scenario 2 but from external API caller)
+
+```
+ackMessage' caller:                 agentSubscriber (sole subQ reader):
+  withConnLock(X) [2254]              → sendMessagesB_ → withConnLocks({..X..})
+  → ack → ackQueueMessage [2267]      [BLOCKED — connLock(X) held]
+  → sendMsgNtf [2381]
+  → writeTBQueue subQ [2386]
+  [BLOCKED — subQ full]
+```
+
+### ConnId overlap verified
+
+No guard prevents a connection undergoing queue rotation (AM_QTEST_) or ACK processing from being included in `sendMessagesB_`'s batch. During these operations, the connection has `connStatus == ConnReady`, passing all filters in `memberSendAction`.
+
+### Cascade amplification
+
+Once any single deadlock triggers, `subQ` never drains. ALL other threads that attempt `writeTBQueue subQ` block progressively — their locks are held forever too. The entire threading system freezes within seconds.
+
+### Affected code sites (blocking `writeTBQueue subQ` inside `connLock`)
+
+| Site | File | Lock line | Write line | Events written |
+|------|------|-----------|------------|----------------|
+| `runSmpQueueMsgDelivery::notify` | Agent.hs | 2187 | 2238 | SWITCH SPCompleted, ERR INTERNAL |
+| `runSmpQueueMsgDelivery::internalErr/notifyDel` | Agent.hs | 2187 | 2238 (via notifyDel→notify) | ERR INTERNAL + delMsg |
+| `ackQueueMessage::sendMsgNtf` | Agent.hs | 2254 or 1930 | 2386 | MSGNTF |
+
+### Safe patterns that already exist in the codebase
+
+1. **`isFullTBQueue` + pending TVar** (used at `runCommandProcessing` lines 1782-1784/1937, and `runProcessSMP` lines 3027-3029/3216):
+   ```haskell
+   -- Before processing (e.g. line 1782):
+   pending <- newTVarIO []
+   -- During processing — safe notify (e.g. line 1937):
+   notify cmd =
+     let t = (corrId, connId, AEvt (sAEntity @e) cmd)
+      in atomically $ ifM (isFullTBQueue subQ) (modifyTVar' pendingCmds (t :)) (writeTBQueue subQ t)
+   -- After processing — flush (e.g. line 1784):
+   mapM_ (atomically . writeTBQueue subQ) . reverse =<< readTVarIO pending
+   ```
+
+2. **`nonBlockingWriteTBQueue`** (used at Client.hs:789, NtfSubSupervisor.hs:507):
+   ```haskell
+   nonBlockingWriteTBQueue q x = do
+     sent <- atomically $ tryWriteTBQueue q x
+     unless sent $ void $ forkIO $ atomically $ writeTBQueue q x
+   ```
+   Note: `nonBlockingWriteTBQueue` does NOT preserve ordering — the spawned background thread may complete out of order relative to subsequent direct writes from the same calling thread.
+
+### Exhaustive proof: no other deadlock scenarios exist
+
+All 15 `withConnLock` sites in Agent.hs were analyzed. Only 3 write to `subQ`:
+
+| withConnLock site | Writes subQ? | Safe? |
+|-------------------|-------------|-------|
+| switchConnectionAsync' (899) | No | ✓ |
+| setConnShortLinkAsync' (995) | No | ✓ |
+| setConnShortLink' (1031) | No | ✓ |
+| deleteConnShortLink' (1075) | No | ✓ |
+| allowConnection' (1407) | No | ✓ |
+| acceptContact' (1417) | No | ✓ |
+| sendMessagesB_ (1708, `withConnLocks`) | No | ✓ |
+| tryWithLock/runSmpCommand (1930) | Yes (1937) | ✓ — `isFullTBQueue` check |
+| tryMoveableWithLock/runSmpCommand (1931) | Yes (1937) | ✓ — `isFullTBQueue` check |
+| **runSmpQueueMsgDelivery AM_QTEST_ (2187)** | **Yes (2238)** | **✗ — DEADLOCK** |
+| **ackMessage' (2254)** | **Yes (2386)** | **✗ — DEADLOCK** |
+| switchConnection' (2298) | No | ✓ |
+| abortConnectionSwitch' (2328) | No | ✓ |
+| synchronizeRatchet' (2351) | No | ✓ |
+| suspendConnection' (2390) | No | ✓ |
+| **processSMP (3037)** | Yes (3216) | ✓ — `isFullTBQueue` check |
+
+Note: `processSMP` (line 3037) holds `connLock` and its local `notify` (line 3216) writes to `subQ`, but it uses the safe `isFullTBQueue` pattern. Its `ack` (line 3196) uses `enqueueCmd` (DB-only), NOT `ackQueueMessage`. The actual `ackQueueMessage` runs later from the async command worker via ICAck/ICAckDel.
+
+Other lock pairs checked — no circular dependencies:
+- `connLock × DB MVar`: DB never acquires connLock
+- `entityLock × connLock`: consistent ordering (entity first in chat, conn in agent)
+- `connLock(X) × connLock(Y)`: single agentSubscriber thread, one `withConnLocks` at a time
+
+---
+
+## Deadlock call graph: agentSubscriber → connLock
+
+All deadlock paths require `agentSubscriber` to synchronously acquire `connLock`. Exhaustive analysis shows that **every such path converges on a single agent function**: `sendMessagesB_` → `withConnLocks` (Agent.hs:1708). No other agent API function called synchronously from the agentSubscriber acquires connLock.
+
+Verified (FACT): `ackMessageAsync` → `enqueueCommand` only (no connLock). `toggleConnectionNtfs` → no lock. `deleteConnectionAsync` → `deleteLock` not `connLock`. `joinConnectionAsync` → `withInvLock` not `connLock`.
+
+Also verified (FACT): `Lock = TMVar Text` (Lock.hs:24) is **non-reentrant** — double acquisition on the same thread deadlocks.
+
+### All 22 trigger paths
+
+Every path goes through `deliverMessage`/`deliverMessages`/`deliverMessagesB` → `withAgent sendMessagesB` → `sendMessagesB_` → `withConnLocks`:
+
+| # | Trigger | Chat function | ConnIds locked | Risk |
+|---|---------|--------------|----------------|------|
+| 1 | Group CON (Invitee) | `introduceToAll` → broadcast XGrpMemNew | **ALL member connIds** | **HIGHEST** |
