chore: bump version to 2.0.15 [skip ci]

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.gitea/workflows/build-app-linux.yml

@@ -0,0 +1,95 @@
+name: Build App (Linux)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build (e.g. v1.4.5)'
+        required: true
+
+jobs:
+  build-linux:
+    name: Build App (Linux)
+    runs-on: ubuntu-latest
+    env:
+      NODE_VERSION: "20"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Install Rust stable
+        run: |
+          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
+          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf xdg-utils rpm
+
+      - name: Install npm dependencies
+        run: npm ci
+
+      - name: Build Tauri app
+        run: npm run tauri build
+
+      - name: Upload to release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          sudo apt-get install -y jq
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          TAG="${RELEASE_TAG}"
+          echo "Release tag: ${TAG}"
+
+          echo "Waiting for release ${TAG} to be available..."
+          RELEASE_ID=""
+          for i in $(seq 1 30); do
+            RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/tags/${TAG}")
+            RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
+
+            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
+              echo "Found release: ${TAG} (ID: ${RELEASE_ID})"
+              break
+            fi
+
+            echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
+            sleep 10
+          done
+
+          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
+            echo "ERROR: Failed to find release for tag ${TAG} after 30 attempts."
+            exit 1
+          fi
+
+          find src-tauri/target/release/bundle -type f \( -name "*.deb" -o -name "*.rpm" -o -name "*.AppImage" \) | while IFS= read -r file; do
+            filename=$(basename "$file")
+            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
+            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
+
+            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
+            if [ -n "${ASSET_ID}" ]; then
+              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
+            fi
+
+            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" \
+              -H "Content-Type: application/octet-stream" \
+              -T "$file" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
+            echo "Upload response: HTTP ${HTTP_CODE}"
+          done

.gitea/workflows/build-app-macos.yml

@@ -0,0 +1,93 @@
+name: Build App (macOS)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build (e.g. v1.4.5)'
+        required: true
+
+jobs:
+  build-macos:
+    name: Build App (macOS)
+    runs-on: macos-latest
+    env:
+      NODE_VERSION: "20"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Install Rust stable
+        run: |
+          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
+          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+      - name: Install system dependencies
+        run: brew install --quiet create-dmg || true
+
+      - name: Install npm dependencies
+        run: npm ci
+
+      - name: Build Tauri app
+        run: npm run tauri build
+
+      - name: Upload to release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          which jq || brew install jq
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          TAG="${RELEASE_TAG}"
+          echo "Release tag: ${TAG}"
+
+          echo "Waiting for release ${TAG} to be available..."
+          RELEASE_ID=""
+          for i in $(seq 1 30); do
+            RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/tags/${TAG}")
+            RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
+
+            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
+              echo "Found release: ${TAG} (ID: ${RELEASE_ID})"
+              break
+            fi
+
+            echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
+            sleep 10
+          done
+
+          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
+            echo "ERROR: Failed to find release for tag ${TAG} after 30 attempts."
+            exit 1
+          fi
+
+          find src-tauri/target/release/bundle -type f -name "*.dmg" | while IFS= read -r file; do
+            filename=$(basename "$file")
+            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
+            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
+
+            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
+            if [ -n "${ASSET_ID}" ]; then
+              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
+            fi
+
+            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" \
+              -H "Content-Type: application/octet-stream" \
+              -T "$file" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
+            echo "Upload response: HTTP ${HTTP_CODE}"
+          done

.gitea/workflows/build-app-windows.yml

@@ -0,0 +1,117 @@
+name: Build App (Windows)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build (e.g. v1.4.5)'
+        required: true
+
+env:
+  NODE_VERSION: "20"
+
+jobs:
+  build-windows:
+    name: Build App (Windows)
+    runs-on: windows-latest
+    env:
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        shell: powershell
+        run: |
+          Write-Host "Building for tag: $env:RELEASE_TAG"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Install Rust stable
+        shell: powershell
+        run: |
+          if (Get-Command rustup -ErrorAction SilentlyContinue) {
+            rustup default stable
+          } else {
+            Invoke-WebRequest -Uri https://win.rustup.rs/x86_64 -OutFile rustup-init.exe
+            .\rustup-init.exe -y --default-toolchain stable
+            echo "$env:USERPROFILE\.cargo\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+          }
+
+      - name: Install npm dependencies
+        shell: powershell
+        run: npm ci
+
+      - name: Build Tauri app
+        shell: powershell
+        run: npm run tauri build
+
+      - name: Upload to release
+        shell: powershell
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          $REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
+          $Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
+          $TAG = $env:RELEASE_TAG
+          Write-Host "Release tag: $TAG"
+
+          if (-not $TAG) {
+            Write-Host "ERROR: RELEASE_TAG is empty"
+            exit 1
+          }
+
+          Write-Host "Waiting for release $TAG to be available..."
+          $RELEASE_ID = $null
+
+          for ($i = 1; $i -le 30; $i++) {
+            try {
+              $release = Invoke-RestMethod -Uri "$REPO_API/releases/tags/$TAG" -Headers $Headers -ErrorAction Stop
+              $RELEASE_ID = $release.id
+
+              if ($RELEASE_ID) {
+                Write-Host "Found release: $TAG (ID: $RELEASE_ID)"
+                break
+              }
+            } catch {}
+
+            Write-Host "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
+            Start-Sleep -Seconds 10
+          }
+
+          if (-not $RELEASE_ID) {
+            Write-Host "ERROR: Failed to find release for tag $TAG after 30 attempts."
+            exit 1
+          }
+
+          Get-ChildItem -Path src-tauri\target\release\bundle -Recurse -Include *.msi,*-setup.exe | ForEach-Object {
+            $filename = $_.Name
+            $encodedName = [System.Uri]::EscapeDataString($filename)
+            $size = [math]::Round($_.Length / 1MB, 1)
+            Write-Host "Uploading $filename ($size MB)..."
+
+            try {
+              $assets = Invoke-RestMethod -Uri "$REPO_API/releases/$RELEASE_ID/assets" -Headers $Headers
+              $existing = $assets | Where-Object { $_.name -eq $filename }
+              if ($existing) {
+                Invoke-RestMethod -Uri "$REPO_API/releases/$RELEASE_ID/assets/$($existing.id)" -Method Delete -Headers $Headers
+              }
+            } catch {}
+
+            $uploadUrl = "$REPO_API/releases/$RELEASE_ID/assets?name=$encodedName"
+            $result = curl.exe --fail --silent --show-error `
+              -X POST `
+              -H "Authorization: token $env:BUILD_TOKEN" `
+              -H "Content-Type: application/octet-stream" `
+              -T "$($_.FullName)" `
+              "$uploadUrl" 2>&1
+            if ($LASTEXITCODE -eq 0) {
+              Write-Host "Upload successful: $filename"
+            } else {
+              Write-Host "WARNING: Upload failed for ${filename}: $result"
+            }
+          }

.gitea/workflows/build-sidecar-cloud.yml

@@ -0,0 +1,229 @@
+name: Build Sidecar (Cloud)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Sidecar release tag to build (e.g. sidecar-v1.0.5)'
+        required: true
+
+jobs:
+  build-cloud-linux:
+    name: Build Cloud Sidecar (Linux)
+    runs-on: ubuntu-latest
+    env:
+      PYTHON_VERSION: "3.11"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        run: |
+          echo "Building cloud sidecar for tag ${RELEASE_TAG}"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Set up Python
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y portaudio19-dev
+
+      - name: Build cloud sidecar
+        env:
+          UV_NO_SOURCES: "1"
+        run: |
+          uv venv
+          uv pip install pyinstaller numpy sounddevice fastapi uvicorn websockets pydantic requests pyyaml packaging
+          .venv/bin/pyinstaller local-transcription-cloud.spec
+
+      - name: Package
+        run: |
+          cd dist/local-transcription-backend && zip -r ../../sidecar-linux-x86_64-cloud.zip .
+
+      - name: Upload to release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          sudo apt-get install -y jq
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          TAG="${RELEASE_TAG}"
+
+          for i in $(seq 1 30); do
+            RELEASE_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/tags/${TAG}" | jq -r '.id // empty')
+            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
+              echo "Found release ${TAG} (ID: ${RELEASE_ID})"
+              break
+            fi
+            echo "Attempt ${i}/30: waiting for release..."
+            sleep 10
+          done
+
+          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
+            echo "ERROR: Release not found"; exit 1
+          fi
+
+          for file in sidecar-*-cloud.zip; do
+            filename=$(basename "$file")
+            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
+            [ -n "${ASSET_ID}" ] && curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
+            curl -s -o /dev/null -w "Upload ${filename}: HTTP %{http_code}\n" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" -H "Content-Type: application/octet-stream" \
+              -T "$file" "${REPO_API}/releases/${RELEASE_ID}/assets?name=${filename}"
+          done
+
+  build-cloud-windows:
+    name: Build Cloud Sidecar (Windows)
+    runs-on: windows-latest
+    env:
+      PYTHON_VERSION: "3.11"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        shell: powershell
+        run: Write-Host "Building cloud sidecar for tag $env:RELEASE_TAG"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install uv
+        shell: powershell
+        run: |
+          if (Get-Command uv -ErrorAction SilentlyContinue) {
+            Write-Host "uv already installed"
+          } else {
+            irm https://astral.sh/uv/install.ps1 | iex
+            $uvPaths = @("$env:USERPROFILE\.local\bin", "$env:USERPROFILE\.cargo\bin", "$env:LOCALAPPDATA\uv\bin")
+            foreach ($p in $uvPaths) { if (Test-Path $p) { echo $p | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append } }
+          }
+
+      - name: Set up Python
+        shell: powershell
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Build cloud sidecar
+        shell: powershell
+        env:
+          UV_NO_SOURCES: "1"
+        run: |
+          uv venv
+          uv pip install pyinstaller numpy sounddevice fastapi uvicorn websockets pydantic requests pyyaml packaging
+          .venv\Scripts\pyinstaller.exe local-transcription-cloud.spec
+
+      - name: Package
+        shell: powershell
+        run: |
+          if (-not (Get-Command 7z -ErrorAction SilentlyContinue)) { choco install 7zip -y }
+          7z a -tzip -mx=5 sidecar-windows-x86_64-cloud.zip .\dist\local-transcription-backend\*
+
+      - name: Upload to release
+        shell: powershell
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          $REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
+          $Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
+          $TAG = $env:RELEASE_TAG
+
+          $RELEASE_ID = $null
+          for ($i = 1; $i -le 30; $i++) {
+            try {
+              $release = Invoke-RestMethod -Uri "$REPO_API/releases/tags/$TAG" -Headers $Headers -ErrorAction Stop
+              $RELEASE_ID = $release.id
+              if ($RELEASE_ID) { Write-Host "Found release $TAG (ID: $RELEASE_ID)"; break }
+            } catch {}
+            Write-Host "Attempt ${i}/30: waiting..."; Start-Sleep -Seconds 10
+          }
+          if (-not $RELEASE_ID) { Write-Host "ERROR: Release not found"; exit 1 }
+
+          Get-ChildItem -Path . -Filter "sidecar-*-cloud.zip" | ForEach-Object {
+            $fn = $_.Name; $enc = [System.Uri]::EscapeDataString($fn)
+            try {
+              $assets = Invoke-RestMethod -Uri "$REPO_API/releases/$RELEASE_ID/assets" -Headers $Headers
+              $existing = $assets | Where-Object { $_.name -eq $fn }
+              if ($existing) { Invoke-RestMethod -Uri "$REPO_API/releases/$RELEASE_ID/assets/$($existing.id)" -Method Delete -Headers $Headers }
+            } catch {}
+            curl.exe --fail -s -X POST -H "Authorization: token $env:BUILD_TOKEN" -H "Content-Type: application/octet-stream" -T "$($_.FullName)" "$REPO_API/releases/$RELEASE_ID/assets?name=$enc"
+            Write-Host "Uploaded $fn"
+          }
+
+  build-cloud-macos:
+    name: Build Cloud Sidecar (macOS)
+    runs-on: macos-latest
+    env:
+      PYTHON_VERSION: "3.11"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        run: |
+          echo "Building cloud sidecar for tag ${RELEASE_TAG}"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Set up Python
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install system dependencies
+        run: brew install portaudio
+
+      - name: Build cloud sidecar
+        env:
+          UV_NO_SOURCES: "1"
+        run: |
+          uv venv
+          uv pip install pyinstaller numpy sounddevice fastapi uvicorn websockets pydantic requests pyyaml packaging
+          .venv/bin/pyinstaller local-transcription-cloud.spec
+
+      - name: Package
+        run: |
+          cd dist/local-transcription-backend && zip -r ../../sidecar-macos-aarch64-cloud.zip .
+
+      - name: Upload to release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          which jq || brew install jq
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          TAG="${RELEASE_TAG}"
+
+          for i in $(seq 1 30); do
+            RELEASE_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/tags/${TAG}" | jq -r '.id // empty')
+            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
+              echo "Found release ${TAG} (ID: ${RELEASE_ID})"
+              break
+            fi
+            echo "Attempt ${i}/30: waiting for release..."
+            sleep 10
+          done
+
+          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
+            echo "ERROR: Release not found"; exit 1
+          fi
+
+          for file in sidecar-*-cloud.zip; do
+            filename=$(basename "$file")
+            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
+            [ -n "${ASSET_ID}" ] && curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
+            curl -s -o /dev/null -w "Upload ${filename}: HTTP %{http_code}\n" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" -H "Content-Type: application/octet-stream" \
+              -T "$file" "${REPO_API}/releases/${RELEASE_ID}/assets?name=${filename}"
+          done

.gitea/workflows/build-sidecar-linux.yml

@@ -0,0 +1,101 @@
+name: Build Sidecar (Linux)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Sidecar release tag to build (e.g. sidecar-v1.0.3)'
+        required: true
+
+jobs:
+  build-sidecar-linux:
+    name: Build Sidecar (Linux)
+    runs-on: ubuntu-latest
+    env:
+      PYTHON_VERSION: "3.11"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install uv
+        run: |
+          if command -v uv &> /dev/null; then
+            echo "uv already installed: $(uv --version)"
+          else
+            curl -LsSf https://astral.sh/uv/install.sh | sh
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Set up Python
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y portaudio19-dev
+
+      - name: Build sidecar (CPU)
+        run: |
+          uv sync --no-sources
+          # PyPI's default torch on Linux includes CUDA (~800MB).
+          # Replace with CPU-only torch from the dedicated index.
+          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
+          .venv/bin/pyinstaller local-transcription-headless.spec
+
+      - name: Package sidecar (CPU)
+        run: |
+          cd dist/local-transcription-backend && zip -9 -r ../../sidecar-linux-x86_64-cpu.zip .
+
+      - name: Upload to sidecar release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          sudo apt-get install -y jq
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          TAG="${RELEASE_TAG}"
+
+          echo "Waiting for sidecar release ${TAG} to be available..."
+          for i in $(seq 1 30); do
+            RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/tags/${TAG}")
+            RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
+
+            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
+              echo "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
+              break
+            fi
+
+            echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
+            sleep 10
+          done
+
+          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
+            echo "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
+            exit 1
+          fi
+
+          for file in sidecar-*.zip; do
+            filename=$(basename "$file")
+            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
+            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
+
+            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
+            if [ -n "${ASSET_ID}" ]; then
+              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
+            fi
+
+            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" \
+              -H "Content-Type: application/octet-stream" \
+              -T "$file" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
+            echo "Upload response: HTTP ${HTTP_CODE}"
+          done

.gitea/workflows/build-sidecar-macos.yml

@@ -0,0 +1,101 @@
+name: Build Sidecar (macOS)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Sidecar release tag to build (e.g. sidecar-v1.0.3)'
+        required: true
+
+jobs:
+  build-sidecar-macos:
+    name: Build Sidecar (macOS)
+    runs-on: macos-latest
+    env:
+      PYTHON_VERSION: "3.11"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install uv
+        run: |
+          if command -v uv &> /dev/null; then
+            echo "uv already installed: $(uv --version)"
+          else
+            curl -LsSf https://astral.sh/uv/install.sh | sh
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Set up Python
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install system dependencies
+        run: brew install portaudio
+
+      - name: Build sidecar (CPU)
+        env:
+          UV_NO_SOURCES: "1"
+        run: |
+          # UV_NO_SOURCES bypasses pyproject.toml's [tool.uv.sources] which forces
+          # torch from the CUDA index (no macOS ARM wheels there).
+          # Default PyPI torch includes MPS (Apple Silicon GPU) support.
+          uv sync
+          .venv/bin/pyinstaller local-transcription-headless.spec
+
+      - name: Package sidecar (CPU)
+        run: |
+          cd dist/local-transcription-backend && zip -r ../../sidecar-macos-aarch64-cpu.zip .
+
+      - name: Upload to sidecar release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          which jq || brew install jq
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          TAG="${RELEASE_TAG}"
+
+          echo "Waiting for sidecar release ${TAG} to be available..."
+          for i in $(seq 1 30); do
+            RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/tags/${TAG}")
+            RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
+
+            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
+              echo "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
+              break
+            fi
+
+            echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
+            sleep 10
+          done
+
+          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
+            echo "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
+            exit 1
+          fi
+
+          for file in sidecar-*.zip; do
+            filename=$(basename "$file")
+            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
+            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
+
+            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
+            if [ -n "${ASSET_ID}" ]; then
+              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
+            fi
+
+            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" \
+              -H "Content-Type: application/octet-stream" \
+              -T "$file" \
+              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
+            echo "Upload response: HTTP ${HTTP_CODE}"
+          done