+| 2 | Group MSG XGrpLinkAcpt | `introduceToRemaining` → broadcast | **ALL member connIds** | **HIGHEST** |
+| 3 | Group CON (Invitee) | `sendIntroductions` → batch intros to new member | new member connId | Medium |
+| 4 | Group CON (Invitee) | `sendHistory` → batch to new member | new member connId | Medium |
+| 5 | Group CON | `sendPendingGroupMessages` | member connId | Medium |
+| 6 | Group SENT | `sendPendingGroupMessages` | member connId | Medium |
+| 7 | Group QCONT | `sendPendingGroupMessages` | member connId | Medium |
+| 8 | Group CON (PendingReview) | `introduceToModerators` → to moderators | moderator connIds | Medium |
+| 9 | Group CON (PreMember) | `sendXGrpMemCon` → to host | host connId | Low |
+| 10 | Group CON (PreMember) | `probeMatchingMemberContact` → probes + hashes | member + N matching connIds | Medium |
+| 11 | Direct CON | `probeMatchingMembers` → probes + hashes | contact + N matching connIds | Medium |
+| 12 | Direct JOINED | `sendAutoReply` | contact connId | Low |
+| 13 | Group JOINED | `sendGroupAutoReply` | member connId | Low |
+| 14 | Group INV | `sendXGrpMemInv` → to host | host connId | Low |
+| 15 | Group INV (legacy) | `sendGrpInvitation` → to contact | contact connId | Low |
+| 16 | Group MSG XGrpMemInv | `xGrpMemInv` → `sendGroupMemberMessage` | re-member connId | Low |
+| 17 | Group MSG XGrpMemDel | `forwardToMember` | deleted member connId | Low |
+| 18 | Group MSG XGrpLinkMem | `probeMatchingMemberContact` | member + N matching connIds | Medium |
+| 19 | Group MSG (dup relay) | `saveGroupRcvMsg` error → `sendDirectMemberMessage` | forwarder connId | Low |
+| 20 | SFDONE | `sendFileDescriptions` → to recipients | recipient connIds | Medium |
+| 21 | Group MSG XGrpLinkAcpt | `sendHistory` → to accepted member | accepted member connId | Medium |
+| 22 | Direct MSG (autoAccept) | `autoAcceptFile` → inline accept reply | contact connId | Low (test-only config) |
+
+### Key observations
+
+1. **Single bottleneck**: All 22 paths converge on `sendMessagesB_` → `withConnLocks` (Agent.hs:1708). The deadlock is between this lock acquisition and any worker thread holding `connLock` + blocking on `writeTBQueue subQ`.
+
+2. **Highest-risk paths** (#1, #2): Broadcasting to ALL group members in `introduceToAll` / `introduceToRemaining` acquires `withConnLocks` on ALL member connIds in a single batch. For large groups, this holds the agentSubscriber thread for a long time, during which subQ fills, which causes worker threads holding connLock on any of those connIds to deadlock.
+
+3. **Medium-risk paths** (#5-7): `sendPendingGroupMessages` fires on every CON/SENT/QCONT. These are frequent and lock the member's connId, which is the SAME connId that a delivery worker or ACK worker may hold while writing to subQ.
+
+---
+
+## Analysis: `withConnLocks` in `sendMessagesB_`
+
+### FACT: the lock protects ratchet encryption state
+
+`sendMessagesB_` (Agent.hs:1708-1713) acquires `withConnLocks` and executes:
+
+1. **`getConn_`** — reads connection metadata, send queues from DB
+2. **`setConnPQSupport`** — updates PQ encryption flag per connection
+3. **`enqueueMessagesB`** → `enqueueMessageB` → `storeSentMsg_` which calls:
+   - **`updateSndIds`** (AgentStore.hs:899) — increments `internalSndId` (sequential send counter)
+   - **`agentRatchetEncryptHeader`** (Agent.hs:3698) — reads current ratchet via `getRatchetForUpdate`, encrypts message header via `rcEncryptHeader`, writes advanced ratchet state via `updateRatchet`
+   - **`createSndMsg`** + **`createSndMsgDelivery`** — inserts message and delivery records
+
+All operations run within `unsafeWithStore` → `withTransaction` (single DB transaction per batch).
+
+### FACT: the lock CANNOT be removed
+
+Without `withConnLocks`, concurrent `sendMessagesB_` calls targeting the same connection would:
+- Read the same ratchet state, both encrypt, one overwrite the other → **ratchet desync** (unrecoverable)
+- Get duplicate `internalSndId` values → **message ID collision**
+- Race on `setConnPQSupport` → **PQ state inconsistency**
+
+The lock serializes ALL operations on the connection's encryption state. Removing it would introduce data corruption.
+
+Note: `sendMessage` (singular, line 530) uses the same `sendMessagesB_` function — there is no lock-free send path.
+
+### Eliminated strategies
+
+- **Strategy C (remove lock)**: The lock protects ratchet encryption. Removing it causes unrecoverable ratchet desync. Eliminated.
+- **Strategy A (async dispatch)**: All 22 chat-layer callers use `deliverMessagesB` return values (delivery IDs, PQ state) synchronously. `forkIO` loses results. Eliminated.
+- **Strategy W (isFullTBQueue + pending TVar)**: The existing pattern (lines 1937, 3216) buffers events in a local TVar and flushes after lock release. Between lock release and flush, another thread can acquire the same connLock and write events to subQ — reordering events within the same connection. This trades a visible deadlock for invisible ordering bugs. Eliminated.
+- **Strategy O (per-connection overflow queues)**: Bounded overflow queues with "drop when full" were analyzed. Drop consequences are unacceptable at 5 of 6 write sites — CONF, INFO, CON cause permanent connection failure after ACK; INV loses connection invitations; SENT/MERR leave messages stuck forever. Unbounded overflow defeats backpressure. Eliminated.
+
+---
+
+## Solution: move subQ writes outside connLock
+
+### Root cause
+
+The `writeTBQueue subQ` calls at the 3 deadlock sites are inside `connLock` by accident of code structure, not necessity. `connLock` protects ratchet encryption state and DB consistency. The `notify` calls write informational events to `subQ` — they do not modify any state that `connLock` protects.
+
+Moving the writes outside the lock scope eliminates the deadlock: blocking `writeTBQueue subQ` without holding `connLock` is safe — agentSubscriber is free to acquire the lock, process events, and drain `subQ`.
+
+### Why reordering doesn't matter at these sites
+
+The chat layer handlers for the 3 deadlock site events do NOT advance the ratchet:
+
+| Event | Chat handler | Calls sendMessagesB_? |
+|-------|-------------|----------------------|
+| SWITCH SPCompleted | Creates internal chat item, updates UI | **No** |
+| ERR INTERNAL | Logs error to view | **No** |
+| MSGNTF | `toView CEvtNtfMessage` → empty output | **No** |
+
+Events that DO trigger ratchet advances (CON, SENT, QCONT → `sendPendingGroupMessages` → `sendMessagesB_`) are all already written OUTSIDE `connLock` in the current code.
+
+Ratchet state lives in the DB, not in subQ events. agentSubscriber processes events sequentially regardless of arrival order. The SENT-before-SWITCH race already exists in the current code (new queue worker writes SENT outside connLock while old queue worker writes SWITCH inside connLock).
+
+### Fix: Site 1 — `runSmpQueueMsgDelivery` AM_QTEST_ (line 2187)
+
+Restructure `withConnLock` to return the event, write outside.
+
+**Current code** (Agent.hs:2187-2214):
+```haskell
+AM_QTEST_ -> withConnLock c connId "runSmpQueueMsgDelivery AM_QTEST_" $ do
+  withStore' c $ \db -> setSndQueueStatus db sq Active
+  SomeConn _ conn <- withStore c (`getConn` connId)
+  case conn of
+    DuplexConnection cData' rqs sqs -> do
+      let addr = qAddress sq
+      case findQ addr sqs of
+        Just SndQueue {dbReplaceQueueId = Just replacedId, primary} ->
+          case removeQP (\sq' -> dbQId sq' == replacedId && not (sameQueue addr sq')) sqs of
+            Nothing -> internalErr msgId "sent QTEST: queue not found in connection"
+            Just (sq', sq'' : sqs') -> do
+              checkSQSwchStatus sq' SSSendingQTEST
+              atomically $ TM.delete (qAddress sq') $ smpDeliveryWorkers c
+              withStore' c $ \db -> do
+                when primary $ setSndQueuePrimary db connId sq
+                deletePendingMsgs db connId sq'
+                deleteConnSndQueue db connId sq'
+              let sqs'' = sq'' :| sqs'
+                  conn' = DuplexConnection cData' rqs sqs''
+              cStats <- connectionStats c conn'
+              notify $ SWITCH QDSnd SPCompleted cStats       -- DEADLOCK
+            _ -> internalErr msgId "sent QTEST: ..."         -- DEADLOCK (via notifyDel → notify)
+        _ -> internalErr msgId "sent QTEST: ..."             -- DEADLOCK
+    _ -> internalErr msgId "QTEST sent not in duplex ..."    -- DEADLOCK
+```
+
+**New code:**
+```haskell
+AM_QTEST_ -> do
+  evt_ <- withConnLock c connId "runSmpQueueMsgDelivery AM_QTEST_" $ do
+    withStore' c $ \db -> setSndQueueStatus db sq Active
+    SomeConn _ conn <- withStore c (`getConn` connId)
+    case conn of
+      DuplexConnection cData' rqs sqs -> do
+        let addr = qAddress sq
+        case findQ addr sqs of
+          Just SndQueue {dbReplaceQueueId = Just replacedId, primary} ->
+            case removeQP (\sq' -> dbQId sq' == replacedId && not (sameQueue addr sq')) sqs of
+              Nothing -> pure $ Left "sent QTEST: queue not found in connection"
+              Just (sq', sq'' : sqs') -> do
+                checkSQSwchStatus sq' SSSendingQTEST
+                atomically $ TM.delete (qAddress sq') $ smpDeliveryWorkers c
+                withStore' c $ \db -> do
+                  when primary $ setSndQueuePrimary db connId sq
+                  deletePendingMsgs db connId sq'
+                  deleteConnSndQueue db connId sq'
+                let sqs'' = sq'' :| sqs'
+                    conn' = DuplexConnection cData' rqs sqs''
+                cStats <- connectionStats c conn'
+                pure $ Right $ SWITCH QDSnd SPCompleted cStats
+              _ -> pure $ Left "sent QTEST: there is only one queue in connection"
+          _ -> pure $ Left "sent QTEST: queue not in connection or not replacing another queue"
+      _ -> pure $ Left "QTEST sent not in duplex connection"
+  -- subQ write is now OUTSIDE connLock — blocking writeTBQueue is safe
+  case evt_ of
+    Right evt -> notify evt
+    Left err -> internalErr msgId err
+```
+
+All DB operations remain inside the lock. Only `notify`/`internalErr` (which write to subQ) move outside. `internalErr` calls `notifyDel` = `notify >> delMsg` — both `notify` (subQ write) and `delMsg` (`deleteSndMsgDelivery`, keyed on unique msgId) are safe outside the lock. The existing double-delete pattern (`delMsg` inside `internalErr` + `delMsgKeep` at line 2216) is preserved.
+
+### Fix: Sites 2 & 3 — `ackQueueMessage::sendMsgNtf` (line 2386)
+
+Change `ackQueueMessage` to return the MSGNTF event instead of writing it to subQ. Callers write to subQ after releasing connLock.
+
+**Current code** (Agent.hs:2371-2386):