.gitea/workflows/build-sidecar-windows.yml

@@ -0,0 +1,135 @@
+name: Build Sidecar (Windows)
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Sidecar release tag to build (e.g. sidecar-v1.0.3)'
+        required: true
+
+jobs:
+  build-sidecar-windows:
+    name: Build Sidecar (Windows)
+    runs-on: windows-latest
+    env:
+      PYTHON_VERSION: "3.11"
+      RELEASE_TAG: "${{ inputs.tag }}"
+    steps:
+      - name: Show tag
+        shell: powershell
+        run: |
+          Write-Host "Building for tag: $env:RELEASE_TAG"
+
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install uv
+        shell: powershell
+        run: |
+          if (Get-Command uv -ErrorAction SilentlyContinue) {
+            Write-Host "uv already installed: $(uv --version)"
+          } else {
+            irm https://astral.sh/uv/install.ps1 | iex
+            $uvPaths = @(
+              "$env:USERPROFILE\.local\bin",
+              "$env:USERPROFILE\.cargo\bin",
+              "$env:LOCALAPPDATA\uv\bin"
+            )
+            foreach ($p in $uvPaths) {
+              if (Test-Path $p) {
+                echo $p | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+              }
+            }
+          }
+
+      - name: Set up Python
+        shell: powershell
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install 7-Zip
+        shell: powershell
+        run: |
+          if (-not (Get-Command 7z -ErrorAction SilentlyContinue)) {
+            choco install 7zip -y
+          }
+
+      - name: Build sidecar (CPU)
+        shell: powershell
+        run: |
+          $env:UV_NO_SOURCES = "1"
+          uv sync
+          # PyPI's default torch includes CUDA. Replace with CPU-only.
+          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
+          .venv\Scripts\pyinstaller.exe local-transcription-headless.spec
+
+      - name: Package sidecar (CPU)
+        shell: powershell
+        run: |
+          7z a -tzip -mx=9 sidecar-windows-x86_64-cpu.zip .\dist\local-transcription-backend\*
+
+      - name: Upload to sidecar release
+        shell: powershell
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          $REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
+          $Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
+          $TAG = $env:RELEASE_TAG
+          Write-Host "Release tag: $TAG"
+
+          if (-not $TAG) {
+            Write-Host "ERROR: RELEASE_TAG is empty"
+            exit 1
+          }
+
+          Write-Host "Waiting for sidecar release $TAG to be available..."
+          $RELEASE_ID = $null
+
+          for ($i = 1; $i -le 30; $i++) {
+            try {
+              $release = Invoke-RestMethod -Uri "$REPO_API/releases/tags/$TAG" -Headers $Headers -ErrorAction Stop
+              $RELEASE_ID = $release.id
+
+              if ($RELEASE_ID) {
+                Write-Host "Found sidecar release: $TAG (ID: $RELEASE_ID)"
+                break
+              }
+            } catch {}
+
+            Write-Host "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
+            Start-Sleep -Seconds 10
+          }
+
+          if (-not $RELEASE_ID) {
+            Write-Host "ERROR: Failed to find sidecar release for tag $TAG after 30 attempts."
+            exit 1
+          }
+
+          Get-ChildItem -Path . -Filter "sidecar-*.zip" | ForEach-Object {
+            $filename = $_.Name
+            $encodedName = [System.Uri]::EscapeDataString($filename)
+            $size = [math]::Round($_.Length / 1MB, 1)
+            Write-Host "Uploading $filename ($size MB)..."
+
+            try {
+              $assets = Invoke-RestMethod -Uri "$REPO_API/releases/$RELEASE_ID/assets" -Headers $Headers
+              $existing = $assets | Where-Object { $_.name -eq $filename }
+              if ($existing) {
+                Invoke-RestMethod -Uri "$REPO_API/releases/$RELEASE_ID/assets/$($existing.id)" -Method Delete -Headers $Headers
+              }
+            } catch {}
+
+            $uploadUrl = "$REPO_API/releases/$RELEASE_ID/assets?name=$encodedName"
+            $result = curl.exe --fail --silent --show-error `
+              -X POST `
+              -H "Authorization: token $env:BUILD_TOKEN" `
+              -H "Content-Type: application/octet-stream" `
+              -T "$($_.FullName)" `
+              "$uploadUrl" 2>&1
+            if ($LASTEXITCODE -eq 0) {
+              Write-Host "Upload successful: $filename"
+            } else {
+              Write-Host "WARNING: Upload failed for ${filename}: $result"
+            }
+          }

.gitea/workflows/build-sidecar.yml

@@ -1,414 +0,0 @@
-name: Build Sidecars
-
-on:
-  push:
-    branches: [main]
-    paths:
-      - 'client/**'
-      - 'server/**'
-      - 'backend/**'
-      - 'pyproject.toml'
-      - 'local-transcription-headless.spec'
-  workflow_dispatch:
-
-jobs:
-  bump-sidecar-version:
-    name: Bump sidecar version and tag
-    if: "!contains(github.event.head_commit.message, '[skip ci]')"
-    runs-on: ubuntu-latest
-    outputs:
-      version: ${{ steps.bump.outputs.version }}
-      tag: ${{ steps.bump.outputs.tag }}
-      has_changes: ${{ steps.check_changes.outputs.has_changes }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
-
-      - name: Check for backend changes
-        id: check_changes
-        run: |
-          # If triggered by workflow_dispatch, always build
-          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            exit 0
-          fi
-          # Check if relevant files changed in this commit
-          CHANGED=$(git diff --name-only HEAD~1 HEAD -- client/ server/ backend/ pyproject.toml local-transcription-headless.spec 2>/dev/null || echo "")
-          if [ -n "$CHANGED" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            echo "Backend changes detected: $CHANGED"
-          else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-            echo "No backend changes detected, skipping sidecar build"
-          fi
-
-      - name: Configure git
-        if: steps.check_changes.outputs.has_changes == 'true'
-        run: |
-          git config user.name "Gitea Actions"
-          git config user.email "actions@gitea.local"
-
-      - name: Bump sidecar patch version
-        if: steps.check_changes.outputs.has_changes == 'true'
-        id: bump
-        run: |
-          # Read current version from pyproject.toml
-          CURRENT=$(grep '^version = ' pyproject.toml | head -1 | sed 's/version = "\(.*\)"/\1/')
-          echo "Current sidecar version: ${CURRENT}"
-
-          # Increment patch number
-          MAJOR=$(echo "${CURRENT}" | cut -d. -f1)
-          MINOR=$(echo "${CURRENT}" | cut -d. -f2)
-          PATCH=$(echo "${CURRENT}" | cut -d. -f3)
-          NEW_PATCH=$((PATCH + 1))
-          NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
-          echo "New sidecar version: ${NEW_VERSION}"
-
-          # Update pyproject.toml
-          sed -i "s/^version = \"${CURRENT}\"/version = \"${NEW_VERSION}\"/" pyproject.toml
-
-          # Update version.py
-          sed -i "s/__version__ = \"${CURRENT}\"/__version__ = \"${NEW_VERSION}\"/" version.py
-          sed -i "s/__version_info__ = .*/__version_info__ = (${MAJOR}, ${MINOR}, ${NEW_PATCH})/" version.py
-
-          echo "version=${NEW_VERSION}" >> $GITHUB_OUTPUT
-          echo "tag=sidecar-v${NEW_VERSION}" >> $GITHUB_OUTPUT
-
-      - name: Commit and tag
-        if: steps.check_changes.outputs.has_changes == 'true'
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          NEW_VERSION="${{ steps.bump.outputs.version }}"
-          TAG="${{ steps.bump.outputs.tag }}"
-          git add pyproject.toml version.py
-          git commit -m "chore: bump sidecar version to ${NEW_VERSION} [skip ci]"
-          git tag "${TAG}"
-
-          REMOTE_URL=$(git remote get-url origin | sed "s|://|://gitea-actions:${BUILD_TOKEN}@|")
-          git pull --rebase "${REMOTE_URL}" main || true
-          git push "${REMOTE_URL}" HEAD:main
-          git push "${REMOTE_URL}" "${TAG}"
-
-      - name: Create Gitea release
-        if: steps.check_changes.outputs.has_changes == 'true'
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ steps.bump.outputs.tag }}"
-          VERSION="${{ steps.bump.outputs.version }}"
-          RELEASE_NAME="Sidecar v${VERSION}"
-
-          curl -s -X POST \
-            -H "Authorization: token ${BUILD_TOKEN}" \
-            -H "Content-Type: application/json" \
-            -d "{\"tag_name\": \"${TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated sidecar build.\", \"draft\": false, \"prerelease\": false}" \
-            "${REPO_API}/releases"
-          echo "Created release: ${RELEASE_NAME}"
-
-  # ── Linux sidecar (CUDA + CPU) ──
-
-  build-sidecar-linux:
-    name: Build Sidecar (Linux)
-    needs: bump-sidecar-version
-    if: needs.bump-sidecar-version.outputs.has_changes == 'true'
-    runs-on: ubuntu-latest
-    env:
-      PYTHON_VERSION: "3.11"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ needs.bump-sidecar-version.outputs.tag }}
-
-      - name: Install uv
-        run: |
-          if command -v uv &> /dev/null; then
-            echo "uv already installed: $(uv --version)"
-          else
-            curl -LsSf https://astral.sh/uv/install.sh | sh
-            echo "$HOME/.local/bin" >> $GITHUB_PATH
-          fi
-
-      - name: Set up Python
-        run: uv python install ${{ env.PYTHON_VERSION }}
-
-      - name: Install system dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y portaudio19-dev
-
-      - name: Build sidecar (CUDA)
-        run: |
-          uv sync
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CUDA)
-        run: |
-          cd dist/local-transcription-backend && zip -r ../../sidecar-linux-x86_64-cuda.zip .
-
-      - name: Build sidecar (CPU)
-        run: |
-          rm -rf dist/local-transcription-backend build/
-          # Install CPU-only PyTorch
-          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CPU)
-        run: |
-          cd dist/local-transcription-backend && zip -r ../../sidecar-linux-x86_64-cpu.zip .
-
-      - name: Upload to sidecar release
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          sudo apt-get install -y jq
-          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ needs.bump-sidecar-version.outputs.tag }}"
-
-          echo "Waiting for sidecar release ${TAG} to be available..."
-          for i in $(seq 1 30); do
-            RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-              "${REPO_API}/releases/tags/${TAG}")
-            RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
-
-            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
-              echo "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
-              break
-            fi
-
-            echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
-            sleep 10
-          done
-
-          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
-            echo "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
-            exit 1
-          fi
-
-          for file in sidecar-*.zip; do
-            filename=$(basename "$file")
-            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
-            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
-
-            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
-            if [ -n "${ASSET_ID}" ]; then
-              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
-                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
-            fi
-
-            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
-              -H "Authorization: token ${BUILD_TOKEN}" \
-              -H "Content-Type: application/octet-stream" \
-              -T "$file" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
-            echo "Upload response: HTTP ${HTTP_CODE}"
-          done
-
-  # ── Windows sidecar (CUDA + CPU) ──
-
-  build-sidecar-windows:
-    name: Build Sidecar (Windows)
-    needs: bump-sidecar-version
-    if: needs.bump-sidecar-version.outputs.has_changes == 'true'
-    runs-on: windows-latest
-    env:
-      PYTHON_VERSION: "3.11"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ needs.bump-sidecar-version.outputs.tag }}
-
-      - name: Install uv
-        shell: powershell
-        run: |
-          if (Get-Command uv -ErrorAction SilentlyContinue) {
-            Write-Host "uv already installed: $(uv --version)"
-          } else {
-            irm https://astral.sh/uv/install.ps1 | iex
-            echo "$env:USERPROFILE\.local\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
-          }
-
-      - name: Set up Python
-        shell: powershell
-        run: uv python install ${{ env.PYTHON_VERSION }}
-
-      - name: Install 7-Zip
-        shell: powershell
-        run: |
-          if (-not (Get-Command 7z -ErrorAction SilentlyContinue)) {
-            choco install 7zip -y
-          }
-
-      - name: Build sidecar (CUDA)
-        shell: powershell
-        run: |
-          uv sync
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CUDA)
-        shell: powershell
-        run: |
-          7z a -tzip -mx=5 sidecar-windows-x86_64-cuda.zip .\dist\local-transcription-backend\*
-
-      - name: Build sidecar (CPU)
-        shell: powershell
-        run: |
-          Remove-Item -Recurse -Force dist\local-transcription-backend, build -ErrorAction SilentlyContinue
-          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CPU)
-        shell: powershell
-        run: |
-          7z a -tzip -mx=5 sidecar-windows-x86_64-cpu.zip .\dist\local-transcription-backend\*
-
-      - name: Upload to sidecar release
-        shell: powershell
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          $REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
-          $Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
-          $TAG = "${{ needs.bump-sidecar-version.outputs.tag }}"
-
-          Write-Host "Waiting for sidecar release ${TAG} to be available..."
-          $RELEASE_ID = $null
-
-          for ($i = 1; $i -le 30; $i++) {
-            try {
-              $release = Invoke-RestMethod -Uri "${REPO_API}/releases/tags/${TAG}" -Headers $Headers -ErrorAction Stop
-              $RELEASE_ID = $release.id
-
-              if ($RELEASE_ID) {
-                Write-Host "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
-                break
-              }
-            } catch {}
-
-            Write-Host "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
-            Start-Sleep -Seconds 10
-          }
-
-          if (-not $RELEASE_ID) {
-            Write-Host "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
-            exit 1
-          }
-
-          Get-ChildItem -Path . -Filter "sidecar-*.zip" | ForEach-Object {
-            $filename = $_.Name
-            $encodedName = [System.Uri]::EscapeDataString($filename)
-            $size = [math]::Round($_.Length / 1MB, 1)
-            Write-Host "Uploading ${filename} (${size} MB)..."
-
-            try {
-              $assets = Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets" -Headers $Headers
-              $existing = $assets | Where-Object { $_.name -eq $filename }
-              if ($existing) {
-                Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets/$($existing.id)" -Method Delete -Headers $Headers
-              }
-            } catch {}
-
-            $uploadUrl = "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encodedName}"
-            $result = curl.exe --fail --silent --show-error `
-              -X POST `
-              -H "Authorization: token $env:BUILD_TOKEN" `
-              -H "Content-Type: application/octet-stream" `
-              -T "$($_.FullName)" `
-              "$uploadUrl" 2>&1
-            if ($LASTEXITCODE -eq 0) {
-              Write-Host "Upload successful: ${filename}"
-            } else {
-              Write-Host "WARNING: Upload failed for ${filename}: ${result}"
-            }
-          }
-
-  # ── macOS sidecar (CPU only — no CUDA on macOS) ──
-
-  build-sidecar-macos:
-    name: Build Sidecar (macOS)
-    needs: bump-sidecar-version
-    if: needs.bump-sidecar-version.outputs.has_changes == 'true'
-    runs-on: macos-latest
-    env:
-      PYTHON_VERSION: "3.11"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ needs.bump-sidecar-version.outputs.tag }}
-
-      - name: Install uv
-        run: |
-          if command -v uv &> /dev/null; then
-            echo "uv already installed: $(uv --version)"
-          else
-            curl -LsSf https://astral.sh/uv/install.sh | sh
-            echo "$HOME/.local/bin" >> $GITHUB_PATH
-          fi
-
-      - name: Set up Python
-        run: uv python install ${{ env.PYTHON_VERSION }}
-
-      - name: Install system dependencies
-        run: brew install portaudio
-
-      - name: Build sidecar (CPU)
-        run: |
-          # Install CPU-only PyTorch for macOS (MPS support included in default torch)
-          uv sync
-          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CPU)
-        run: |
-          cd dist/local-transcription-backend && zip -r ../../sidecar-macos-aarch64-cpu.zip .
-
-      - name: Upload to sidecar release
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          which jq || brew install jq
-          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ needs.bump-sidecar-version.outputs.tag }}"
-
-          echo "Waiting for sidecar release ${TAG} to be available..."
-          for i in $(seq 1 30); do
-            RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-              "${REPO_API}/releases/tags/${TAG}")
-            RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
-
-            if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
-              echo "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
-              break
-            fi
-
-            echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
-            sleep 10
-          done
-
-          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
-            echo "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
-            exit 1
-          fi
-
-          for file in sidecar-*.zip; do
-            filename=$(basename "$file")
-            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
-            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
-
-            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
-            if [ -n "${ASSET_ID}" ]; then
-              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
-                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
-            fi
-
-            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
-              -H "Authorization: token ${BUILD_TOKEN}" \
-              -H "Content-Type: application/octet-stream" \
-              -T "$file" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
-            echo "Upload response: HTTP ${HTTP_CODE}"
-          done

.gitea/workflows/cleanup-releases.yml

@@ -0,0 +1,102 @@
+name: Cleanup Old Releases
+
+on:
+  workflow_dispatch:
+    inputs:
+      keep_app_releases:
+        description: 'Number of app releases to keep'
+        required: false
+        default: '3'
+      keep_sidecar_releases:
+        description: 'Number of sidecar releases to keep'
+        required: false
+        default: '2'
+      dry_run:
+        description: 'Dry run (show what would be deleted without deleting)'
+        required: false
+        default: 'true'
+
+jobs:
+  cleanup:
+    name: Cleanup Old Releases
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup releases
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          KEEP_APP="${{ inputs.keep_app_releases }}"
+          KEEP_SIDECAR="${{ inputs.keep_sidecar_releases }}"
+          DRY_RUN="${{ inputs.dry_run }}"
+
+          echo "=== Cleanup Configuration ==="
+          echo "Keep app releases: ${KEEP_APP}"
+          echo "Keep sidecar releases: ${KEEP_SIDECAR}"
+          echo "Dry run: ${DRY_RUN}"
+          echo ""
+
+          # Fetch all releases
+          ALL_RELEASES=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+            "${REPO_API}/releases?limit=50")
+
+          # ── App releases (v* tags, not sidecar-v*) ──
+          echo "=== App Releases ==="
+          APP_RELEASES=$(echo "$ALL_RELEASES" | jq -c '[.[] | select(.tag_name | startswith("v")) | select(.tag_name | startswith("sidecar") | not)]')
+          APP_TOTAL=$(echo "$APP_RELEASES" | jq 'length')
+          echo "Found ${APP_TOTAL} app releases, keeping ${KEEP_APP}"
+
+          if [ "$APP_TOTAL" -gt "$KEEP_APP" ]; then
+            echo "$APP_RELEASES" | jq -c ".[$KEEP_APP:][]" | while read -r release; do
+              ID=$(echo "$release" | jq -r '.id')
+              TAG=$(echo "$release" | jq -r '.tag_name')
+              SIZE=$(echo "$release" | jq '[.assets[]?.size // 0] | add // 0')
+              SIZE_MB=$(echo "scale=1; $SIZE / 1048576" | bc 2>/dev/null || echo "?")
+
+              # Protect v1.4.0 (last pre-Tauri release)
+              if [ "$TAG" = "v1.4.0" ]; then
+                echo "  PROTECT ${TAG} (${SIZE_MB} MB)"
+                continue
+              fi
+
+              if [ "$DRY_RUN" = "true" ]; then
+                echo "  WOULD DELETE ${TAG} (ID: ${ID}, ${SIZE_MB} MB)"
+              else
+                echo "  DELETING ${TAG} (ID: ${ID}, ${SIZE_MB} MB)..."
+                curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                  "${REPO_API}/releases/${ID}"
+              fi
+            done
+          else
+            echo "  Nothing to clean up"
+          fi
+
+          echo ""
+
+          # ── Sidecar releases (sidecar-v* tags) ──
+          echo "=== Sidecar Releases ==="
+          SIDECAR_RELEASES=$(echo "$ALL_RELEASES" | jq -c '[.[] | select(.tag_name | startswith("sidecar-v"))]')
+          SIDECAR_TOTAL=$(echo "$SIDECAR_RELEASES" | jq 'length')
+          echo "Found ${SIDECAR_TOTAL} sidecar releases, keeping ${KEEP_SIDECAR}"
+
+          if [ "$SIDECAR_TOTAL" -gt "$KEEP_SIDECAR" ]; then
+            echo "$SIDECAR_RELEASES" | jq -c ".[$KEEP_SIDECAR:][]" | while read -r release; do
+              ID=$(echo "$release" | jq -r '.id')
+              TAG=$(echo "$release" | jq -r '.tag_name')
+              SIZE=$(echo "$release" | jq '[.assets[]?.size // 0] | add // 0')
+              SIZE_MB=$(echo "scale=1; $SIZE / 1048576" | bc 2>/dev/null || echo "?")
+
+              if [ "$DRY_RUN" = "true" ]; then
+                echo "  WOULD DELETE ${TAG} (ID: ${ID}, ${SIZE_MB} MB)"
+              else
+                echo "  DELETING ${TAG} (ID: ${ID}, ${SIZE_MB} MB)..."
+                curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                  "${REPO_API}/releases/${ID}"
+              fi
+            done
+          else
+            echo "  Nothing to clean up"
+          fi
+
+          echo ""
+          echo "=== Done ==="