+```haskell
+ackQueueMessage :: AgentClient -> RcvQueue -> SMP.MsgId -> AM ()
+ackQueueMessage c rq@RcvQueue {userId, connId, server} srvMsgId = do
+  atomically $ incSMPServerStat c userId server ackAttempts
+  tryAllErrors (sendAck c rq srvMsgId) >>= \case
+    Right _ -> sendMsgNtf ackMsgs
+    Left (SMP _ SMP.NO_MSG) -> sendMsgNtf ackNoMsgErrs
+    Left e -> ...
+  where
+    sendMsgNtf stat = do
+      atomically $ incSMPServerStat c userId server stat
+      whenM (liftIO $ hasGetLock c rq) $ do
+        atomically $ releaseGetLock c rq
+        brokerTs_ <- eitherToMaybe <$> tryAllErrors (withStore c $ \db -> getRcvMsgBrokerTs db connId srvMsgId)
+        atomically $ writeTBQueue (subQ c) ("", connId, AEvt SAEConn $ MSGNTF srvMsgId brokerTs_)
+```
+
+**New code** — return `Maybe ATransmission` instead of writing:
+```haskell
+ackQueueMessage :: AgentClient -> RcvQueue -> SMP.MsgId -> AM (Maybe ATransmission)
+ackQueueMessage c rq@RcvQueue {userId, connId, server} srvMsgId = do
+  atomically $ incSMPServerStat c userId server ackAttempts
+  tryAllErrors (sendAck c rq srvMsgId) >>= \case
+    Right _ -> sendMsgNtf ackMsgs
+    Left (SMP _ SMP.NO_MSG) -> sendMsgNtf ackNoMsgErrs
+    Left e -> ... >> pure Nothing
+  where
+    sendMsgNtf stat = do
+      atomically $ incSMPServerStat c userId server stat
+      ifM (liftIO $ hasGetLock c rq)
+        (do atomically $ releaseGetLock c rq
+            brokerTs_ <- eitherToMaybe <$> tryAllErrors (withStore c $ \db -> getRcvMsgBrokerTs db connId srvMsgId)
+            pure $ Just ("", connId, AEvt SAEConn $ MSGNTF srvMsgId brokerTs_))
+        (pure Nothing)
+```
+
+**Caller 1: `ackMessage'`** (Agent.hs:2253-2267) — return event from `withConnLock`, write after:
+```haskell
+ackMessage' c connId msgId rcptInfo_ = do
+  t_ <- withConnLock c connId "ackMessage" $ do
+    SomeConn _ conn <- withStore c (`getConn` connId)
+    case conn of
+      DuplexConnection {} -> do
+        t_ <- ack
+        sendRcpt conn
+        del
+        pure t_
+      RcvConnection {} -> do
+        t_ <- ack
+        del
+        pure t_
+      SndConnection {} -> throwE $ CONN SIMPLEX "ackMessage"
+      ContactConnection {} -> throwE $ CMD PROHIBITED "ackMessage: ContactConnection"
+      NewConnection _ -> throwE $ CMD PROHIBITED "ackMessage: NewConnection"
+  -- subQ write is OUTSIDE connLock
+  case t_ of
+    Just t -> atomically $ writeTBQueue (subQ c) t
+    Nothing -> pure ()
+```
+
+**Caller 2: `ICAck` / `ICAckDel`** (Agent.hs:1823-1824) — inline `tryWithLock` as `tryCommand` + `withConnLock`, write subQ between the two scopes:
+
+`tryWithLock name = tryCommand . withConnLock c connId name` — by inlining, the subQ write can be placed outside `withConnLock` but inside `tryCommand` (retaining retry/error handling).
+
+```haskell
+ICAck rId srvMsgId -> withServer $ \srv ->
+  tryCommand $ do
+    t_ <- withConnLock c connId "ICAck" $ ack srv rId srvMsgId
+    -- subQ write is OUTSIDE connLock — cannot deadlock with agentSubscriber
+    forM_ t_ $ atomically . writeTBQueue subQ
+
+ICAckDel rId srvMsgId msgId -> withServer $ \srv ->
+  tryCommand $ do
+    t_ <- withConnLock c connId "ICAckDel" $ do
+      t_ <- ack srv rId srvMsgId
+      withStore' c (\db -> deleteMsg db connId msgId)
+      pure t_
+    -- subQ write is OUTSIDE connLock — cannot deadlock with agentSubscriber
+    forM_ t_ $ atomically . writeTBQueue subQ
+```
+
+Where `ack` now returns `AM (Maybe ATransmission)`:
+```haskell
+ack srv rId srvMsgId = do
+  rq <- withStore c $ \db -> getRcvQueue db connId srv rId
+  ackQueueMessage c rq srvMsgId
+```
+
+All subQ writes for MSGNTF are now outside connLock. FIFO ordering is preserved — no `nonBlockingWriteTBQueue`, no forked threads. The same thread that held the lock writes to subQ sequentially after releasing it.
+
+### Race analysis
+
+Window between connLock release and subQ write at Site 1:
+
+| Thread | Can acquire connLock(X)? | Writes subQ? | Consequence |
+|--------|-------------------------|-------------|-------------|
+| agentSubscriber via sendMessagesB_ | Yes | **No** (encrypts only) | No race |
+| processSMP for connId X | Yes | Yes (pending flush) | MSG before SWITCH — cosmetic |
+| runCommandProcessing for connId X | Yes | Yes (pending flush) | Command response before SWITCH — cosmetic |
+| New queue delivery worker | No (SENT outside lock) | Yes | SENT before SWITCH — cosmetic, **already exists in current code** |
+
+All races are cosmetic UI ordering. None affect ratchet state, protocol correctness, or message delivery.
+
+### Summary of changes
+
+| File | Change | Lines affected |
+|------|--------|---------------|
+| Agent.hs | Restructure AM_QTEST_ to return event from `withConnLock`, write outside | ~2187-2214 |
+| Agent.hs | Change `ackQueueMessage` return type to `AM (Maybe ATransmission)`, return event instead of writing | ~2371-2386 |
+| Agent.hs | `ackMessage'`: return event from `withConnLock`, write outside | ~2253-2267 |
+| Agent.hs | `ICAck`/`ICAckDel`: inline `tryCommand` + `withConnLock`, write subQ between scopes | ~1823-1824 |
+| Agent.hs | `ack` helper: propagate new return type | ~1899-1901 |
+
+No new data structures. No new modules. No changes to other write sites (1937, 3216 — already safe). ~25 lines changed total.

protocol/diagrams/duplex-messaging/duplex-creating-fast.mmd

@@ -0,0 +1,65 @@
+sequenceDiagram
+  participant A as Alice
+  participant AA as Alice's<br>agent
+  participant AS as Alice's<br>server
+  participant BS as Bob's<br>server
+  participant BA as Bob's<br>agent
+  participant B as Bob
+
+  note over AA, BA: status (receive/send): NONE/NONE
+
+  note over A, AA: 1. request connection<br>from agent
+  A ->> AA: createConnection
+ 
+  note over AA, AS: 2. create Alice's SMP queue
+  AA ->> AS: NEW: create SMP queue<br>allow sender to secure
+  AS ->> AA: IDS: SMP queue IDs
+  note over AA: status: NEW/NONE
+
+  AA ->> A: INV: invitation<br>to connect
+
+  note over A, B: 3. out-of-band invitation
+  A ->> B: OOB: invitation to connect
+
+  note over BA, B: 4. accept connection
+  B ->> BA: joinConnection:<br>via invitation info
+  note over BA: status: NONE/NEW
+
+  note over BA, AS: 5. secure Alice's SMP queue
+  BA ->> AS: SKEY: secure queue (this command needs to be proxied)
+  note over BA: status: NONE/SECURED
+
+  note over BA, BS: 6. create Bob's SMP queue
+  BA ->> BS: NEW: create SMP queue<br>allow sender to secure
+  BS ->> BA: IDS: SMP queue IDs
+  note over BA: status: NEW/SECURED
+
+  note over BA, AA: 7. confirm Alice's SMP queue
+  BA ->> AS: SEND: Bob's info without sender's key (SMP confirmation with reply queues)
+  note over BA: status: NEW/CONFIRMED
+
+  AS ->> AA: MSG: Bob's info without<br>sender server key
+  note over AA: status: CONFIRMED/NEW
+  AA ->> AS: ACK: confirm message
+  AA ->> A: CONF: connection request ID<br>and Bob's info
+  A -> AA: allowConnection: accept connection request,<br>send Alice's info
+  
+  note over AA, BS: 8. secure Bob's SMP queue
+  AA ->> BS: SKEY: secure queue (this command needs to be proxied)
+  note over BA: status: CONFIRMED/SECURED
+
+  AA ->> BS: SEND: Alice's info without sender's server key (SMP confirmation without reply queues)
+  note over AA: status: CONFIRMED/CONFIRMED
+
+  note over AA, A: 9. notify Alice<br>about connection success<br>(no HELLO needed in v6)
+  AA ->> A: CON: connected
+  note over AA: status: ACTIVE/ACTIVE
+
+  note over BA, B: 10. notify Bob<br>about connection success
+  BS ->> BA: MSG: Alice's info without<br>sender's server key
+  note over BA: status: CONFIRMED/CONFIRMED
+  BA ->> B: INFO: Alice's info
+  BA ->> BS: ACK: confirm message
+
+  BA ->> B: CON: connected
+  note over BA: status: ACTIVE/ACTIVE

protocol/diagrams/duplex-messaging/duplex-creating-v2.mmd

@@ -1,71 +0,0 @@
-sequenceDiagram
-  participant A as Alice
-  participant AA as Alice's<br>agent
-  participant AS as Alice's<br>server
-  participant BS as Bob's<br>server
-  participant BA as Bob's<br>agent
-  participant B as Bob
-
-  note over AA, BA: status (receive/send): NONE/NONE
-
-  note over A, AA: 1. request connection<br>from agent
-  A ->> AA: NEW: create<br>duplex connection
- 
-  note over AA, AS: 2. create Alice's SMP queue
-  AA ->> AS: NEW: create SMP queue
-  AS ->> AA: IDS: SMP queue IDs
-  note over AA: status: NEW/NONE
-
-  AA ->> A: INV: invitation<br>to connect
-
-  note over A, B: 3. out-of-band invitation
-  A ->> B: OOB: invitation to connect
-
-  note over BA, B: 4. accept connection
-  B ->> BA: JOIN:<br>via invitation info
-  note over BA: status: NONE/NEW
-
-  note over BA, BS: 5. create Bob's SMP queue
-  BA ->> BS: NEW: create SMP queue
-  BS ->> BA: IDS: SMP queue IDs
-  note over BA: status: NEW/NEW
-
-  note over BA, AA: 6. establish Alice's SMP queue
-  BA ->> AS: SEND: Bob's info and sender server key (SMP confirmation with reply queues)
-  note over BA: status: NEW/CONFIRMED
-
-  AS ->> AA: MSG: Bob's info and<br>sender server key
-  note over AA: status: CONFIRMED/NONE
-  AA ->> AS: ACK: confirm message
-  AA ->> A: CONF: connection request ID<br>and Bob's info
-  A ->> AA: LET: accept connection request,<br>send Alice's info
-  AA ->> AS: KEY: secure queue
-  note over AA: status: SECURED/NONE
-
-  AA ->> BS: SEND: Alice's info and sender's server key (SMP confirmation without reply queues)
-  note over AA: status: SECURED/CONFIRMED
-
-  BS ->> BA: MSG: Alice's info and<br>sender's server key
-  note over BA: status: CONFIRMED/CONFIRMED
-  BA ->> B: INFO: Alice's info
-  BA ->> BS: ACK: confirm message
-  BA ->> BS: KEY: secure queue
-  note over BA: status: SECURED/CONFIRMED
-
-  BA ->> AS: SEND: HELLO: only needs to be sent once in v2
-
-  note over BA: status: SECURED/ACTIVE
-  note over BA, B: 7a. notify Bob<br>about connection success
-  BA ->> B: CON: connected
-
-  AS ->> AA: MSG: HELLO: Alice's agent<br>knows Bob can send
-  note over AA: status: SECURED/ACTIVE
-  AA ->> AS: ACK: confirm message
-  note over A, AA: 7a. notify Alice<br>about connection success
-  AA ->> A: CON: connected
-
-  AA ->> BS: SEND: HELLO: only needs to be sent once in v2
-  note over AA: status: ACTIVE/ACTIVE
-  BS ->> BA: MSG: HELLO: Bob's agent<br>knows Alice can send
-  note over BA: status: ACTIVE/ACTIVE
-  BA ->> BS: ACK: confirm message

protocol/diagrams/duplex-messaging/duplex-creating.mmd

@@ -8,8 +8,8 @@ sequenceDiagram
 
   note over AA, BA: status (receive/send): NONE/NONE
 
-  note over A, AA: 1. request connection from agent
-  A ->> AA: NEW: create<br>duplex connection
+  note over A, AA: 1. request connection<br>from agent
+  A ->> AA: createConnection
  
   note over AA, AS: 2. create Alice's SMP queue
   AA ->> AS: NEW: create SMP queue
@@ -17,63 +17,58 @@ sequenceDiagram
   note over AA: status: NEW/NONE
 