.gitea/workflows/release.yml

@@ -1,17 +1,41 @@
 name: Release
 
 on:
-  push:
-    branches: [main]
+  workflow_dispatch:
 
 jobs:
-  bump-version:
-    name: Bump version and tag
+  test:
+    name: Run Tests
     if: "!contains(github.event.head_commit.message, '[skip ci]')"
     runs-on: ubuntu-latest
-    outputs:
-      new_version: ${{ steps.bump.outputs.new_version }}
-      tag: ${{ steps.bump.outputs.tag }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Install npm deps
+        run: npm ci
+
+      - name: Frontend tests
+        run: npx vitest run
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Python tests
+        run: |
+          uv venv .testvenv
+          VIRTUAL_ENV=.testvenv uv pip install pytest httpx pytest-asyncio anyio fastapi pydantic pyyaml uvicorn requests
+          .testvenv/bin/python -m pytest backend/tests/ client/tests/ -v --tb=short
+
+  bump-version:
+    name: Bump version and tag
+    needs: test
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
@@ -23,13 +47,10 @@ jobs:
           git config user.email "actions@gitea.local"
 
       - name: Bump patch version
-        id: bump
         run: |
-          # Read current version from package.json
           CURRENT=$(grep '"version"' package.json | head -1 | sed 's/.*"version": *"\([^"]*\)".*/\1/')
           echo "Current version: ${CURRENT}"
 
-          # Increment patch number
           MAJOR=$(echo "${CURRENT}" | cut -d. -f1)
           MINOR=$(echo "${CURRENT}" | cut -d. -f2)
           PATCH=$(echo "${CURRENT}" | cut -d. -f3)
@@ -37,264 +58,56 @@ jobs:
           NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
           echo "New version: ${NEW_VERSION}"
 
-          # Update package.json
           sed -i "s/\"version\": \"${CURRENT}\"/\"version\": \"${NEW_VERSION}\"/" package.json
-
-          # Update src-tauri/tauri.conf.json
           sed -i "s/\"version\": \"${CURRENT}\"/\"version\": \"${NEW_VERSION}\"/" src-tauri/tauri.conf.json
-
-          # Update src-tauri/Cargo.toml
           sed -i "s/^version = \"${CURRENT}\"/version = \"${NEW_VERSION}\"/" src-tauri/Cargo.toml
-
-          # Update version.py
           sed -i "s/__version__ = \"${CURRENT}\"/__version__ = \"${NEW_VERSION}\"/" version.py
           sed -i "s/__version_info__ = .*/__version_info__ = (${MAJOR}, ${MINOR}, ${NEW_PATCH})/" version.py
 
-          echo "new_version=${NEW_VERSION}" >> $GITHUB_OUTPUT
-          echo "tag=v${NEW_VERSION}" >> $GITHUB_OUTPUT
+          # Write to env file instead of step outputs (avoids act runner bug)
+          echo "NEW_VERSION=${NEW_VERSION}" >> $GITHUB_ENV
+          echo "RELEASE_TAG=v${NEW_VERSION}" >> $GITHUB_ENV
 
       - name: Commit and tag
         env:
           BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
         run: |
-          NEW_VERSION="${{ steps.bump.outputs.new_version }}"
           git add package.json src-tauri/tauri.conf.json src-tauri/Cargo.toml version.py
           git commit -m "chore: bump version to ${NEW_VERSION} [skip ci]"
-          git tag "v${NEW_VERSION}"
+          git tag "${RELEASE_TAG}"
 
           REMOTE_URL=$(git remote get-url origin | sed "s|://|://gitea-actions:${BUILD_TOKEN}@|")
           git pull --rebase "${REMOTE_URL}" main || true
           git push "${REMOTE_URL}" HEAD:main
-          git push "${REMOTE_URL}" "v${NEW_VERSION}"
+          git push "${REMOTE_URL}" "${RELEASE_TAG}"
 
       - name: Create Gitea release
         env:
           BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
         run: |
           REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ steps.bump.outputs.tag }}"
-          RELEASE_NAME="Local Transcription ${TAG}"
+          RELEASE_NAME="Local Transcription ${RELEASE_TAG}"
 
           curl -s -X POST \
             -H "Authorization: token ${BUILD_TOKEN}" \
             -H "Content-Type: application/json" \
-            -d "{\"tag_name\": \"${TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated build.\", \"draft\": false, \"prerelease\": false}" \
+            -d "{\"tag_name\": \"${RELEASE_TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated build.\", \"draft\": false, \"prerelease\": false}" \
             "${REPO_API}/releases"
           echo "Created release: ${RELEASE_NAME}"
 
-  # ── Platform builds (run after version bump) ──
-
-  build-linux:
-    name: Build App (Linux)
-    needs: bump-version
-    runs-on: ubuntu-latest
-    env:
-      NODE_VERSION: "20"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ needs.bump-version.outputs.tag }}
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-
-      - name: Install Rust stable
-        run: |
-          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
-          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
-
-      - name: Install system dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf xdg-utils rpm
-
-      - name: Install npm dependencies
-        run: npm ci
-
-      - name: Build Tauri app
-        run: npm run tauri build
-
-      - name: Upload to release
+      - name: Trigger per-OS app builds
         env:
           BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
         run: |
-          sudo apt-get install -y jq
           REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ needs.bump-version.outputs.tag }}"
-          echo "Release tag: ${TAG}"
 
-          RELEASE_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-            "${REPO_API}/releases/tags/${TAG}" | jq -r '.id // empty')
-
-          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
-            echo "ERROR: Failed to find release for tag ${TAG}."
-            exit 1
-          fi
-          echo "Release ID: ${RELEASE_ID}"
-
-          find src-tauri/target/release/bundle -type f \( -name "*.deb" -o -name "*.rpm" -o -name "*.AppImage" \) | while IFS= read -r file; do
-            filename=$(basename "$file")
-            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
-            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
-
-            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
-            if [ -n "${ASSET_ID}" ]; then
-              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
-                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
-            fi
-
-            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+          for workflow in build-app-linux.yml build-app-windows.yml build-app-macos.yml; do
+            echo "Dispatching ${workflow} for ${RELEASE_TAG}..."
+            HTTP_CODE=$(curl -s -w "%{http_code}" -o /tmp/dispatch_resp.txt -X POST \
               -H "Authorization: token ${BUILD_TOKEN}" \
-              -H "Content-Type: application/octet-stream" \
-              -T "$file" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
-            echo "Upload response: HTTP ${HTTP_CODE}"
-          done
-
-  build-windows:
-    name: Build App (Windows)
-    needs: bump-version
-    runs-on: windows-latest
-    env:
-      NODE_VERSION: "20"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ needs.bump-version.outputs.tag }}
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-
-      - name: Install Rust stable
-        shell: powershell
-        run: |
-          if (Get-Command rustup -ErrorAction SilentlyContinue) {
-            rustup default stable
-          } else {
-            Invoke-WebRequest -Uri https://win.rustup.rs/x86_64 -OutFile rustup-init.exe
-            .\rustup-init.exe -y --default-toolchain stable
-            echo "$env:USERPROFILE\.cargo\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
-          }
-
-      - name: Install npm dependencies
-        shell: powershell
-        run: npm ci
-
-      - name: Build Tauri app
-        shell: powershell
-        run: npm run tauri build
-
-      - name: Upload to release
-        shell: powershell
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          $REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
-          $Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
-          $TAG = "${{ needs.bump-version.outputs.tag }}"
-          Write-Host "Release tag: ${TAG}"
-
-          $release = Invoke-RestMethod -Uri "${REPO_API}/releases/tags/${TAG}" -Headers $Headers -ErrorAction Stop
-          $RELEASE_ID = $release.id
-          Write-Host "Release ID: ${RELEASE_ID}"
-
-          Get-ChildItem -Path src-tauri\target\release\bundle -Recurse -Include *.msi,*-setup.exe | ForEach-Object {
-            $filename = $_.Name
-            $encodedName = [System.Uri]::EscapeDataString($filename)
-            $size = [math]::Round($_.Length / 1MB, 1)
-            Write-Host "Uploading ${filename} (${size} MB)..."
-
-            try {
-              $assets = Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets" -Headers $Headers
-              $existing = $assets | Where-Object { $_.name -eq $filename }
-              if ($existing) {
-                Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets/$($existing.id)" -Method Delete -Headers $Headers
-              }
-            } catch {}
-
-            $uploadUrl = "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encodedName}"
-            $result = curl.exe --fail --silent --show-error `
-              -X POST `
-              -H "Authorization: token $env:BUILD_TOKEN" `
-              -H "Content-Type: application/octet-stream" `
-              -T "$($_.FullName)" `
-              "$uploadUrl" 2>&1
-            if ($LASTEXITCODE -eq 0) {
-              Write-Host "Upload successful: ${filename}"
-            } else {
-              Write-Host "WARNING: Upload failed for ${filename}: ${result}"
-            }
-          }
-
-  build-macos:
-    name: Build App (macOS)
-    needs: bump-version
-    runs-on: macos-latest
-    env:
-      NODE_VERSION: "20"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ needs.bump-version.outputs.tag }}
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-
-      - name: Install Rust stable
-        run: |
-          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
-          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
-
-      - name: Install system dependencies
-        run: brew install --quiet create-dmg || true
-
-      - name: Install npm dependencies
-        run: npm ci
-
-      - name: Build Tauri app
-        run: npm run tauri build
-
-      - name: Upload to release
-        env:
-          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
-        run: |
-          which jq || brew install jq
-          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ needs.bump-version.outputs.tag }}"
-          echo "Release tag: ${TAG}"
-
-          RELEASE_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-            "${REPO_API}/releases/tags/${TAG}" | jq -r '.id // empty')
-
-          if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
-            echo "ERROR: Failed to find release for tag ${TAG}."
-            exit 1
-          fi
-          echo "Release ID: ${RELEASE_ID}"
-
-          find src-tauri/target/release/bundle -type f -name "*.dmg" | while IFS= read -r file; do
-            filename=$(basename "$file")
-            encoded_name=$(echo "$filename" | sed 's/ /%20/g')
-            echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
-
-            ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
-            if [ -n "${ASSET_ID}" ]; then
-              curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
-                "${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
-            fi
-
-            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
-              -H "Authorization: token ${BUILD_TOKEN}" \
-              -H "Content-Type: application/octet-stream" \
-              -T "$file" \
-              "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
-            echo "Upload response: HTTP ${HTTP_CODE}"
+              -H "Content-Type: application/json" \
+              -d "{\"ref\": \"main\", \"inputs\": {\"tag\": \"${RELEASE_TAG}\"}}" \
+              "${REPO_API}/actions/workflows/${workflow}/dispatches")
+            echo "  -> HTTP ${HTTP_CODE}"
+            if [ "$HTTP_CODE" != "204" ]; then cat /tmp/dispatch_resp.txt; echo ""; fi
           done

.gitea/workflows/sidecar-release.yml

@@ -0,0 +1,102 @@
+name: Sidecar Release
+
+on:
+  workflow_dispatch:
+
+jobs:
+  test:
+    name: Run Tests
+    if: "!contains(github.event.head_commit.message, '[skip ci]')"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Python tests
+        run: |
+          uv venv .testvenv
+          VIRTUAL_ENV=.testvenv uv pip install pytest httpx pytest-asyncio anyio fastapi pydantic pyyaml uvicorn requests
+          .testvenv/bin/python -m pytest backend/tests/ client/tests/ -v --tb=short
+
+  bump-sidecar-version:
+    name: Bump sidecar version and tag
+    needs: test
+    if: "!contains(github.event.head_commit.message, '[skip ci]')"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+
+      - name: Configure git
+        run: |
+          git config user.name "Gitea Actions"
+          git config user.email "actions@gitea.local"
+
+      - name: Bump sidecar patch version
+        run: |
+          CURRENT=$(grep '^version = ' pyproject.toml | head -1 | sed 's/version = "\(.*\)"/\1/')
+          echo "Current sidecar version: ${CURRENT}"
+
+          MAJOR=$(echo "${CURRENT}" | cut -d. -f1)
+          MINOR=$(echo "${CURRENT}" | cut -d. -f2)
+          PATCH=$(echo "${CURRENT}" | cut -d. -f3)
+          NEW_PATCH=$((PATCH + 1))
+          NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
+          echo "New sidecar version: ${NEW_VERSION}"
+
+          sed -i "s/^version = \"${CURRENT}\"/version = \"${NEW_VERSION}\"/" pyproject.toml
+
+          # Write to env file instead of step outputs (avoids act runner bug)
+          echo "NEW_VERSION=${NEW_VERSION}" >> $GITHUB_ENV
+          echo "RELEASE_TAG=sidecar-v${NEW_VERSION}" >> $GITHUB_ENV
+
+      - name: Commit and tag
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          git add pyproject.toml
+          git commit -m "chore: bump sidecar version to ${NEW_VERSION} [skip ci]"
+          git tag "${RELEASE_TAG}"
+
+          REMOTE_URL=$(git remote get-url origin | sed "s|://|://gitea-actions:${BUILD_TOKEN}@|")
+          git pull --rebase "${REMOTE_URL}" main || true
+          git push "${REMOTE_URL}" HEAD:main
+          git push "${REMOTE_URL}" "${RELEASE_TAG}"
+
+      - name: Create Gitea release
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          RELEASE_NAME="Sidecar v${NEW_VERSION}"
+
+          curl -s -X POST \
+            -H "Authorization: token ${BUILD_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d "{\"tag_name\": \"${RELEASE_TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated sidecar build.\", \"draft\": false, \"prerelease\": false}" \
+            "${REPO_API}/releases"
+          echo "Created release: ${RELEASE_NAME}"
+
+      - name: Trigger per-OS sidecar builds
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+
+          for workflow in build-sidecar-linux.yml build-sidecar-windows.yml build-sidecar-macos.yml build-sidecar-cloud.yml; do
+            echo "Dispatching ${workflow} for ${RELEASE_TAG}..."
+            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
+              -H "Authorization: token ${BUILD_TOKEN}" \
+              -H "Content-Type: application/json" \
+              -d "{\"ref\": \"main\", \"inputs\": {\"tag\": \"${RELEASE_TAG}\"}}" \
+              "${REPO_API}/actions/workflows/${workflow}/dispatches")
+            echo "  -> HTTP ${HTTP_CODE}"
+          done
+
+      # NOTE: Automatic cleanup disabled -- it races with async builds.
+      # Clean up old releases manually from the Gitea UI when needed.

.gitea/workflows/test.yml

@@ -0,0 +1,66 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  python-tests:
+    name: Python Backend Tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        run: |
+          if command -v uv &> /dev/null; then
+            echo "uv already installed: $(uv --version)"
+          else
+            curl -LsSf https://astral.sh/uv/install.sh | sh
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Run pytest
+        run: |
+          uv venv .testvenv
+          VIRTUAL_ENV=.testvenv uv pip install pytest httpx pytest-asyncio anyio fastapi pydantic pyyaml uvicorn requests
+          .testvenv/bin/python -m pytest backend/tests/ client/tests/ -v --tb=short
+
+  frontend-tests:
+    name: Frontend Tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run Vitest
+        run: npx vitest run
+
+  rust-tests:
+    name: Rust Sidecar Tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust
+        run: |
+          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
+          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+      - name: Install Tauri system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf
+
+      - name: Run cargo test
+        working-directory: src-tauri
+        run: cargo test

.gitignore

@@ -10,8 +10,8 @@ dist/
 downloads/
 eggs/
 .eggs/
-lib/
-lib64/
+/lib/
+/lib64/
 parts/
 sdist/
 var/
@@ -63,3 +63,6 @@ dist/
 
 # Tauri
 src-tauri/target/
+
+# Windows NTFS alternate data streams
+*:Zone.Identifier

CLAUDE.md

@@ -4,52 +4,114 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project Overview
 
-Local Transcription is a desktop application for real-time speech-to-text transcription designed for streamers. It uses Whisper models (via faster-whisper) to transcribe audio locally with optional multi-user server synchronization.
+Local Transcription is a cross-platform desktop application for real-time speech-to-text transcription designed for streamers. It supports local Whisper models and cloud-based Deepgram transcription, with OBS browser source integration and optional multi-user sync.
+
+**Architecture:** Two-process model — a Tauri v2 shell (Svelte 5 frontend) communicates with a headless Python backend (sidecar) via REST API and WebSocket.
 