   AA ->> A: INV: invitation<br>to connect
-  note over AA: status: PENDING/NONE
 
   note over A, B: 3. out-of-band invitation
   A ->> B: OOB: invitation to connect
 
   note over BA, B: 4. accept connection
-  B ->> BA: JOIN:<br>via invitation info
+  B ->> BA: joinConnection:<br>via invitation info
   note over BA: status: NONE/NEW
 
-  note over BA, AA: 5. establish Alice's SMP queue
-  BA ->> AS: SEND: Bob's info and sender server key (SMP confirmation)
-  note over BA: status: NONE/CONFIRMED
-  activate BA
+  note over BA, BS: 5. create Bob's SMP queue
+  BA ->> BS: NEW: create SMP queue
+  BS ->> BA: IDS: SMP queue IDs
+  note over BA: status: NEW/NEW
+
+  note over BA, AA: 6. confirm Alice's SMP queue
+  BA ->> AS: SEND: Bob's info and sender server key (SMP confirmation with reply queues)
+  note over BA: status: NEW/CONFIRMED
+
   AS ->> AA: MSG: Bob's info and<br>sender server key
   note over AA: status: CONFIRMED/NONE
   AA ->> AS: ACK: confirm message
   AA ->> A: CONF: connection request ID<br>and Bob's info
-  A ->> AA: LET: accept connection request,<br>send Alice's info
+  A ->> AA: allowConnection: accept connection request,<br>send Alice's info
   AA ->> AS: KEY: secure queue
   note over AA: status: SECURED/NONE
 
-  BA ->> AS: SEND: HELLO: try sending until successful
-  deactivate BA
-  note over BA: status: NONE/ACTIVE
-  AS ->> AA: MSG: HELLO: Alice's agent<br>knows Bob can send
-  note over AA: status: ACTIVE/NONE
-  AA ->> AS: ACK: confirm message
+  AA ->> BS: SEND: Alice's info and sender's server key (SMP confirmation without reply queues)
+  note over AA: status: SECURED/CONFIRMED
 
-  note over BA, BS: 6. create Bob's SMP queue
-  BA ->> BS: NEW: create SMP queue
-  BS ->> BA: IDS: SMP queue IDs
-  note over BA: status: NEW/ACTIVE
-
-  note over AA, BA: 7. establish Bob's SMP queue
-  BA ->> AS: SEND: REPLY: invitation to the connect
-  note over BA: status: PENDING/ACTIVE
-  AS ->> AA: MSG: REPLY: invitation<br>to connect
-  note over AA: status: ACTIVE/NEW
-  AA ->> AS: ACK: confirm message
-
-  AA ->> BS: SEND: Alice's info and sender's server key
-  note over AA: status: ACTIVE/CONFIRMED
-  activate AA
+  note over BA, AA: 7. confirm Bob's SMP queue
   BS ->> BA: MSG: Alice's info and<br>sender's server key
-  note over BA: status: CONFIRMED/ACTIVE
+  note over BA: status: CONFIRMED/CONFIRMED
   BA ->> B: INFO: Alice's info
   BA ->> BS: ACK: confirm message
   BA ->> BS: KEY: secure queue
+  note over BA: status: SECURED/CONFIRMED
+
+  BA ->> AS: SEND: HELLO message
+
   note over BA: status: SECURED/ACTIVE
 
-  AA ->> BS: SEND: HELLO: try sending until successful
-  deactivate AA
+  AS ->> AA: MSG: HELLO: Alice's agent<br>knows Bob can send
+  note over AA: status: SECURED/ACTIVE
+  AA ->> AS: ACK: confirm message
+  AA ->> BS: SEND: HELLO
+
+  note over A, AA: 8. notify Alice<br>about connection success
+  AA ->> A: CON: connected
   note over AA: status: ACTIVE/ACTIVE
+
   BS ->> BA: MSG: HELLO: Bob's agent<br>knows Alice can send
   note over BA: status: ACTIVE/ACTIVE
   BA ->> BS: ACK: confirm message
 
-  note over A, B: 8. notify users about connection success
-  AA ->> A: CON: connected
+  note over BA, B: 9. notify Bob<br>about connection success
   BA ->> B: CON: connected

protocol/diagrams/duplex-messaging/queue-rotation-fast.mmd

@@ -0,0 +1,17 @@
+sequenceDiagram
+  participant A as Alice
+  participant R as Current server<br>that has A's<br>receive queue
+  participant R' as New server<br>that has the new A's<br>receive queue
+  participant S as Server<br>that has A's send queue<br>(B's receive queue)
+  participant B as Bob
+
+  A ->> R': NEW: create new queue<br>(allow SKEY)
+  A ->> S: SEND: QADD (R'): send address<br>of the new queue(s)
+  S ->> B: MSG: QADD (R')
+  B ->> R': SKEY: secure new queue
+  B ->> R': SEND: QTEST
+  R' ->> A: MSG: QTEST
+  A ->> R: DEL: delete the old queue
+  B ->> R': SEND: send messages to the new queue
+  R' ->> A: MSG: receive messages from the new queue
+  