 **Key Features:**
-- Standalone desktop GUI (PySide6/Qt)
-- Local transcription with CPU/GPU support
-- Built-in web server for OBS browser source integration
-- Optional Node.js-based multi-user server for syncing transcriptions across users
-- Noise suppression and Voice Activity Detection (VAD)
-- Cross-platform builds (Linux/Windows) with PyInstaller
+- Cross-platform desktop app (Windows, macOS, Linux) via Tauri v2 + Svelte 5
+- Headless Python backend with FastAPI control API
+- Dual transcription modes: local Whisper or cloud Deepgram (managed/BYOK)
+- Built-in web server for OBS browser source at `http://localhost:8080`
+- Optional multi-user sync via Node.js server
+- CUDA, MPS (Apple Silicon), and CPU support
+- Auto-updates, custom fonts, configurable colors
+
+> **Legacy GUI:** The original PySide6/Qt GUI (`main.py`, `gui/`) still works during the transition. New features should target the Tauri frontend and headless backend.
 
 ## Project Structure
 
 ```
 local-transcription/
-├── client/                   # Core transcription logic
-│   ├── audio_capture.py      # Audio input and buffering
-│   ├── transcription_engine.py # Whisper model integration
+├── src/                             # Svelte 5 frontend (Tauri UI)
+│   ├── App.svelte                   # Main app shell
+│   ├── app.css                      # Global dark theme styles
+│   ├── main.ts                      # Svelte mount point
+│   ├── lib/components/              # UI components
+│   │   ├── Header.svelte            # Title bar + settings button
+│   │   ├── StatusBar.svelte         # State indicator, device, user info
+│   │   ├── Controls.svelte          # Start/Stop, Clear, Save buttons
+│   │   ├── TranscriptionDisplay.svelte  # Scrolling transcript view
+│   │   └── Settings.svelte          # Full settings modal (all sections)
+│   └── lib/stores/                  # Svelte 5 reactive stores ($state/$derived)
+│       ├── backend.ts               # WebSocket + REST API client
+│       ├── config.ts                # App configuration fetch/update
+│       └── transcriptions.ts        # Transcript data management
+├── src-tauri/                       # Tauri v2 Rust shell
+│   ├── src/lib.rs                   # Plugin registration (shell, dialog, process)
+│   ├── src/main.rs                  # Entry point
+│   ├── tauri.conf.json              # Window, bundle, plugin config
+│   └── Cargo.toml                   # Rust dependencies
+├── backend/                         # Headless Python backend (the sidecar)
+│   ├── app_controller.py            # Core orchestration (engine, sync, config)
+│   ├── api_server.py                # FastAPI REST endpoints + /ws/control
+│   └── main_headless.py             # Headless entry point (prints JSON to stdout)
+├── client/                          # Core transcription modules (used by backend)
+│   ├── audio_capture.py             # Audio input handling
+│   ├── transcription_engine_realtime.py  # RealtimeSTT / Whisper engine
+│   ├── deepgram_transcription.py    # Deepgram WebSocket cloud transcription
 │   ├── noise_suppression.py         # VAD and noise reduction
-│   ├── device_utils.py       # CPU/GPU device management
-│   ├── config.py             # Configuration management
-│   └── server_sync.py        # Multi-user server sync client
-├── gui/                      # Desktop application UI
-│   ├── main_window_qt.py     # Main application window (PySide6)
-│   ├── settings_dialog_qt.py # Settings dialog (PySide6)
+│   ├── device_utils.py              # CPU/GPU/MPS detection
+│   ├── config.py                    # YAML config management (~/.local-transcription/)
+│   ├── server_sync.py               # Multi-user server sync client
+│   ├── instance_lock.py             # Single-instance PID lock
+│   └── update_checker.py            # Gitea release update checker
+├── gui/                             # Legacy PySide6/Qt GUI (still functional)
+│   ├── main_window_qt.py            # Main window (orchestration lives here in legacy)
+│   ├── settings_dialog_qt.py        # Settings dialog
 │   └── transcription_display_qt.py  # Display widget
-├── server/                   # Web display servers
-│   ├── web_display.py        # FastAPI server for OBS browser source (local)
-│   └── nodejs/               # Optional multi-user Node.js server
-│       ├── server.js         # Multi-user sync server with WebSocket
-│       ├── package.json      # Node.js dependencies
-│       └── README.md         # Server deployment documentation
-├── config/                   # Example configuration files
-│   └── default_config.yaml   # Default settings template
-├── main.py                   # GUI application entry point
+├── server/
+│   ├── web_display.py               # FastAPI OBS display server (WebSocket + HTML)
+│   └── nodejs/                      # Optional multi-user sync server
+├── .gitea/workflows/                # CI/CD
+│   ├── release.yml                  # Coordinator: version bump, tag, release creation
+│   ├── build-app-linux.yml          # Linux Tauri app build (triggered by v* tag)
+│   ├── build-app-windows.yml        # Windows Tauri app build (triggered by v* tag)
+│   ├── build-app-macos.yml          # macOS Tauri app build (triggered by v* tag)
+│   ├── sidecar-release.yml          # Sidecar coordinator: version bump, tag, release
+│   ├── build-sidecar-linux.yml      # Linux sidecar build (triggered by sidecar-v* tag)
+│   ├── build-sidecar-windows.yml    # Windows sidecar build (triggered by sidecar-v* tag)
+│   └── build-sidecar-macos.yml      # macOS sidecar build (triggered by sidecar-v* tag)
+├── config/default_config.yaml       # Default settings template
+├── main.py                          # Legacy PySide6 GUI entry point
 ├── main_cli.py                      # CLI version for testing
-└── pyproject.toml           # Dependencies and build config
+├── version.py                       # Version string (__version__)
+├── local-transcription.spec         # PyInstaller config (legacy, includes PySide6)
+├── local-transcription-headless.spec # PyInstaller config (headless sidecar, no Qt)
+├── pyproject.toml                   # Python deps (uv, CUDA PyTorch index)
+├── package.json                     # Node/Tauri deps
+└── vite.config.ts                   # Vite build config ($lib alias)
 ```
 
 ## Development Commands
 
-### Installation and Setup
+### Frontend (Tauri + Svelte)
 ```bash
-# Install dependencies (creates .venv automatically)
+# Install npm dependencies
+npm install
+
+# Run Tauri in development mode (hot-reload)
+npm run tauri dev
+
+# Build frontend only (for testing)
+npx vite build
+
+# Type-check Svelte
+npx svelte-check
+
+# Check Rust compiles
+cd src-tauri && cargo check
+```
+
+### Backend (Python)
+```bash
+# Install Python dependencies
 uv sync
 
-# Run the GUI application
+# Run the headless backend standalone (for development)
+uv run python -m backend.main_headless --port 8080
+
+# Run the legacy PySide6 GUI
 uv run python main.py
 
 # Run CLI version (headless, for testing)
@@ -57,257 +119,163 @@ uv run python main_cli.py
 
 # List available audio devices
 uv run python main_cli.py --list-devices
-
-# Install with CUDA support (if needed)
-uv pip install torch --index-url https://download.pytorch.org/whl/cu121
 ```
 
-### Building Executables
+### Building
 ```bash
-# Linux (includes CUDA support - works on both GPU and CPU systems)
-./build.sh
+# Build Tauri app (produces platform installer)
+npm run tauri build
 
-# Windows (includes CUDA support - works on both GPU and CPU systems)
-build.bat
+# Build headless Python sidecar (no PySide6)
+uv run pyinstaller local-transcription-headless.spec
+# Output: dist/local-transcription-backend/
 
-# Manual build with PyInstaller
-uv sync                          # Install dependencies (includes CUDA PyTorch)
-uv pip uninstall -q enum34       # Remove incompatible enum34 package
+# Build legacy PySide6 app
 uv run pyinstaller local-transcription.spec
+# Or use: ./build.sh (Linux) / build.bat (Windows)
 ```
 
-**Important:** All builds include CUDA support via `pyproject.toml` configuration. CUDA builds can be created on systems without NVIDIA GPUs. The PyTorch CUDA runtime is bundled, and the app automatically falls back to CPU if no GPU is available.
-
 ### Testing
 ```bash
-# Run component tests
 uv run python test_components.py
-
-# Check CUDA availability
 uv run python check_cuda.py
-
-# Test web server manually
-uv run python -m uvicorn server.web_display:app --reload
 ```
 
-## Architecture
+## Architecture Details
 
-### Audio Processing Pipeline
+### Communication: Tauri <-> Python Backend
 
-1. **Audio Capture** ([client/audio_capture.py](client/audio_capture.py))
-   - Captures audio from microphone/system using sounddevice
-   - Handles automatic sample rate detection and resampling
-   - Uses chunking with overlap for better transcription quality
-   - Default: 3-second chunks with 0.5s overlap
+The Svelte frontend connects to the Python backend via two channels:
 
-2. **Noise Suppression** ([client/noise_suppression.py](client/noise_suppression.py))
-   - Applies noisereduce for background noise reduction
-   - Voice Activity Detection (VAD) using webrtcvad
-   - Skips silent segments to improve performance
+**REST API** (on port 8081 by default):
+- `GET /api/status` — app state, device info, version
+- `POST /api/start` / `POST /api/stop` — transcription control
+- `GET /api/config` / `PUT /api/config` — read/write settings (dot-notation keys)
+- `GET /api/audio-devices` / `GET /api/compute-devices` — device enumeration
+- `POST /api/reload-engine` — reload with new model/device
+- `GET /api/transcriptions` / `POST /api/clear` — transcript management
+- `POST /api/save-file` — write text to a file path
+- `GET /api/check-update` / `POST /api/skip-version` — update management
+- `POST /api/login` / `POST /api/register` / `GET /api/balance` — managed mode proxy
 
-3. **Transcription** ([client/transcription_engine.py](client/transcription_engine.py))
-   - Uses faster-whisper for efficient inference
-   - Supports CPU, CUDA, and Apple MPS (Mac)
-   - Models: tiny, base, small, medium, large
-   - Thread-safe model loading with locks
+**WebSocket** `/ws/control`:
+- Pushes real-time events: `state_changed`, `transcription`, `preview`, `error`, `credits_low`
+- Client sends keepalive pings
 
-4. **Display** ([gui/main_window_qt.py](gui/main_window_qt.py))
-   - PySide6/Qt-based desktop GUI
-   - Real-time transcription display with scrolling
-   - Settings panel with live updates (no restart needed)
+The OBS display server runs separately on port 8080 (`GET /` for HTML, `WebSocket /ws` for transcriptions).
 
-### Web Server Architecture
+### Backend Process Lifecycle
 
-**Local Web Server** ([server/web_display.py](server/web_display.py))
-- Always runs when GUI starts (port 8080 by default)
-- FastAPI with WebSocket for real-time updates
-- Used for OBS browser source integration
-- Single-user (displays only local transcriptions)
+1. `main_headless.py` starts, acquires instance lock, creates `AppController`
+2. `AppController.initialize()` starts the OBS web server (port 8080) and engine init thread
+3. `APIServer` wraps the controller with FastAPI routes, runs on port 8081
+4. Backend prints `{"event": "ready", "port": 8080}` to stdout for Tauri to discover
+5. On shutdown: engine stopped, web server stopped, lock released
 
-**Multi-User Server** (Optional - for syncing across multiple users)
+### Headless Backend vs Legacy GUI
 
-**Node.js WebSocket Server** ([server/nodejs/](server/nodejs/)) - **RECOMMENDED**
-- Real-time WebSocket support (< 100ms latency)
-- Handles 100+ concurrent users
-- Easy deployment to VPS/cloud hosting (Railway, Heroku, DigitalOcean, or any VPS)
-- Configurable display options via URL parameters:
-  - `timestamps=true/false` - Show/hide timestamps
-  - `maxlines=50` - Maximum visible lines (prevents scroll bars in OBS)
-  - `fontsize=16` - Font size in pixels
-  - `fontfamily=Arial` - Font family
-  - `fade=10` - Seconds before text fades (0 = never)
+The `AppController` class (`backend/app_controller.py`) extracts all orchestration logic from `gui/main_window_qt.py` into a Qt-free class. The mapping:
 
-See [server/nodejs/README.md](server/nodejs/README.md) for deployment instructions
+| Legacy (MainWindow) | Headless (AppController) |
+|---------------------|--------------------------|
+| `_initialize_components()` | `_initialize_engine()` |
+| `_start_transcription()` | `start_transcription()` |
+| `_stop_transcription()` | `stop_transcription()` |
+| `_on_settings_saved()` | `apply_settings()` |
+| `_reload_engine()` | `reload_engine()` |
+| `_start_web_server_if_enabled()` | `_start_web_server()` |
+| `_start_server_sync()` | `_start_server_sync()` |
+| Qt signals | Callbacks (`on_state_changed`, `on_transcription`, etc.) |
 
-### Configuration System
+### Threading Model (Headless)
 
-- Config stored at `~/.local-transcription/config.yaml`
-- Managed by [client/config.py](client/config.py)
-- Settings apply immediately without restart (except model changes)
-- YAML format with nested keys (e.g., `transcription.model`)
+- Main thread: Uvicorn (FastAPI) event loop
+- Engine init thread: Downloads models, initializes VAD
+- Web server thread: Separate asyncio loop for OBS display
+- Audio capture: Runs in engine callback threads
+- All results flow through `AppController` callbacks -> `APIServer` WebSocket broadcast
 
-### Device Management
+### Svelte Frontend
 
-- [client/device_utils.py](client/device_utils.py) handles CPU/GPU detection
-- Auto-detects CUDA, MPS (Mac), or falls back to CPU
-- Compute types: float32 (best quality), float16 (GPU), int8 (fastest)
-- Thread-safe device selection
+Uses Svelte 5 runes throughout (`$state`, `$derived`, `$effect`, `$props`). No Svelte 4 patterns.
 
-## Key Implementation Details
+**Stores** (`src/lib/stores/`):
+- `backend.ts` — WebSocket connection + REST helpers (`apiGet`, `apiPost`, `apiPut`), auto-reconnect
+- `config.ts` — fetches/updates config from backend API
+- `transcriptions.ts` — manages transcript list, listens for `CustomEvent`s from backend store
 
-### PyInstaller Build Configuration
+**Key patterns:**
+- Backend store dispatches `CustomEvent`s on `window` for cross-store communication
+- Settings component collects all changed values into a `Record<string, any>` with dot-notation keys, sends via `PUT /api/config`
+- Controls use Tauri dialog plugin for native file save, falls back to blob download
 
-- [local-transcription.spec](local-transcription.spec) controls build
-- UPX compression enabled for smaller executables
-- Hidden imports required for PySide6, faster-whisper, torch
-- Console mode enabled by default (set `console=False` to hide)
+## CI/CD
 
-### Threading Model
+Eight Gitea Actions workflows in `.gitea/workflows/`, split into coordinators and per-OS builders:
 
-- Main thread: Qt GUI event loop
-- Audio thread: Captures and processes audio chunks
-- Web server thread: Runs FastAPI server
-- Transcription: Runs in callback thread from audio capture
-- All transcription results communicated via Qt signals
+**App release (Tauri):**
+- **`release.yml`**: Coordinator. Triggers on push to `main`. Auto-bumps version in package.json/tauri.conf.json/Cargo.toml/version.py, commits, tags `v{VERSION}`, creates Gitea release.
+- **`build-app-linux.yml`**: Triggers on `v*` tag push or `workflow_dispatch`. Builds Tauri app, uploads `.deb`/`.rpm`/`.AppImage`.
+- **`build-app-windows.yml`**: Triggers on `v*` tag push or `workflow_dispatch`. Builds Tauri app, uploads `.msi`/`*-setup.exe`.
+- **`build-app-macos.yml`**: Triggers on `v*` tag push or `workflow_dispatch`. Builds Tauri app, uploads `.dmg`.
 
-### Server Sync (Optional Multi-User Feature)
+**Sidecar release (Python backend):**
+- **`sidecar-release.yml`**: Coordinator. Triggers on push to `main` with changes in `client/`, `server/`, `backend/`, `pyproject.toml`, or `local-transcription-headless.spec`. Bumps version in pyproject.toml/version.py, tags `sidecar-v{VERSION}`, creates Gitea release.
+- **`build-sidecar-linux.yml`**: Triggers on `sidecar-v*` tag push or `workflow_dispatch`. Builds CUDA + CPU sidecars via PyInstaller.
+- **`build-sidecar-windows.yml`**: Triggers on `sidecar-v*` tag push or `workflow_dispatch`. Builds CUDA + CPU sidecars via PyInstaller.
+- **`build-sidecar-macos.yml`**: Triggers on `sidecar-v*` tag push or `workflow_dispatch`. Builds CPU-only sidecar via PyInstaller.
 
-- [client/server_sync.py](client/server_sync.py) handles server communication
-- Toggle in Settings: "Enable Server Sync"
-- Sends transcriptions to Node.js server via HTTP POST
-- Real-time updates via WebSocket to display page
-- Per-speaker font support (Web-Safe, Google Fonts, Custom uploads)
-- Falls back gracefully if server unavailable
+All per-OS build workflows can be re-run independently via `workflow_dispatch` with an optional `tag` input. All require a `BUILD_TOKEN` secret (Gitea API token with release write access).
 