protocol/diagrams/duplex-messaging/queue-rotation.mmd

@@ -0,0 +1,21 @@
+sequenceDiagram
+  participant A as Alice
+  participant R as Current server<br>that has A's<br>receive queue
+  participant R' as New server<br>that has the new A's<br>receive queue
+  participant S as Server<br>that has A's send queue<br>(B's receive queue)
+  participant B as Bob
+
+  A ->> R': NEW: create new queue
+  A ->> S: SEND: QADD (R'): send address<br>of the new queue(s)
+  S ->> B: MSG: QADD (R')
+  B ->> R: SEND: QKEY (R'): sender's key<br>for the new queue(s)
+  R ->> A: MSG: QKEY(R')
+  A ->> R': KEY: secure new queue
+  A ->> S: SEND: QUSE (R'): instruction to use new queue(s)
+  S ->> B: MSG: QUSE (R')
+  B ->> R': SEND: QTEST
+  R' ->> A: MSG: QTEST
+  A ->> R: DEL: delete the old queue
+  B ->> R': SEND: send messages to the new queue
+  R' ->> A: MSG: receive messages from the new queue
+  

protocol/diagrams/notifications/register-token-detailed.mmd

@@ -0,0 +1,30 @@
+sequenceDiagram
+  participant M as mobile app
+  participant C as chat core
+  participant A as agent
+  participant P as push server
+  participant APN as APN
+
+  note over M, APN: get device token
+  M ->> APN: registerForRemoteNotifications()
+  APN ->> M: device token
+
+  note over M, P: register device token with push server
+  M ->> C: /_ntf register <token>
+  C ->> A: registerNtfToken(<token>)
+  A ->> P: TNEW
+  P ->> A: ID (tokenId)
+  A ->> C: registered
+  C ->> M: registered
+
+  note over M, APN: verify device token
+  P ->> APN: E2E encrypted code<br>in background<br>notification
+  APN ->> M: deliver background notification with e2ee verification token
+  M ->> C: /_ntf verify <e2ee code>
+  C ->> A: verifyNtfToken(<e2ee code>)
+  A ->> P: TVFY code
+  P ->> A: OK / ERR
+  A ->> C: verified
+  C ->> M: verified
+
+  note over M, APN: now token ID can be used

protocol/diagrams/notifications/register-token.mmd

@@ -1,30 +1,26 @@
 sequenceDiagram
-  participant M as mobile app
-  participant C as chat core
+  participant C as client app
   participant A as agent
-  participant P as push server
-  participant APN as APN
+  participant P as SimpleX<br>Notification<br>Server
+  participant APN as Apple<br>Push Notifications<br>Server
 
-  note over M, APN: get device token
-  M ->> APN: registerForRemoteNotifications()
-  APN ->> M: device token
+  note over C, APN: get device token
+  C ->> APN: registerForRemoteNotifications()
+  APN ->> C: device token
 
-  note over M, P: register device token with push server
-  M ->> C: /_ntf register <token>
-  C ->> A: registerNtfToken(<token>)
+  note over C, P: register device token with push server
+  C ->> A: registerToken
   A ->> P: TNEW
   P ->> A: ID (tokenId)
   A ->> C: registered
-  C ->> M: registered
 
-  note over M, APN: verify device token
+  note over C, APN: verify device token
   P ->> APN: E2E encrypted code<br>in background<br>notification
-  APN ->> M: deliver background notification with e2ee verification token
-  M ->> C: /_ntf verify <e2ee code>
-  C ->> A: verifyNtfToken(<e2ee code>)
+  APN ->> C: deliver background notification with e2ee verification token
+  C ->> A: verifyToken<br>(<e2ee code>)
   A ->> P: TVFY code
   P ->> A: OK / ERR
   A ->> C: verified
-  C ->> M: verified
 
-  note over M, APN: now token ID can be used
+  note over C, APN: now token ID can be used
+  

protocol/diagrams/notifications/subscription-detailed.mmd

@@ -0,0 +1,40 @@
+sequenceDiagram
+  participant M as mobile app
+  participant C as chat core
+  participant A as agent
+  participant S as SMP server
+  participant N as NTF server
+  participant APN as APN
+
+  note over M, APN: register subscription
+
+  alt register existing
+    M -->> A: on /_ntf register, for subscribed queues
+  else create new connection
+    A -->> S: NEW / JOIN
+    note over A, S: ...<br>Connection handshake<br>...
+    S -->> A: CON
+  end
+  A ->> S: NKEY nKey
+  S ->> A: NID nId
+  A ->> N: SNEW tknId dhKey (smpServer, nId, nKey)
+  N ->> A: ID subId dhKey
+  N ->> S: NSUB nId
+  S ->> N: OK [/ NMSG]
+
+  note over M, APN: notify about message
+
+  S ->> N: NMSG
+  N ->> APN: APNSMutableContent<br>ntfQueue, nonce
+  APN ->> M: UNMutableNotificationContent
+  note over M, S: ...<br>Client awaken, message is received<br>...
+  S ->> M: message
+  note over M: mutate notification
+
+  note over M, APN: change APN token
+
+  APN ->> M: new device token
+  M -->> C: /_ntf_sub update tkn
+  C -->> A: updateNtfToken()
+  A -->> N: TUPD tknId newDeviceToken
+  note over M, N: ...<br>Verify token<br>...

protocol/diagrams/notifications/subscription.mmd

@@ -1,17 +1,16 @@
 sequenceDiagram
-  participant M as mobile app
-  participant C as chat core
+  participant C as client app
   participant A as agent
   participant S as SMP server
   participant N as NTF server
   participant APN as APN
 
-  note over M, APN: register subscription
+  note over C, APN: register subscription
 
   alt register existing
-    M -->> A: on /_ntf register, for subscribed queues
+    C -->> A: registerToken
   else create new connection
-    A -->> S: NEW / JOIN
+    A -->> S: create/joinConnection
     note over A, S: ...<br>Connection handshake<br>...
     S -->> A: CON
   end
@@ -20,21 +19,20 @@ sequenceDiagram
   A ->> N: SNEW tknId dhKey (smpServer, nId, nKey)
   N ->> A: ID subId dhKey
   N ->> S: NSUB nId
-  S ->> N: OK [/ NMSG]
+  S ->> N: OK / NMSG:<br>confirm subscription
 
-  note over M, APN: notify about message
+  note over C, APN: notify about message
 
   S ->> N: NMSG
   N ->> APN: APNSMutableContent<br>ntfQueue, nonce
-  APN ->> M: UNMutableNotificationContent
-  note over M, S: ...<br>Client awaken, message is received<br>...
-  S ->> M: message
-  note over M: mutate notification
+  APN ->> C: UNMutableNotificationContent
+  note over C, S: ...<br>Client awaken, message is received<br>...
+  S ->> C: message
+  note over C: show notification
 
-  note over M, APN: change APN token
+  note over C, APN: change APN token
 
-  APN ->> M: new device token
-  M -->> C: /_ntf_sub update tkn
-  C -->> A: updateNtfToken()
+  APN ->> C: new device token
+  C -->> A: updateToken()
   A -->> N: TUPD tknId newDeviceToken
-  note over M, N: ...<br>Verify token<br>...
+  note over C, N: ...<br>Verify token<br>...

protocol/diagrams/simplex-messaging/simplex-creating-fast.mmd

@@ -0,0 +1,23 @@
+sequenceDiagram
+  participant B as Bob (sender)
+  participant S as server (queue RID)
+  participant A as Alice (recipient)
+
+  note over A: creating queue<br>("public" key RK<br>for msg retrieval)
+  A ->> S: 1. create queue ("NEW")
+  S ->> A: respond with queue RID and SID ("IDS")
+
+  note over A: out-of-band msg<br>(sender's queue SID<br>and "public" key EK<br>to encrypt msgs)
+  A -->> B: 2. send out-of-band message
+
+  note over B: secure queue<br>(with "public" key SK for<br>sending messages)
+  B ->> S: 3. confirm queue ("SKEY" command authorized with SK)
+
+  note over B: confirm queue<br>(public key<br>for e2e encryption<br>and any optional<br>encrypted info.)
+  B ->> S: 4. confirm queue ("SEND" command authorized with SK)
+
+  S ->> A: 5. deliver Bob's message (MSG)
+  note over A: decrypt message<br>("private" key EK)
+  A ->> S: acknowledge message (ACK)
+
+  note over S: 6. simplex<br>queue RID<br>is ready to use!

protocol/diagrams/simplex-messaging/simplex-creating.mmd

@@ -10,11 +10,13 @@ sequenceDiagram
   note over A: out-of-band msg<br>(sender's queue SID<br>and "public" key EK<br>to encrypt msgs)
   A -->> B: 2. send out-of-band message
 
-  note over B: confirm queue<br>("public" key SK for<br>sending messages<br>and any optional<br>info encrypted with<br>"public" key EK)
+  note over B: confirm queue<br>("public" key SK for<br>sending messages,<br>public key for<br>e2e encryption<br>and any optional<br>encrypted info)
   B ->> S: 3. confirm queue ("SEND" command not signed)
 
-  S ->> A: 4. deliver Bob's message
+  S ->> A: 4. deliver Bob's message (MSG)
   note over A: decrypt message<br>("private" key EK)
+  A ->> S: acknowledge message (ACK)
+
   A ->> S: 5. secure queue ("KEY", RK-signed)
 
   note over S: 6. simplex<br>queue RID<br>is ready to use!

protocol/diagrams/xftp/xftp-receiving-file.mmd

@@ -0,0 +1,18 @@
+sequenceDiagram
+  participant B as Bob (recipient)
+  participant S as XFTP server(s)
+
+  note over B: having received file description<br>from sender
+
+  loop for each chunk
+    B ->> S: 1a. download chunk ("FGET")
+    S ->> B: send chunk body ("FILE")
+
+    opt
+      B ->> S: 1b. acknowledge chunk reception ("FACK")
+      note over S: delete recipient ID
+      S ->> B: respond with ok ("OK")
+    end
+  end
+
+  note over B: 2. combine chunks into a file<br>3. decrypt file using key from file description<br>4. extract file name and unpad the file<br>5. validate file digest with the file description

protocol/diagrams/xftp/xftp-sending-file.mmd

@@ -0,0 +1,23 @@
+sequenceDiagram
+  participant A as Alice (sender)
+  participant S as XFTP server(s)
+  participant B as recipient(s)
+
+  note over A: 1. prepare file:<br>encrypt,<br>split into chunks,<br>generate recipient<br>keys, etc.
+
+  loop for each chunk
+    A ->> S: 2a. register chunk ("FNEW")
+    S ->> A: respond with sender's and recipients' chunk IDs ("SIDS")
+
+    opt
+      A ->> S: 2b. request additional recipient IDs ("FADD")
+      S ->> A: respond with added recipients' chunk IDs ("RIDS")
+    end
+
+    A ->> S: 2c. upload chunk to chosen server ("FPUT")
+    S ->> A: respond with ok ("OK")
+  end
+
+  note over A: 3. prepare file description(s)
+
+  A -->> B: 4. send file description(s) out-of-band

protocol/diagrams/xrcp/session.mmd

@@ -0,0 +1,44 @@
+sequenceDiagram
+  participant CI as Controller UI
+  participant CC as Controller Core
+  participant HC as Host Core
+  participant HI as Host UI
+
+note over CI, HI: 1. Session invitation
+CI->>CC: "Link a mobile"
+CC-->>CI: Session invitation URI
+note over CC: Listen for TCP connection
+activate CC
+HI->>HC: Session invitation URI
+
+note over CI, HI: 2. Establishing TLS connection
+HC-->>CC: TCP connect
+note over CC, HC: TLS handshake
+par
+    note over CC: validate client X509 credentials
+    CC->>CI: session code from tlsUnique
+    CI-->>CC: user confirmation
+and
+    note over HC: validate server X509 credentials
+    HC->>HI: session code from tlsUnique
+    HI-->>HC: user confirmation
+end
+
+note over CI, HI: 3. Session verification and protocol negotiation
+HC->>CC: host HELLO
+note over CC: validate version, CA fingerprint
+alt
+    CC-->>HC: controller ERROR
+else
+    CC-->>HC: controller HELLO
+    note over CC, HC: update stored keys
+end
+deactivate CC
+
+note over CI, HI: 4. Session operation
+loop
+    CI->>CC: command
+    CC->>HC: XRCP command
+    HC-->>CC: XRCP response
+    CC-->>CI: response
+end