 ## Common Patterns
 
 ### Adding a New Setting
 
-1. Add to [config/default_config.yaml](config/default_config.yaml)
-2. Update [client/config.py](client/config.py) if validation needed
-3. Add UI control in [gui/settings_dialog_qt.py](gui/settings_dialog_qt.py)
-4. Apply setting in relevant component (no restart if possible)
-5. Emit signal to update display if needed
+1. Add default to [config/default_config.yaml](config/default_config.yaml)
+2. Add UI control in [src/lib/components/Settings.svelte](src/lib/components/Settings.svelte)
+3. Ensure the setting is included in the save handler's config update
+4. Apply in `AppController.apply_settings()` or the relevant component
+5. For legacy GUI: also update [gui/settings_dialog_qt.py](gui/settings_dialog_qt.py)
+
+### Adding a New API Endpoint
+
+1. Add route in [backend/api_server.py](backend/api_server.py) `_setup_routes()`
+2. Add supporting logic in [backend/app_controller.py](backend/app_controller.py) if needed
+3. Call from Svelte via `backendStore.apiGet/apiPost/apiPut`
 
 ### Modifying Transcription Display
 
-- Local GUI: [gui/transcription_display_qt.py](gui/transcription_display_qt.py)
-- Local web display (OBS): [server/web_display.py](server/web_display.py) (HTML in `_get_html()`)
+- Tauri UI: [src/lib/components/TranscriptionDisplay.svelte](src/lib/components/TranscriptionDisplay.svelte)
+- OBS display: [server/web_display.py](server/web_display.py) (HTML in `_get_html()`)
 - Multi-user display: [server/nodejs/server.js](server/nodejs/server.js) (display page in `/display` route)
 
-### Adding a New Model Size
-
-- Update [client/transcription_engine.py](client/transcription_engine.py)
-- Add to model selector in [gui/settings_dialog_qt.py](gui/settings_dialog_qt.py)
-- Update CLI argument choices in [main_cli.py](main_cli.py)
-
 ## Dependencies
 
-**Core:**
-- `faster-whisper`: Optimized Whisper inference
-- `torch`: ML framework (CUDA-enabled via special index)
-- `PySide6`: Qt6 bindings for GUI
-- `sounddevice`: Cross-platform audio I/O
-- `noisereduce`, `webrtcvad`: Audio preprocessing
-
-**Web Server:**
-- `fastapi`, `uvicorn`: Web server and ASGI
-- `websockets`: Real-time communication
-
-**Build:**
-- `pyinstaller`: Create standalone executables
-- `uv`: Fast package manager
-
-**PyTorch CUDA Index:**
-- Configured in [pyproject.toml](pyproject.toml) under `[[tool.uv.index]]`
-- Uses PyTorch's custom wheel repository for CUDA builds
-- Automatically installed with `uv sync` when using CUDA build scripts
+**Frontend:** Tauri v2, Svelte 5, Vite, TypeScript
+**Backend:** Python 3.9+, FastAPI, Uvicorn, RealtimeSTT, faster-whisper, PyTorch (CUDA), sounddevice
+**Build:** PyInstaller (sidecar), Tauri CLI (app), uv (Python packages)
+**CI:** Gitea Actions with platform-specific runners
 
 ## Platform-Specific Notes
 
 ### Linux
-- Uses PulseAudio/ALSA for audio
-- Build scripts use bash (`.sh` files)
-- Executable: `dist/LocalTranscription/LocalTranscription`
+- Tauri needs: `libgtk-3-dev`, `libwebkit2gtk-4.1-dev`, `libappindicator3-dev`, `librsvg2-dev`, `patchelf`
+- Audio: PulseAudio/ALSA via sounddevice
 
 ### Windows
-- Uses Windows Audio/WASAPI
-- Build scripts use batch (`.bat` files)
-- Executable: `dist\LocalTranscription\LocalTranscription.exe`
-- Requires Visual C++ Redistributable on target systems
+- Tauri needs: WebView2 (usually pre-installed on Windows 10+)
+- Audio: WASAPI via sounddevice
 
-### Cross-Building
-- **Cannot cross-compile** - must build on target platform
-- CI/CD should use platform-specific runners
-
-## Troubleshooting
-
-### Model Loading Issues
-- Models download to `~/.cache/huggingface/`
-- First run requires internet connection
-- Check disk space (models: 75MB-3GB depending on size)
-
-### Audio Device Issues
-- Run `uv run python main_cli.py --list-devices`
-- Check permissions (microphone access)
-- Try different device indices in settings
-
-### GPU Not Detected
-- Run `uv run python check_cuda.py`
-- Install CUDA drivers (not CUDA toolkit - bundled in build)
-- Verify PyTorch sees GPU: `python -c "import torch; print(torch.cuda.is_available())"`
-
-### Web Server Port Conflicts
-- Default port: 8080
-- Change in [gui/main_window_qt.py](gui/main_window_qt.py) or config
-- Use `lsof -i :8080` (Linux) or `netstat -ano | findstr :8080` (Windows)
-
-## OBS Integration
-
-### Local Display (Single User)
-1. Start Local Transcription app
-2. In OBS: Add "Browser" source
-3. URL: `http://localhost:8080`
-4. Set dimensions (e.g., 1920x300)
-
-### Multi-User Display (Node.js Server)
-1. Deploy Node.js server (see [server/nodejs/README.md](server/nodejs/README.md))
-2. Each user configures Server URL: `http://your-server:3000/api/send`
-3. Enter same room name and passphrase
-4. In OBS: Add "Browser" source
-5. URL: `http://your-server:3000/display?room=ROOM&fade=10&timestamps=true&maxlines=50&fontsize=16`
-6. Customize URL parameters as needed:
-   - `timestamps=false` - Hide timestamps
-   - `maxlines=30` - Show max 30 lines (prevents scroll bars)
-   - `fontsize=18` - Larger font
-   - `fontfamily=Courier` - Different font
-
-## Performance Optimization
-
-**For Real-Time Transcription:**
-- Use `tiny` or `base` model (faster)
-- Enable GPU if available (5-10x faster)
-- Increase chunk_duration for better accuracy (higher latency)
-- Decrease chunk_duration for lower latency (less context)
-- Enable VAD to skip silent audio
-
-**For Build Size Reduction:**
-- Don't bundle models (download on demand)
-- Use CPU-only build if no GPU users
-- Enable UPX compression (already in spec)
-
-## Phase Status
-
-- ✅ **Phase 1**: Standalone desktop application (complete)
-- ✅ **Web Server**: Local OBS integration (complete)
-- ✅ **Builds**: PyInstaller executables (complete)
-- ✅ **Phase 2**: Multi-user Node.js server (complete, optional)
-- ⏸️ **Phase 3+**: Advanced features (see [NEXT_STEPS.md](NEXT_STEPS.md))
+### macOS
+- Tauri needs: Xcode Command Line Tools
+- Audio: CoreAudio via sounddevice
+- GPU: MPS (Apple Silicon) detected by `device_utils.py`
+- `Info.plist` must include `NSMicrophoneUsageDescription` for mic access
+- No CUDA builds — CPU/MPS only
 
 ## Related Documentation
 
-- [README.md](README.md) - User-facing documentation
-- [BUILD.md](BUILD.md) - Detailed build instructions
-- [INSTALL.md](INSTALL.md) - Installation guide
-- [NEXT_STEPS.md](NEXT_STEPS.md) - Future enhancements
-- [server/nodejs/README.md](server/nodejs/README.md) - Node.js server setup and deployment
+- [README.md](README.md) — User-facing documentation
+- [BUILD.md](BUILD.md) — Detailed build instructions
+- [INSTALL.md](INSTALL.md) — Installation guide
+- [server/nodejs/README.md](server/nodejs/README.md) — Node.js server setup

README.md

@@ -1,13 +1,14 @@
 # Local Transcription
 
-A real-time speech-to-text desktop application for streamers. Run locally on your machine with GPU or CPU, display transcriptions via OBS browser source, and optionally sync with other users through a multi-user server.
+A real-time speech-to-text desktop application for streamers. Runs locally on your machine with GPU or CPU, displays transcriptions via OBS browser source, and optionally syncs with other users through a multi-user server.
 
 **Version 1.4.0**
 
 ## Features
 
 - **Real-Time Transcription**: Live speech-to-text using Whisper models with minimal latency
-- **Standalone Desktop App**: PySide6/Qt GUI that works without any server
+- **Cross-Platform**: Native desktop app for Windows, macOS, and Linux via [Tauri](https://tauri.app/)
+- **Dual Transcription Modes**: Local (Whisper) or cloud (Deepgram) with managed billing or BYOK
 - **CPU & GPU Support**: Automatic detection of CUDA (NVIDIA), MPS (Apple Silicon), or CPU fallback
 - **Advanced Voice Detection**: Dual-layer VAD (WebRTC + Silero) for accurate speech detection
 - **OBS Integration**: Built-in web server for browser source capture at `http://localhost:8080`
@@ -16,36 +17,70 @@ A real-time speech-to-text desktop application for streamers. Run locally on you
 - **Customizable Colors**: User-configurable colors for name, text, and background
 - **Noise Suppression**: Built-in audio preprocessing to reduce background noise
 - **Auto-Updates**: Automatic update checking with release notes display
-- **Cross-Platform**: Builds available for Windows and Linux
+
+## Architecture
+
+The application uses a two-process architecture:
+
+1. **Tauri Shell** (Svelte 5 frontend) — lightweight native window (~50MB) rendering the UI
+2. **Python Backend** (sidecar) — headless process running transcription, audio capture, and the OBS web server
+
+The Tauri frontend communicates with the Python backend via REST API and WebSocket, following the same pattern as [voice-to-notes](https://repo.anhonesthost.net/MacroPad/voice-to-notes).
+
+```
+Tauri App (user launches this)
+  └─ Spawns Python backend as sidecar
+       ├─ FastAPI REST API (control endpoints)
+       ├─ WebSocket /ws/control (real-time state + transcriptions)
+       ├─ OBS web display at http://localhost:8080
+       └─ Transcription engine (Whisper or Deepgram)
+```
+
+> **Legacy GUI**: The original PySide6/Qt desktop GUI (`main.py`) still works alongside the new Tauri frontend during the transition period.
 
 ## Quick Start
 
 ### Running from Source
 
 ```bash
-# Install dependencies
+# Install Python dependencies
 uv sync
 
-# Run the application
+# Run the Tauri app (frontend + backend)
+npm install
+npm run tauri dev
+
+# Or run just the headless backend (for development)
+uv run python -m backend.main_headless
+
+# Or run the legacy PySide6 GUI
 uv run python main.py
 ```
 
 ### Using Pre-Built Executables
 
-Download the latest release from the [releases page](https://repo.anhonesthost.net/streamer-tools/local-transcription/releases) and run the executable for your platform.
+Download the latest release from the [releases page](https://repo.anhonesthost.net/streamer-tools/local-transcription/releases):
+
+- **App installer** (Tauri shell): `.msi` (Windows), `.dmg` (macOS), `.deb`/`.rpm`/`.AppImage` (Linux)
+- **Sidecar** (Python backend): Download the matching `sidecar-*` zip for your platform (CUDA or CPU)
 
 ### Building from Source
 
-**Linux:**
 ```bash
-./build.sh
-# Output: dist/LocalTranscription/LocalTranscription
-```
+# Build the Tauri app
+npm install
+npm run tauri build
+# Output: src-tauri/target/release/bundle/
 
-**Windows:**
-```cmd
+# Build the Python sidecar (headless, no Qt)
+uv sync
+uv run pyinstaller local-transcription-headless.spec
+# Output: dist/local-transcription-backend/
+
+# Build the legacy PySide6 app (Linux)
+./build.sh
+# Build the legacy PySide6 app (Windows)
 build.bat
-# Output: dist\LocalTranscription\LocalTranscription.exe
 ```
 
 For detailed build instructions, see [BUILD.md](BUILD.md).
@@ -57,14 +92,23 @@ For detailed build instructions, see [BUILD.md](BUILD.md).
 1. Launch the application
 2. Select your microphone from the audio device dropdown
 3. Choose a Whisper model (smaller = faster, larger = more accurate):
-   - `tiny.en` / `tiny` - Fastest, good for quick captions
-   - `base.en` / `base` - Balanced speed and accuracy
-   - `small.en` / `small` - Better accuracy
-   - `medium.en` / `medium` - High accuracy
-   - `large-v3` - Best accuracy (requires more resources)
+   - `tiny.en` / `tiny` — Fastest, good for quick captions
+   - `base.en` / `base` — Balanced speed and accuracy
+   - `small.en` / `small` — Better accuracy
+   - `medium.en` / `medium` — High accuracy
+   - `large-v3` — Best accuracy (requires more resources)
 4. Click **Start** to begin transcription
 5. Transcriptions appear in the main window and at `http://localhost:8080`
 
+### Remote Transcription (Deepgram)
+
+Instead of local Whisper models, you can use cloud-based transcription:
+
+- **Managed mode**: Sign up via the transcription proxy for metered billing
+- **BYOK mode**: Bring your own Deepgram API key for direct access
+
+Configure in Settings > Remote Transcription.
+
 ### OBS Browser Source Setup
 
 1. Start the Local Transcription app
@@ -88,7 +132,7 @@ For syncing transcriptions across multiple users (e.g., multi-host streams or tr
 
 ## Configuration
 
-Settings are stored at `~/.local-transcription/config.yaml` and can be modified through the GUI settings panel.
+Settings are stored at `~/.local-transcription/config.yaml` and can be modified through the GUI settings panel or the REST API.
 
 ### Key Settings
 
@@ -100,6 +144,7 @@ Settings are stored at `~/.local-transcription/config.yaml` and can be modified
 | `transcription.silero_sensitivity` | VAD sensitivity (0-1, lower = more sensitive) | `0.4` |
 | `transcription.post_speech_silence_duration` | Silence before finalizing (seconds) | `0.3` |
 | `transcription.continuous_mode` | Fast speaker mode for quick talkers | `false` |
+| `remote.mode` | Transcription mode (local/managed/byok) | `local` |
 | `display.show_timestamps` | Show timestamps with transcriptions | `true` |
 | `display.fade_after_seconds` | Fade out time (0 = never) | `10` |
 | `display.font_source` | Font type (System Font/Web-Safe/Google Font/Custom File) | `System Font` |
@@ -111,70 +156,126 @@ See [config/default_config.yaml](config/default_config.yaml) for all available o
 
 ```
 local-transcription/
+├── src/                             # Svelte 5 frontend (Tauri UI)
+│   ├── App.svelte                   # Main app shell
+│   ├── lib/components/              # UI components
+│   │   ├── Header.svelte
+│   │   ├── StatusBar.svelte
+│   │   ├── Controls.svelte
+│   │   ├── TranscriptionDisplay.svelte
+│   │   └── Settings.svelte
+│   └── lib/stores/                  # Reactive state management
+│       ├── backend.ts               # WebSocket + REST API client
+│       ├── config.ts                # App configuration
+│       └── transcriptions.ts        # Transcription data
+├── src-tauri/                       # Tauri v2 Rust shell
+│   ├── src/main.rs
+│   └── tauri.conf.json
+├── backend/                         # Headless Python backend (sidecar)
+│   ├── app_controller.py            # Orchestration logic (engine, sync, config)
+│   ├── api_server.py                # FastAPI REST + WebSocket control API
+│   └── main_headless.py             # Headless entry point
 ├── client/                          # Core transcription modules
 │   ├── audio_capture.py             # Audio input handling
-│   ├── transcription_engine_realtime.py  # RealtimeSTT integration
+│   ├── transcription_engine_realtime.py  # RealtimeSTT / Whisper
+│   ├── deepgram_transcription.py    # Deepgram cloud transcription
 │   ├── noise_suppression.py         # VAD and noise reduction
-│   ├── device_utils.py          # CPU/GPU detection
+│   ├── device_utils.py              # CPU/GPU/MPS detection
 │   ├── config.py                    # Configuration management
 │   ├── server_sync.py               # Multi-user server client
 │   └── update_checker.py            # Auto-update functionality
-├── gui/                         # Desktop application UI
-│   ├── main_window_qt.py        # Main application window
-│   ├── settings_dialog_qt.py    # Settings dialog
-│   └── transcription_display_qt.py  # Display widget
+├── gui/                             # Legacy PySide6/Qt GUI
+│   ├── main_window_qt.py
+│   ├── settings_dialog_qt.py
+│   └── transcription_display_qt.py
 ├── server/                          # Web servers
 │   ├── web_display.py               # Local FastAPI server for OBS
 │   └── nodejs/                      # Multi-user sync server
-│       ├── server.js            # Express + WebSocket server
-│       └── README.md            # Deployment instructions
+├── .gitea/workflows/                # CI/CD
+│   ├── release.yml                  # Tauri app builds (all platforms)
+│   └── build-sidecar.yml            # Python sidecar builds (CUDA + CPU)
 ├── config/
 │   └── default_config.yaml          # Default settings template
-├── main.py                      # GUI entry point
+├── main.py                          # Legacy GUI entry point
 ├── main_cli.py                      # CLI version (for testing)
-├── build.sh                     # Linux build script
-├── build.bat                    # Windows build script
-└── local-transcription.spec     # PyInstaller configuration
+├── local-transcription.spec         # PyInstaller config (legacy, with PySide6)
+├── local-transcription-headless.spec # PyInstaller config (headless sidecar)
+├── pyproject.toml                   # Python dependencies
+└── package.json                     # Node.js / Tauri dependencies
 ```
 
 ## Technology Stack
 
-### Desktop Application
+### Frontend (Tauri)
+- **Tauri v2** — Native cross-platform shell (Rust)
+- **Svelte 5** — Reactive UI framework (TypeScript)
+- **Vite** — Frontend build tool
+
+### Backend (Python Sidecar)
 - **Python 3.9+**
-- **PySide6** - Qt6 GUI framework
-- **RealtimeSTT** - Real-time speech-to-text with advanced VAD
-- **faster-whisper** - Optimized Whisper model inference
-- **PyTorch** - ML framework (CUDA-enabled)
-- **sounddevice** - Cross-platform audio capture
-- **webrtcvad + silero_vad** - Voice activity detection
-- **noisereduce** - Noise suppression
+- **FastAPI + Uvicorn** — REST API and WebSocket server
+- **RealtimeSTT** — Real-time speech-to-text with advanced VAD
+- **faster-whisper** — Optimized Whisper model inference (CTranslate2)
+- **PyTorch** — ML framework (CUDA-enabled builds available)
+- **sounddevice** — Cross-platform audio capture
+- **webrtcvad + silero_vad** — Voice activity detection
 
-### Web Servers
-- **FastAPI + Uvicorn** - Local web display server
-- **Node.js + Express + WebSocket** - Multi-user sync server
+### Multi-User Server (Optional)
+- **Node.js + Express + WebSocket** — Real-time sync server
 
-### Build Tools
-- **PyInstaller** - Executable packaging
-- **uv** - Fast Python package manager
+### Build & CI/CD
+- **PyInstaller** — Python sidecar packaging
+- **Tauri CLI** — App bundling (.msi, .dmg, .deb, .rpm, .AppImage)
+- **Gitea Actions** — Automated cross-platform builds
+- **uv** — Fast Python package manager
+
+## CI/CD
+
+Two Gitea Actions workflows in `.gitea/workflows/`:
+
+| Workflow | Trigger | Produces |
+|----------|---------|----------|
+| `release.yml` | Push to `main` | Tauri app installers for all platforms |
+| `build-sidecar.yml` | Changes to `client/`, `server/`, `backend/`, or `pyproject.toml` | Python sidecar zips (CUDA + CPU) |
+
+Both workflows require a `BUILD_TOKEN` secret in the repo settings (Gitea API token with release write access).
+
+### Release Artifacts
+
+| Platform | App Installer | Sidecar (CUDA) | Sidecar (CPU) |
+|----------|--------------|----------------|---------------|
+| Linux x86_64 | `.deb`, `.rpm`, `.AppImage` | `sidecar-linux-x86_64-cuda.zip` | `sidecar-linux-x86_64-cpu.zip` |
+| Windows x86_64 | `.msi`, `-setup.exe` | `sidecar-windows-x86_64-cuda.zip` | `sidecar-windows-x86_64-cpu.zip` |
+| macOS ARM64 | `.dmg` | — | `sidecar-macos-aarch64-cpu.zip` |
 
 ## System Requirements
 
 ### Minimum
-- Python 3.9+
 - 4GB RAM
 - Any modern CPU
 
-### Recommended (for real-time performance)
+### Recommended (for local real-time transcription)
 - 8GB+ RAM
 - NVIDIA GPU with CUDA support (for GPU acceleration)
-- FFmpeg (installed automatically with dependencies)
 
 ### For Building
-- **Linux**: gcc, Python dev headers
-- **Windows**: Visual Studio Build Tools, Python dev headers
+- **Tauri app**: Node.js 20+, Rust stable, platform SDK (see [Tauri prerequisites](https://tauri.app/start/prerequisites/))
+- **Python sidecar**: Python 3.9+, uv, PyInstaller
+- **Linux**: `libgtk-3-dev`, `libwebkit2gtk-4.1-dev`, `libappindicator3-dev`, `librsvg2-dev`, `patchelf`
+- **Windows**: Visual Studio Build Tools, WebView2
+- **macOS**: Xcode Command Line Tools
 
 ## Troubleshooting
 
+### macOS: "App is damaged and can't be opened"
+macOS Gatekeeper blocks unsigned applications. Since the app is not yet signed with an Apple Developer certificate, you need to remove the quarantine flag before opening:
+
+```bash
+xattr -cr "/Applications/Local Transcription.app"
+```
+
+Then open the app normally. You only need to do this once after downloading.
+
 ### Model Loading Issues
 - Models download automatically on first use to `~/.cache/huggingface/`
 - First run requires internet connection
@@ -185,7 +286,7 @@ local-transcription/
 # List available audio devices
 uv run python main_cli.py --list-devices
 ```
-- Ensure microphone permissions are granted
+- Ensure microphone permissions are granted (especially on macOS)
 - Try different device indices in settings
 
 ### GPU Not Detected
@@ -193,13 +294,13 @@ uv run python main_cli.py --list-devices
 # Check CUDA availability
 uv run python -c "import torch; print(torch.cuda.is_available())"
 ```
-- Install NVIDIA drivers (CUDA toolkit is bundled)
+- Install NVIDIA drivers (CUDA toolkit is bundled in CUDA sidecar builds)
 - The app automatically falls back to CPU if no GPU is available
 
 ### Web Server Port Conflicts
-- Default port is 8080
+- Default port is 8080; the app tries ports 8080-8084 automatically
 - Change in settings or edit config file
-- Check for conflicts: `lsof -i :8080` (Linux) or `netstat -ano | findstr :8080` (Windows)
+- Check for conflicts: `lsof -i :8080` (Linux/macOS) or `netstat -ano | findstr :8080` (Windows)
 
 ## Use Cases
 
@@ -222,3 +323,5 @@ MIT License
 - [OpenAI Whisper](https://github.com/openai/whisper) for the speech recognition model
 - [RealtimeSTT](https://github.com/KoljaB/RealtimeSTT) for real-time transcription capabilities
 - [faster-whisper](https://github.com/guillaumekln/faster-whisper) for optimized inference
+- [Tauri](https://tauri.app/) for the cross-platform desktop framework
+- [Deepgram](https://deepgram.com/) for cloud transcription API

backend/api_server.py

@@ -99,11 +99,19 @@ class APIServer:
 
         self.controller.on_credits_low = on_credits_low
 
+    def set_event_loop(self, loop: asyncio.AbstractEventLoop):
+        """Set the event loop used for broadcasting (call from uvicorn startup)."""
+        self._event_loop = loop
+
     def _broadcast_control(self, data: dict):
         """Send a message to all connected /ws/control clients."""
         if not self.control_connections:
             return
 
+        loop = getattr(self, '_event_loop', None)
+        if loop is None:
+            return
+
         message = json.dumps(data)
         disconnected = []
 
@@ -111,7 +119,7 @@ class APIServer:
             try:
                 asyncio.run_coroutine_threadsafe(
                     ws.send_text(message),
-                    asyncio.get_event_loop(),
+                    loop,
                 )
             except Exception:
                 disconnected.append(ws)
@@ -124,6 +132,10 @@ class APIServer:
         app = self.app
         ctrl = self.controller
 
+        @app.on_event("startup")
+        async def on_startup():
+            self.set_event_loop(asyncio.get_event_loop())
+
         # ── Status ─────────────────────────────────────────────
 
         @app.get("/api/status")
@@ -139,14 +151,24 @@ class APIServer:
 
         @app.post("/api/start")
         async def start_transcription():
-            success, message = ctrl.start_transcription()
+            import asyncio
+            # Run in thread pool to avoid blocking the event loop
+            # (start_recording can block up to 15s waiting for Deepgram WS)
+            loop = asyncio.get_event_loop()
+            success, message = await loop.run_in_executor(
+                None, ctrl.start_transcription
+            )
             if not success:
                 raise HTTPException(status_code=400, detail=message)
             return {"status": "ok", "message": message}
 
         @app.post("/api/stop")
         async def stop_transcription():
-            success, message = ctrl.stop_transcription()
+            import asyncio
+            loop = asyncio.get_event_loop()
+            success, message = await loop.run_in_executor(
+                None, ctrl.stop_transcription
+            )
             if not success:
                 raise HTTPException(status_code=400, detail=message)
             return {"status": "ok", "message": message}
@@ -211,7 +233,11 @@ class APIServer:
 
         @app.post("/api/reload-engine")
         async def reload_engine():
-            success, message = ctrl.reload_engine()
+            import asyncio
+            loop = asyncio.get_event_loop()
+            success, message = await loop.run_in_executor(
+                None, ctrl.reload_engine
+            )
             if not success:
                 raise HTTPException(status_code=500, detail=message)
             return {"status": "ok", "message": message}

backend/app_controller.py

@@ -18,13 +18,18 @@ import sys
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
 
 from client.config import Config
-from client.device_utils import DeviceManager
-from client.transcription_engine_realtime import RealtimeTranscriptionEngine, TranscriptionResult
+from client.models import TranscriptionResult
 from client.deepgram_transcription import DeepgramTranscriptionEngine
 from client.server_sync import ServerSyncClient
 from server.web_display import TranscriptionWebServer
 from version import __version__
 
+# Heavy imports (torch, RealtimeSTT, faster-whisper) are deferred so
+# the cloud-only sidecar build can exclude them entirely.
+# Imported lazily in _initialize_engine() when remote.mode == "local".
+RealtimeTranscriptionEngine = None
+DeviceManager = None
+
 
 class AppState:
     """Enum-like class for application states."""
@@ -89,7 +94,24 @@ class AppController:
 
     def __init__(self, config: Optional[Config] = None):
         self.config = config or Config()
-        self.device_manager = DeviceManager()
+
+        # DeviceManager is only needed for local Whisper mode.
+        # Lazy-import to keep the cloud-only sidecar lightweight.
+        global DeviceManager
+        if DeviceManager is None:
+            try:
+                from client.device_utils import DeviceManager as _DM
+                DeviceManager = _DM
+            except ImportError:
+                DeviceManager = None
+
+        self.device_manager = DeviceManager() if DeviceManager else None
+        self.is_cloud_only = DeviceManager is None
+
+        # If this is the cloud-only sidecar and mode is still "local",
+        # auto-switch to "byok" so the engine doesn't try to load Whisper.
+        if self.is_cloud_only and self.config.get('remote.mode', 'local') == 'local':
+            self.config.set('remote.mode', 'byok')
 
         # State
         self._state = AppState.INITIALIZING
@@ -243,15 +265,12 @@ class AppController:
 
     def _initialize_engine(self):
         """Initialize the transcription engine in a background thread."""
-        device_config = self.config.get('transcription.device', 'auto')
-        self.device_manager.set_device(device_config)
-
         audio_device_str = self.config.get('audio.input_device', 'default')
         audio_device = None if audio_device_str == 'default' else int(audio_device_str)
 
         model = self.config.get('transcription.model', 'base.en')
         language = self.config.get('transcription.language', 'en')
-        device = self.device_manager.get_device_for_whisper()
+        device_config = self.config.get('transcription.device', 'auto')
         compute_type = self.config.get('transcription.compute_type', 'default')
 
         self.current_model_size = model
@@ -284,6 +303,27 @@ class AppController:
             self.transcription_engine.set_error_callback(self._on_remote_error)
             self.transcription_engine.set_credits_low_callback(self._on_credits_low)
         else:
+            # Lazy-import heavy local transcription dependencies
+            global RealtimeTranscriptionEngine
+            if RealtimeTranscriptionEngine is None:
+                try:
+                    from client.transcription_engine_realtime import RealtimeTranscriptionEngine as _RTE
+                    RealtimeTranscriptionEngine = _RTE
+                except ImportError:
+                    # Cloud-only sidecar -- local engine not available
+                    self._set_state(
+                        AppState.ERROR,
+                        "Local transcription not available in this build. "
+                        "Please switch to Cloud (Deepgram) mode in Settings."
+                    )
+                    return
+
+            if self.device_manager:
+                self.device_manager.set_device(device_config)
+                device = self.device_manager.get_device_for_whisper()
+            else:
+                device = "cpu"
+
             self.transcription_engine = RealtimeTranscriptionEngine(
                 model=model,
                 device=device,
@@ -332,6 +372,14 @@ class AppController:
                 device_display = "Unknown"
 
             self._set_state(AppState.READY, f"Ready | Device: {device_display}")
+        else:
+            # Cloud sidecar with no API key -- show helpful setup message
+            # instead of a scary error. The user needs to enter their key.
+            if self.is_cloud_only:
+                self._set_state(
+                    AppState.READY,
+                    "Setup needed: Open Settings > Remote Transcription > enter your Deepgram API key"
+                )
             else:
                 self._set_state(AppState.ERROR, message)
 
@@ -348,7 +396,14 @@ class AppController:
         try:
             success = self.transcription_engine.start_recording()
             if not success:
-                return False, "Failed to start recording"
+                import logging
+                # Check if there's a recent error in the logger
+                err_detail = getattr(self.transcription_engine, '_last_error', '')
+                msg = f"Failed to start recording"
+                if err_detail:
+                    msg += f": {err_detail}"
+                print(f"ERROR: {msg}")
+                return False, msg
 
             # Start server sync if enabled
             if self.config.get('server_sync.enabled', False):
@@ -577,12 +632,18 @@ class AppController:
             if self.config.get('server_sync.enabled', False):
                 self._start_server_sync()
 
-        # Check if model/device changed
+        # Check if model/device/remote mode changed -- any of these require
+        # a full engine reload since they change which engine class is used
         new_model = self.config.get('transcription.model', 'base.en')
         new_device = self.config.get('transcription.device', 'auto')
+        new_remote_mode = self.config.get('remote.mode', 'local')
+        current_remote_mode = 'local'
+        if self.transcription_engine:
+            current_remote_mode = getattr(self.transcription_engine, 'mode', 'local')
         engine_reload_needed = (
             self.current_model_size != new_model
             or self.current_device_config != new_device
+            or current_remote_mode != new_remote_mode
         )
 
         if engine_reload_needed:
@@ -596,7 +657,7 @@ class AppController:
         host = self.config.get('web_server.host', '127.0.0.1')
         port = self.actual_web_port or self.config.get('web_server.port', 8080)
 
-        device_info = self.device_manager.get_device_info()
+        device_info = self.device_manager.get_device_info() if self.device_manager else []
 
         remote_mode = self.config.get('remote.mode', 'local')
         if remote_mode in ('managed', 'byok') and self.transcription_engine:
@@ -640,10 +701,13 @@ class AppController:
 
     def get_compute_devices(self) -> list[dict]:
         """List available compute devices."""
-        device_info = self.device_manager.get_device_info()
         devices = [{"id": "auto", "name": "Auto-detect"}]
+        if self.device_manager:
+            device_info = self.device_manager.get_device_info()
             for dev_id, dev_name in device_info:
                 devices.append({"id": dev_id, "name": dev_name})
+        else:
+            devices.append({"id": "cloud", "name": "Cloud (Deepgram)"})
         return devices
 
     # ── Update Checking ────────────────────────────────────────────

backend/main_headless.py

@@ -88,11 +88,16 @@ def main():
         # Create API server wrapping the controller
         api_server = APIServer(controller)
 
-        # Determine actual port (web server may have shifted if port was in use)
-        actual_port = controller.actual_web_port or args.port
+        # OBS display runs on the configured port, API server on port+1
+        obs_port = controller.actual_web_port or args.port
+        api_port = obs_port + 1
 
-        # Print ready event so Tauri can discover the port
-        print(json.dumps({"event": "ready", "port": actual_port}), flush=True)
+        # Print ready event so Tauri can discover the API port
+        print(json.dumps({
+            "event": "ready",
+            "port": api_port,
+            "obs_port": obs_port,
+        }), flush=True)
 
         # Run the API server (blocks)
         import uvicorn
@@ -104,7 +109,7 @@ def main():
         uvicorn.run(
             api_server.app,
             host=args.host,
-            port=actual_port + 1,  # API on port+1, OBS display on the main port
+            port=api_port,
             log_level="error",
             access_log=False,
         )

backend/tests/conftest.py

@@ -0,0 +1,159 @@
+"""Shared fixtures for backend tests.
+
+Heavy third-party modules (torch, sounddevice, numpy, RealtimeSTT, etc.) are
+stubbed at the *sys.modules* level before any backend code is imported.  This
+lets the test suite run on a plain Python install without GPU drivers, audio
+hardware, or heavyweight ML libraries.
+"""
+
+import sys
+import types
+from pathlib import Path
+from unittest.mock import MagicMock
+
+import pytest
+
+# ── Project root on sys.path ────────────────────────────────────────
+project_root = Path(__file__).resolve().parent.parent.parent
+if str(project_root) not in sys.path:
+    sys.path.insert(0, str(project_root))
+
+
+# ── Stub heavy modules before anything imports them ─────────────────
+
+def _stub(name: str) -> types.ModuleType:
+    """Create a stub module and register it in sys.modules if not already present."""
+    if name in sys.modules:
+        return sys.modules[name]
+    mod = types.ModuleType(name)
+    sys.modules[name] = mod
+    return mod
+
+
+# numpy -- must behave like a real module for `import numpy as np`
+_np = _stub("numpy")
+_np.float32 = float
+_np.float64 = float
+_np.int16 = int
+_np.ndarray = MagicMock
+_np.array = MagicMock(return_value=MagicMock())
+_np.zeros = MagicMock(return_value=MagicMock())
+_np.frombuffer = MagicMock(return_value=MagicMock())
+
+# torch + sub-modules
+_torch = _stub("torch")
+_torch.cuda = MagicMock()
+_torch.cuda.is_available = MagicMock(return_value=False)
+_torch.backends = MagicMock()
+_torch.backends.mps = MagicMock()
+_torch.backends.mps.is_available = MagicMock(return_value=False)
+_stub("torch.cuda")
+_stub("torch.backends")
+_stub("torch.backends.mps")
+_stub("torchaudio")
+
+# sounddevice
+_sd = _stub("sounddevice")
+_sd.query_devices = MagicMock(return_value=[])
+
+# RealtimeSTT (imported by transcription_engine_realtime)
+_rtstt = _stub("RealtimeSTT")
+_rtstt.AudioToTextRecorder = MagicMock
+
+# faster_whisper (sometimes imported transitively)
+_stub("faster_whisper")
+
+# noisereduce
+_stub("noisereduce")
+
+# scipy
+_scipy = _stub("scipy")
+_stub("scipy.signal")
+_stub("scipy.io")
+_stub("scipy.io.wavfile")
+
+# webrtcvad
+_stub("webrtcvad")
+
+# openwakeword
+_stub("openwakeword")
+
+# pvporcupine
+_stub("pvporcupine")
+
+# PySide6 (should not be needed, but just in case)
+_stub("PySide6")
+_stub("PySide6.QtWidgets")
+_stub("PySide6.QtCore")
+_stub("PySide6.QtGui")
+
+# websockets
+_ws = _stub("websockets")
+_ws.connect = MagicMock
+
+# deepgram  (cloud transcription)
+_stub("deepgram")
+
+
+# ── Fixtures ────────────────────────────────────────────────────────
+
+@pytest.fixture
+def mock_config(tmp_path):
+    """Return a Config object backed by a temporary file.
+
+    This avoids touching the real user config at ~/.local-transcription/.
+    """
+    config_file = tmp_path / "test_config.yaml"
+    from client.config import Config
+
+    config = Config(config_path=str(config_file))
+    return config
+
+
+@pytest.fixture
+def controller(mock_config):
+    """Return an AppController wired to *mock_config* without starting heavy
+    subsystems (engine, web server, device manager).
+
+    The transcription engine, web server thread, and DeviceManager are all
+    replaced with lightweight mocks so the test suite can run without a GPU,
+    audio hardware, or a free network port.
+    """
+    from unittest.mock import patch
+
+    with patch("backend.app_controller.DeviceManager") as MockDM, \
+         patch("backend.app_controller.RealtimeTranscriptionEngine"), \
+         patch("backend.app_controller.DeepgramTranscriptionEngine"), \
+         patch("backend.app_controller.TranscriptionWebServer"), \
+         patch("backend.app_controller.ServerSyncClient"):
+
+        # DeviceManager stub
+        dm_instance = MagicMock()
+        dm_instance.get_device_info.return_value = [("cpu", "CPU")]
+        dm_instance.get_device_for_whisper.return_value = "cpu"
+        MockDM.return_value = dm_instance
+
+        from backend.app_controller import AppController
+
+        ctrl = AppController(config=mock_config)
+        yield ctrl
+
+
+@pytest.fixture
+def api_client(controller):
+    """Return an httpx.AsyncClient speaking ASGI to the APIServer's FastAPI app.
+
+    Usage in tests::
+
+        async def test_something(api_client):
+            resp = await api_client.get("/api/status")
+            assert resp.status_code == 200
+    """
+    from backend.api_server import APIServer
+    import httpx
+
+    api = APIServer(controller)
+
+    transport = httpx.ASGITransport(app=api.app)
+    client = httpx.AsyncClient(transport=transport, base_url="http://testserver")
+    return client

backend/tests/test_api_server.py

@@ -0,0 +1,150 @@
+"""Tests for backend.api_server.APIServer REST endpoints."""
+
+import sys
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+import pytest_asyncio
+
+# Ensure project root is on path
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(project_root))
+
+
+# ── GET /api/status ─────────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_get_status(api_client):
+    resp = await api_client.get("/api/status")
+    assert resp.status_code == 200
+    data = resp.json()
+    assert "state" in data
+    assert "is_transcribing" in data
+    assert "version" in data
+    assert "web_server" in data
+
+
+# ── GET /api/config ─────────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_get_config(api_client):
+    resp = await api_client.get("/api/config")
+    assert resp.status_code == 200
+    data = resp.json()
+    # The config should be a dict (the raw config mapping)
+    assert isinstance(data, dict)
+
+
+# ── PUT /api/config ─────────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_put_config(api_client, controller):
+    """Updating config via PUT should persist and return success."""
+    # Patch reload_engine to avoid heavy lifting
+    controller.reload_engine = MagicMock(return_value=(True, "ok"))
+    controller.current_model_size = "base.en"
+    controller.current_device_config = "auto"
+    controller.config.set("transcription.model", "base.en")
+    controller.config.set("transcription.device", "auto")
+
+    resp = await api_client.put(
+        "/api/config",
+        json={"settings": {"display.font_size": 24}},
+    )
+    assert resp.status_code == 200
+    body = resp.json()
+    assert body["status"] == "ok"
+
+    # Verify the value was actually saved
+    assert controller.config.get("display.font_size") == 24
+
+
+# ── POST /api/start (engine not ready) ─────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_start_when_not_ready(api_client, controller):
+    """Starting transcription without an engine should return 400."""
+    controller.transcription_engine = None
+    resp = await api_client.post("/api/start")
+    assert resp.status_code == 400
+
+
+# ── POST /api/clear ─────────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_clear(api_client, controller):
+    from client.models import TranscriptionResult
+    from datetime import datetime
+
+    controller.transcriptions = [
+        TranscriptionResult(text="One", is_final=True, timestamp=datetime.now(), user_name="U"),
+    ]
+
+    resp = await api_client.post("/api/clear")
+    assert resp.status_code == 200
+    body = resp.json()
+    assert body["cleared"] == 1
+    assert len(controller.transcriptions) == 0
+
+
+# ── GET /api/audio-devices ──────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_get_audio_devices(api_client, controller):
+    """Audio devices endpoint should return a list, even when mocked."""
+    # Mock sounddevice so the test works without audio hardware
+    with patch("backend.app_controller.AppController.get_audio_devices",
+               return_value=[{"index": 0, "name": "Mock Mic"}]):
+        resp = await api_client.get("/api/audio-devices")
+    assert resp.status_code == 200
+    data = resp.json()
+    assert "devices" in data
+    assert len(data["devices"]) >= 1
+
+
+# ── GET /api/compute-devices ────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_get_compute_devices(api_client, controller):
+    resp = await api_client.get("/api/compute-devices")
+    assert resp.status_code == 200
+    data = resp.json()
+    assert "devices" in data
+    # At minimum we get the "Auto-detect" entry
+    assert any(d["id"] == "auto" for d in data["devices"])
+
+
+# ── GET /api/check-update ──────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_check_update(api_client, controller):
+    """check-update should return a dict with an 'available' key."""
+    with patch.object(controller, "check_for_updates",
+                      return_value={"available": False, "current_version": "1.0.0"}):
+        resp = await api_client.get("/api/check-update")
+    assert resp.status_code == 200
+    data = resp.json()
+    assert "available" in data
+
+
+# ── GET /api/version ────────────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_version(api_client):
+    resp = await api_client.get("/api/version")
+    assert resp.status_code == 200
+    data = resp.json()
+    assert "version" in data
+    # Should be a non-empty string
+    assert isinstance(data["version"], str)
+    assert len(data["version"]) > 0

backend/tests/test_app_controller.py

@@ -0,0 +1,183 @@
+"""Tests for backend.app_controller.AppController."""
+
+import sys
+from datetime import datetime
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+# Ensure project root is on path
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(project_root))
+
+from backend.app_controller import AppState
+
+
+# ── basic state ─────────────────────────────────────────────────────
+
+
+def test_initial_state(controller):
+    """A freshly constructed controller should be INITIALIZING and not transcribing."""
+    assert controller.state == AppState.INITIALIZING
+    assert controller.is_transcribing is False
+
+
+# ── start / stop ────────────────────────────────────────────────────
+
+
+def test_start_transcription_without_engine(controller):
+    """Starting transcription before the engine is ready should fail gracefully."""
+    controller.transcription_engine = None
+    success, message = controller.start_transcription()
+    assert success is False
+    assert "not ready" in message.lower()
+
+
+def test_start_stop_cycle(controller):
+    """Full start -> stop cycle with a mocked engine that reports ready."""
+    engine = MagicMock()
+    engine.is_ready.return_value = True
+    engine.start_recording.return_value = True
+    controller.transcription_engine = engine
+
+    # Start
+    ok, msg = controller.start_transcription()
+    assert ok is True
+    assert controller.is_transcribing is True
+    assert controller.state == AppState.TRANSCRIBING
+
+    # Stop
+    ok, msg = controller.stop_transcription()
+    assert ok is True
+    assert controller.is_transcribing is False
+    engine.stop_recording.assert_called_once()
+
+
+def test_double_start_rejected(controller):
+    """Calling start_transcription twice should reject the second call."""
+    engine = MagicMock()
+    engine.is_ready.return_value = True
+    engine.start_recording.return_value = True
+    controller.transcription_engine = engine
+
+    controller.start_transcription()
+    success, message = controller.start_transcription()
+    assert success is False
+    assert "already" in message.lower()
+
+
+# ── transcription storage ───────────────────────────────────────────
+
+
+def test_clear_transcriptions(controller):
+    """clear_transcriptions should empty the list and return the count."""
+    from client.models import TranscriptionResult
+
+    controller.transcriptions = [
+        TranscriptionResult(text="Hello", is_final=True, timestamp=datetime.now(), user_name="Alice"),
+        TranscriptionResult(text="World", is_final=True, timestamp=datetime.now(), user_name="Bob"),
+    ]
+    count = controller.clear_transcriptions()
+    assert count == 2
+    assert len(controller.transcriptions) == 0
+
+
+def test_get_transcriptions_text_with_timestamps(controller):
+    """get_transcriptions_text should include [HH:MM:SS] prefixes when requested."""
+    from client.models import TranscriptionResult
+
+    ts = datetime(2025, 1, 15, 10, 30, 45)
+    controller.transcriptions = [
+        TranscriptionResult(text="Test line", is_final=True, timestamp=ts, user_name="User"),
+    ]
+
+    text = controller.get_transcriptions_text(include_timestamps=True)
+    assert "[10:30:45]" in text
+    assert "User:" in text
+    assert "Test line" in text
+
+
+# ── settings / engine reload ────────────────────────────────────────
+
+
+def test_apply_settings_triggers_reload_on_model_change(controller):
+    """Changing the transcription model should trigger an engine reload."""
+    controller.current_model_size = "base.en"
+    controller.current_device_config = "auto"
+
+    # Patch reload_engine so it doesn't actually try to spin up threads
+    controller.reload_engine = MagicMock(return_value=(True, "reloaded"))
+
+    reloaded, msg = controller.apply_settings({
+        "transcription.model": "small.en",
+    })
+
+    assert reloaded is True
+    controller.reload_engine.assert_called_once()
+
+
+def test_apply_settings_no_reload_when_same(controller):
+    """If model and device haven't changed, no reload should happen."""
+    controller.current_model_size = "base.en"
+    controller.current_device_config = "auto"
+
+    # Ensure config returns the same values
+    controller.config.set("transcription.model", "base.en")
+    controller.config.set("transcription.device", "auto")
+    # Remote mode must also match (no engine means current mode is 'local')
+    controller.config.set("remote.mode", "local")
+
+    controller.reload_engine = MagicMock(return_value=(True, "reloaded"))
+
+    reloaded, msg = controller.apply_settings({
+        "display.font_size": 20,
+    })
+
+    assert reloaded is False
+    controller.reload_engine.assert_not_called()
+
+
+# ── transcription callbacks ─────────────────────────────────────────
+
+
+def test_on_final_transcription_callback_fires(controller):
+    """_on_final_transcription should append and invoke on_transcription callback."""
+    from client.models import TranscriptionResult
+
+    received = []
+    controller.on_transcription = lambda data: received.append(data)
+
+    controller.is_transcribing = True
+    controller._set_state(AppState.TRANSCRIBING)
+
+    result = TranscriptionResult(
+        text="Hello world",
+        is_final=True,
+        timestamp=datetime.now(),
+        user_name="Tester",
+    )
+    controller._on_final_transcription(result)
+
+    assert len(controller.transcriptions) == 1
+    assert len(received) == 1
+    assert received[0]["text"] == "Hello world"
+    assert received[0]["user_name"] == "Tester"
+    assert received[0]["is_preview"] is False
+
+
+def test_on_final_transcription_ignored_when_not_transcribing(controller):
+    """If the controller is not in transcribing state the callback should be a no-op."""
+    from client.models import TranscriptionResult
+
+    controller.is_transcribing = False
+
+    result = TranscriptionResult(
+        text="Should be ignored",
+        is_final=True,
+        timestamp=datetime.now(),
+        user_name="Ghost",
+    )
+    controller._on_final_transcription(result)
+
+    assert len(controller.transcriptions) == 0

backend/tests/test_main_headless.py

@@ -0,0 +1,56 @@
+"""Tests for backend.main_headless ready-event JSON format."""
+
+import sys
+from pathlib import Path
+
+import pytest
+
+# Ensure project root is on path
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(project_root))
+
+
+def test_ready_event_reports_api_port_not_obs_port():
+    """The ready JSON printed by main_headless must set ``port`` to
+    ``obs_port + 1`` (the API port), not the OBS display port.
+
+    From main_headless.py::
+
+        obs_port = controller.actual_web_port or args.port
+        api_port = obs_port + 1
+
+        print(json.dumps({
+            "event": "ready",
+            "port": api_port,
+            "obs_port": obs_port,
+        }), flush=True)
+
+    We verify this contract by reading the source and checking the
+    structure directly (running main() would start a real server).
+    """
+    import ast
+    import textwrap
+
+    source_path = project_root / "backend" / "main_headless.py"
+    source = source_path.read_text()
+
+    # Verify the key relationships exist in the source:
+    # 1. api_port = obs_port + 1
+    assert "api_port = obs_port + 1" in source, (
+        "Expected `api_port = obs_port + 1` in main_headless.py"
+    )
+
+    # 2. The ready event JSON uses api_port for "port", not obs_port
+    assert '"port": api_port' in source or "'port': api_port" in source, (
+        "The ready event should report api_port as 'port'"
+    )
+
+    # 3. obs_port is also included separately
+    assert '"obs_port": obs_port' in source or "'obs_port': obs_port" in source, (
+        "The ready event should also include 'obs_port'"
+    )
+
+    # 4. Verify the event name
+    assert '"event": "ready"' in source or "'event': 'ready'" in source, (
+        "The ready event should have event='ready'"
+    )

client/deepgram_transcription.py

@@ -17,7 +17,7 @@ from datetime import datetime
 from queue import Queue, Empty
 from typing import Optional, Callable
 
-from client.transcription_engine_realtime import TranscriptionResult
+from client.models import TranscriptionResult
 
 logger = logging.getLogger(__name__)
 
@@ -67,7 +67,7 @@ class DeepgramTranscriptionEngine:
         # Audio parameters
         self.sample_rate: int = 16000
         self.channels: int = 1
-        self.blocksize: int = 4096
+        self.blocksize: int = 1024  # ~64ms chunks for lower latency streaming
 
         # Callbacks
         self.realtime_callback: Optional[Callable[[TranscriptionResult], None]] = None
@@ -156,17 +156,30 @@ class DeepgramTranscriptionEngine:
             return True
 
         self._stop_event.clear()
+        self._ws_connected = threading.Event()
         self._is_recording = True
 
         # Start the asyncio event-loop thread (handles WS send/receive)
         self._thread = threading.Thread(target=self._run_event_loop, daemon=True)
         self._thread.start()
 
+        # Wait for the WebSocket to connect before starting audio capture.
+        # Without this, audio chunks arrive before the WS is open -> broken pipe.
+        if not self._ws_connected.wait(timeout=15):
+            logger.error("Timed out waiting for Deepgram WebSocket connection")
+            print("ERROR: Timed out waiting for Deepgram WebSocket connection")
+            self._last_error = "Timed out connecting to Deepgram"
+            self._is_recording = False
+            self._stop_event.set()
+            return False
+
         # Start the audio capture stream
         try:
             self._start_audio_stream()
         except Exception as exc:
             logger.error("Failed to open audio stream: %s", exc)
+            print(f"ERROR: Failed to open audio stream: {exc}")
+            self._last_error = f"Audio stream error: {exc}"
             self._is_recording = False
             self._stop_event.set()
             return False
@@ -283,6 +296,11 @@ class DeepgramTranscriptionEngine:
                 if not await self._managed_handshake():
                     return
 
+            # Signal that the WebSocket is connected and ready
+            logger.info("WebSocket connected to Deepgram")
+            if hasattr(self, '_ws_connected'):
+                self._ws_connected.set()
+
             # Run send and receive concurrently
             await asyncio.gather(
                 self._send_loop(),
@@ -314,6 +332,8 @@ class DeepgramTranscriptionEngine:
             f"model={self.deepgram_model}"
             f"&language={self.language}"
             "&interim_results=true"
+            "&punctuate=true"
+            "&smart_format=true"
             "&encoding=linear16"
             f"&sample_rate={self.sample_rate}"
             f"&channels={self.channels}"
@@ -370,10 +390,16 @@ class DeepgramTranscriptionEngine:
 
     async def _send_loop(self):
         """Drain the audio queue and push raw PCM bytes over the WebSocket."""
+        loop = asyncio.get_event_loop()
         while not self._stop_event.is_set():
             try:
-                pcm_bytes = self._audio_queue.get(timeout=0.1)
-            except Empty:
+                # Use run_in_executor to avoid blocking the async event loop
+                # (which would stall the receive loop and delay transcriptions)
+                pcm_bytes = await asyncio.wait_for(
+                    loop.run_in_executor(None, lambda: self._audio_queue.get(timeout=0.5)),
+                    timeout=1.0,
+                )
+            except (Empty, asyncio.TimeoutError):
                 continue
 
             try:

client/models.py

@@ -0,0 +1,29 @@
+"""Shared data models used across transcription engines."""
+
+from datetime import datetime
+
+
+class TranscriptionResult:
+    """Represents a transcription result."""
+
+    def __init__(self, text: str, is_final: bool, timestamp: datetime, user_name: str = ""):
+        """
+        Initialize transcription result.
+
+        Args:
+            text: Transcribed text
+            is_final: Whether this is a final transcription or realtime preview
+            timestamp: Timestamp of transcription
+            user_name: Name of the user/speaker
+        """
+        self.text = text.strip()
+        self.is_final = is_final
+        self.timestamp = timestamp
+        self.user_name = user_name
+
+    def __repr__(self) -> str:
+        time_str = self.timestamp.strftime("%H:%M:%S")
+        prefix = "[FINAL]" if self.is_final else "[PREVIEW]"
+        if self.user_name and self.user_name.strip():
+            return f"{prefix} [{time_str}] {self.user_name}: {self.text}"
+        return f"{prefix} [{time_str}] {self.text}"

client/tests/test_config.py

@@ -0,0 +1,78 @@
+"""Tests for client.config.Config."""
+
+import sys
+from pathlib import Path
+
+import pytest
+
+# Ensure project root is on path
+project_root = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(project_root))
+
+from client.config import Config
+
+
+@pytest.fixture
+def cfg(tmp_path):
+    """A Config backed by a temp file so we never touch the real user config."""
+    return Config(config_path=str(tmp_path / "test_config.yaml"))
+
+
+# ── dot-notation get ────────────────────────────────────────────────
+
+
+def test_dot_notation_get(cfg):
+    """Config.get should traverse nested dicts using dot-separated keys."""
+    cfg.config = {"audio": {"sample_rate": 16000}}
+    assert cfg.get("audio.sample_rate") == 16000
+
+
+# ── dot-notation set ────────────────────────────────────────────────
+
+
+def test_dot_notation_set(cfg):
+    """Config.set should create/update nested values via dot-separated keys."""
+    cfg.set("audio.sample_rate", 44100)
+    assert cfg.config["audio"]["sample_rate"] == 44100
+
+    # Also readable via .get
+    assert cfg.get("audio.sample_rate") == 44100
+
+
+# ── missing key returns default ─────────────────────────────────────
+
+
+def test_missing_key_returns_default(cfg):
+    """Accessing a nonexistent key should return the supplied default."""
+    assert cfg.get("nonexistent.path", "fallback") == "fallback"
+    assert cfg.get("also.missing") is None  # default default is None
+
+
+# ── nested set creates intermediate dicts ───────────────────────────
+
+
+def test_nested_set_creates_path(cfg):
+    """Setting a deeply nested key should create all intermediate dicts."""
+    cfg.config = {}
+    cfg.set("a.b.c.d", 42)
+
+    assert cfg.config["a"]["b"]["c"]["d"] == 42
+    assert cfg.get("a.b.c.d") == 42
+
+
+# ── save and reload round-trip ──────────────────────────────────────
+
+
+def test_save_and_reload(tmp_path):
+    """Values persisted via save() should survive a fresh Config load."""
+    config_file = str(tmp_path / "roundtrip.yaml")
+
+    # Create and populate
+    cfg1 = Config(config_path=config_file)
+    cfg1.set("user.name", "TestUser")
+    cfg1.set("transcription.model", "tiny.en")
+
+    # Load a fresh instance from the same file
+    cfg2 = Config(config_path=config_file)
+    assert cfg2.get("user.name") == "TestUser"
+    assert cfg2.get("transcription.model") == "tiny.en"

client/transcription_engine_realtime.py

@@ -8,30 +8,8 @@ from threading import Lock
 import logging
 
 
-class TranscriptionResult:
-    """Represents a transcription result."""
-
-    def __init__(self, text: str, is_final: bool, timestamp: datetime, user_name: str = ""):
-        """
-        Initialize transcription result.
-
-        Args:
-            text: Transcribed text
-            is_final: Whether this is a final transcription or realtime preview
-            timestamp: Timestamp of transcription
-            user_name: Name of the user/speaker
-        """
-        self.text = text.strip()
-        self.is_final = is_final
-        self.timestamp = timestamp
-        self.user_name = user_name
-
-    def __repr__(self) -> str:
-        time_str = self.timestamp.strftime("%H:%M:%S")
-        prefix = "[FINAL]" if self.is_final else "[PREVIEW]"
-        if self.user_name and self.user_name.strip():
-            return f"{prefix} [{time_str}] {self.user_name}: {self.text}"
-        return f"{prefix} [{time_str}] {self.text}"
+# Re-export TranscriptionResult from the shared models module for backward compatibility
+from client.models import TranscriptionResult  # noqa: F401
 
     def to_dict(self) -> dict:
         """Convert to dictionary."""

config/default_config.yaml

@@ -42,7 +42,7 @@ transcription:
 
 server_sync:
   enabled: false
-  url: "http://localhost:3000/api/send"
+  url: ""
   room: "default"
   passphrase: ""
   # Font settings are now in the display section (shared for local and server sync)
@@ -69,7 +69,7 @@ web_server:
   host: "127.0.0.1"
 
 remote:
-  mode: local  # local | managed | byok
+  mode: byok  # local | managed | byok
   server_url: ""  # Proxy server URL for managed mode (e.g., wss://your-proxy.com)
   auth_token: ""  # JWT stored after login (managed mode)
   byok_api_key: ""  # Deepgram API key for BYOK mode

local-transcription-cloud.spec

@@ -0,0 +1,169 @@
+# -*- mode: python ; coding: utf-8 -*-
+"""PyInstaller spec file for cloud-only Local Transcription backend.
+
+This builds a lightweight sidecar (~50MB) that only supports Deepgram
+cloud transcription (managed + BYOK). No local Whisper models, no
+PyTorch, no CUDA -- just audio capture and WebSocket streaming.
+"""
+
+import sys
+import os
+
+block_cipher = None
+is_windows = sys.platform == 'win32'
+
+from PyInstaller.utils.hooks import collect_submodules, collect_data_files
+
+# Data files
+datas = [
+    ('config/default_config.yaml', 'config'),
+]
+
+# Collect sounddevice's bundled PortAudio library (_sounddevice_data)
+try:
+    import sounddevice
+    sd_path = os.path.dirname(sounddevice.__file__)
+    sd_data = os.path.join(sd_path, '_sounddevice_data')
+    if os.path.exists(sd_data):
+        datas.append((sd_data, '_sounddevice_data'))
+        print(f"  + Collected sounddevice PortAudio data from {sd_data}")
+    # Also collect the package itself
+    sd_datas = collect_data_files('sounddevice')
+    if sd_datas:
+        datas += sd_datas
+        print(f"  + Collected {len(sd_datas)} sounddevice data files")
+except ImportError:
+    print("  - Warning: sounddevice not found")
+
+# Hidden imports -- only lightweight deps needed for Deepgram streaming
+hiddenimports = [
+    'sounddevice',
+    '_sounddevice_data',
+    'numpy',
+    # FastAPI and dependencies
+    'fastapi',
+    'fastapi.routing',
+    'fastapi.responses',
+    'starlette',
+    'starlette.applications',
+    'starlette.routing',
+    'starlette.responses',
+    'starlette.websockets',
+    'starlette.middleware',
+    'starlette.middleware.cors',
+    'pydantic',
+    'pydantic.fields',
+    'pydantic.main',
+    'anyio',
+    'anyio._backends',
+    'anyio._backends._asyncio',
+    'sniffio',
+    # Uvicorn
+    'uvicorn',
+    'uvicorn.logging',
+    'uvicorn.loops',
+    'uvicorn.loops.auto',
+    'uvicorn.protocols',
+    'uvicorn.protocols.http',
+    'uvicorn.protocols.http.auto',
+    'uvicorn.protocols.http.h11_impl',
+    'uvicorn.protocols.websockets',
+    'uvicorn.protocols.websockets.auto',
+    'uvicorn.protocols.websockets.wsproto_impl',
+    'uvicorn.lifespan',
+    'uvicorn.lifespan.on',
+    'h11',
+    'websockets',
+    'websockets.legacy',
+    'websockets.legacy.server',
+    # HTTP client
+    'requests',
+    'urllib3',
+    'certifi',
+    'charset_normalizer',
+]
+
+# Collect submodules for key packages
+print("Collecting submodules for cloud backend packages...")
+for package in ['fastapi', 'starlette', 'pydantic', 'pydantic_core', 'anyio', 'uvicorn', 'websockets', 'h11']:
+    try:
+        submodules = collect_submodules(package)
+        hiddenimports += submodules
+        print(f"  + Collected {len(submodules)} submodules from {package}")
+    except Exception as e:
+        print(f"  - Warning: Could not collect {package}: {e}")
+
+# Collect data files
+for package in ['fastapi', 'starlette', 'pydantic', 'uvicorn']:
+    try:
+        data_files = collect_data_files(package)
+        if data_files:
+            datas += data_files
+    except Exception:
+        pass
+
+# Pydantic critical deps
+hiddenimports += [
+    'colorsys', 'decimal', 'json', 'ipaddress', 'pathlib', 'uuid',
+    'email.message', 'typing_extensions',
+]
+
+a = Analysis(
+    ['backend/main_headless.py'],
+    pathex=[],
+    binaries=[],
+    datas=datas,
+    hiddenimports=hiddenimports,
+    hookspath=['hooks'],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[
+        # Exclude all heavy ML/local transcription deps
+        'torch', 'torchaudio', 'torchvision',
+        'faster_whisper', 'ctranslate2',
+        'RealtimeSTT', 'webrtcvad', 'webrtcvad_wheels',
+        'silero_vad', 'onnxruntime',
+        'openwakeword', 'pvporcupine', 'pyaudio',
+        'noisereduce', 'scipy',
+        # Exclude GUI frameworks
+        'PySide6', 'PyQt5', 'PyQt6', 'tkinter',
+        # Exclude other unnecessary heavy packages
+        'matplotlib', 'PIL', 'cv2',
+    ],
+    win_no_prefer_redirects=False,
+    win_private_assemblies=False,
+    cipher=block_cipher,
+    noarchive=False,
+)
+
+pyz = PYZ(a.pure, a.zipped_data, cipher=block_cipher)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    [],
+    exclude_binaries=True,
+    name='local-transcription-backend',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+    icon='LocalTranscription.ico' if is_windows else None,
+)
+
+coll = COLLECT(
+    exe,
+    a.binaries,
+    a.zipfiles,
+    a.datas,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    name='local-transcription-backend',
+)

local-transcription-headless.spec

@@ -38,6 +38,21 @@ datas = [
     (vad_assets_path, 'faster_whisper/assets'),
 ] + pvporcupine_data_files
 
+# Collect sounddevice's bundled PortAudio library (_sounddevice_data)
+try:
+    import sounddevice
+    sd_path = os.path.dirname(sounddevice.__file__)
+    sd_data = os.path.join(sd_path, '_sounddevice_data')
+    if os.path.exists(sd_data):
+        datas.append((sd_data, '_sounddevice_data'))
+        print(f"  + Collected sounddevice PortAudio data from {sd_data}")
+    sd_datas = collect_data_files('sounddevice')
+    if sd_datas:
+        datas += sd_datas
+        print(f"  + Collected {len(sd_datas)} sounddevice data files")
+except ImportError:
+    print("  - Warning: sounddevice not found")
+
 # Hidden imports -- NO PySide6/Qt needed for headless backend
 hiddenimports = [
     # Transcription engine
@@ -46,6 +61,7 @@ hiddenimports = [
     'faster_whisper.vad',
     'ctranslate2',
     'sounddevice',
+    '_sounddevice_data',
     'scipy',
     'scipy.signal',
     'numpy',

package.json

@@ -1,7 +1,7 @@
 {
   "name": "local-transcription",
   "private": true,
-  "version": "1.4.0",
+  "version": "2.0.15",
   "type": "module",
   "scripts": {
     "dev": "vite dev",
@@ -12,16 +12,19 @@
   "devDependencies": {
     "@sveltejs/vite-plugin-svelte": "^5.0.0",
     "@tauri-apps/cli": "^2.0.0",
+    "@testing-library/svelte": "^5.3.1",
     "@tsconfig/svelte": "^5.0.0",
+    "jsdom": "^29.0.2",
     "svelte": "^5.0.0",
     "svelte-check": "^4.0.0",
     "typescript": "~5.6.0",
-    "vite": "^6.0.0"
+    "vite": "^6.0.0",
+    "vitest": "^4.1.3"
   },
   "dependencies": {
     "@tauri-apps/api": "^2.0.0",
     "@tauri-apps/plugin-dialog": "^2.0.0",
-    "@tauri-apps/plugin-shell": "^2.0.0",
-    "@tauri-apps/plugin-process": "^2.0.0"
+    "@tauri-apps/plugin-process": "^2.0.0",
+    "@tauri-apps/plugin-shell": "^2.0.0"
   }
 }

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "local-transcription"
-version = "1.0.0"
+version = "1.0.11"
 description = "A standalone desktop application for real-time speech-to-text transcription using Whisper models"
 readme = "README.md"
 requires-python = ">=3.9"

server/nodejs/server.js

@@ -703,6 +703,36 @@ app.post('/api/send', async (req, res) => {
     }
 });
 
+// Create room explicitly (no transcription needed)
+app.post('/api/create-room', async (req, res) => {
+    try {
+        const { room, passphrase } = req.body;
+
+        if (!room || !passphrase) {
+            return res.status(400).json({ error: 'Missing room or passphrase' });
+        }
+
+        // Check if room already exists
+        const existing = await loadRoom(room);
+        if (existing) {
+            const valid = await verifyPassphrase(room, passphrase);
+            if (!valid) {
+                return res.status(401).json({ error: 'Room exists with different passphrase' });
+            }
+            return res.json({ status: 'ok', room, created: false, message: 'Room already exists' });
+        }
+
+        // Create the room (verifyPassphrase creates it if it doesn't exist)
+        await verifyPassphrase(room, passphrase);
+
+        console.log(`[Room] Created room "${room}"`);
+        res.json({ status: 'ok', room, created: true });
+    } catch (err) {
+        console.error('Error in /api/create-room:', err);
+        res.status(500).json({ error: err.message });
+    }
+});
+
 // List transcriptions
 app.get('/api/list', async (req, res) => {
     try {

src-tauri/Cargo.lock

@@ -47,6 +47,15 @@ version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 
+[[package]]
+name = "arbitrary"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3d036a3c4ab069c7b410a2ce876bd74808d2d0888a82667669f8e783a898bf1"
+dependencies = [
+ "derive_arbitrary",
+]
+
 [[package]]
 name = "atk"
 version = "0.18.2"
@@ -307,8 +316,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c673075a2e0e5f4a1dde27ce9dee1ea4558c7ffe648f576438a20ca1d2acc4b0"
 dependencies = [
  "iana-time-zone",
+ "js-sys",
  "num-traits",
  "serde",
+ "wasm-bindgen",
  "windows-link 0.2.1",
 ]
 
@@ -338,6 +349,16 @@ dependencies = [
  "version_check",
 ]
 
+[[package]]
+name = "core-foundation"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91e195e091a93c46f7102ec7818a2aa394e1e1771c3ab4825963fa03e45afb8f"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
 [[package]]
 name = "core-foundation"
 version = "0.10.1"
@@ -361,9 +382,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "064badf302c3194842cf2c5d61f56cc88e54a759313879cdf03abdd27d0c3b97"
 dependencies = [
  "bitflags 2.11.0",
- "core-foundation",
+ "core-foundation 0.10.1",
  "core-graphics-types",
- "foreign-types",
+ "foreign-types 0.5.0",
  "libc",
 ]
 
@@ -374,7 +395,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3d44a101f213f6c4cdc1853d4b78aef6db6bdfa3468798cc1d9912f4735013eb"
 dependencies = [
  "bitflags 2.11.0",
- "core-foundation",
+ "core-foundation 0.10.1",
  "libc",
 ]
 
@@ -515,6 +536,17 @@ dependencies = [
  "serde_core",
 ]
 
+[[package]]
+name = "derive_arbitrary"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e567bd82dcff979e4b03460c307b3cdc9e96fde3d73bed1496d2bc75d9dd62a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "derive_more"
 version = "0.99.20"
@@ -792,6 +824,15 @@ version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb"
 
+[[package]]
+name = "foreign-types"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6f339eb8adc052cd2ca78910fda869aefa38d22d5cb648e6485e4d3fc06f3b1"
+dependencies = [
+ "foreign-types-shared 0.1.1",
+]
+
 [[package]]
 name = "foreign-types"
 version = "0.5.0"
@@ -799,7 +840,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d737d9aa519fb7b749cbc3b962edcf310a8dd1f4b67c91c4f83975dbdd17d965"
 dependencies = [
  "foreign-types-macros",
- "foreign-types-shared",
+ "foreign-types-shared 0.3.1",
 ]
 
 [[package]]
@@ -813,6 +854,12 @@ dependencies = [
  "syn 2.0.117",
 ]
 
+[[package]]
+name = "foreign-types-shared"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "00b0228411908ca8685dba7fc2cdd70ec9990a6e753e89b6ac91a84c40fbaf4b"
+
 [[package]]
 name = "foreign-types-shared"
 version = "0.3.1"
@@ -1222,6 +1269,25 @@ dependencies = [
  "syn 2.0.117",
 ]
 
+[[package]]
+name = "h2"
+version = "0.4.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f44da3a8150a6703ed5d34e164b875fd14c2cdab9af1252a9a1020bde2bdc54"
+dependencies = [
+ "atomic-waker",
+ "bytes",
+ "fnv",
+ "futures-core",
+ "futures-sink",
+ "http",
+ "indexmap 2.13.1",
+ "slab",
+ "tokio",
+ "tokio-util",
+ "tracing",
+]
+
 [[package]]
 name = "hashbrown"
 version = "0.12.3"
@@ -1332,6 +1398,7 @@ dependencies = [
  "bytes",
  "futures-channel",
  "futures-core",
+ "h2",
  "http",
  "http-body",
  "httparse",
@@ -1342,6 +1409,38 @@ dependencies = [
  "want",
 ]
 
+[[package]]
+name = "hyper-rustls"
+version = "0.27.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3c93eb611681b207e1fe55d5a71ecf91572ec8a6705cdb6857f7d8d5242cf58"
+dependencies = [
+ "http",
+ "hyper",
+ "hyper-util",
+ "rustls",
+ "rustls-pki-types",
+ "tokio",
+ "tokio-rustls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-tls"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0"
+dependencies = [
+ "bytes",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "native-tls",
+ "tokio",
+ "tokio-native-tls",
+ "tower-service",
+]
+
 [[package]]
 name = "hyper-util"
 version = "0.1.20"
@@ -1360,9 +1459,11 @@ dependencies = [
  "percent-encoding",
  "pin-project-lite",
  "socket2",
+ "system-configuration",
  "tokio",
  "tower-service",
  "tracing",
+ "windows-registry",
 ]
 
 [[package]]
@@ -1766,6 +1867,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "linux-raw-sys"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
+
 [[package]]
 name = "litemap"
 version = "0.8.2"
@@ -1774,8 +1881,12 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
 [[package]]
 name = "local-transcription"
-version = "1.4.0"
+version = "2.0.12"
 dependencies = [
+ "bytes",
+ "chrono",
+ "futures-util",
+ "reqwest 0.12.28",
  "serde",
  "serde_json",
  "tauri",
@@ -1783,6 +1894,9 @@ dependencies = [
  "tauri-plugin-dialog",
  "tauri-plugin-process",
  "tauri-plugin-shell",
+ "tempfile",
+ "tokio",
+ "zip",
 ]
 
 [[package]]
@@ -1911,6 +2025,23 @@ dependencies = [
  "windows-sys 0.60.2",
 ]
 
+[[package]]
+name = "native-tls"
+version = "0.2.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "465500e14ea162429d264d44189adc38b199b62b1c21eea9f69e4b73cb03bbf2"
+dependencies = [
+ "libc",
+ "log",
+ "openssl",
+ "openssl-probe",
+ "openssl-sys",
+ "schannel",
+ "security-framework",
+ "security-framework-sys",
+ "tempfile",
+]
+
 [[package]]
 name = "ndk"
 version = "0.9.0"
@@ -2132,6 +2263,50 @@ dependencies = [
  "pathdiff",
 ]
 
+[[package]]
+name = "openssl"
+version = "0.10.76"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "951c002c75e16ea2c65b8c7e4d3d51d5530d8dfa7d060b4776828c88cfb18ecf"
+dependencies = [
+ "bitflags 2.11.0",
+ "cfg-if",
+ "foreign-types 0.3.2",
+ "libc",
+ "once_cell",
+ "openssl-macros",
+ "openssl-sys",
+]
+
+[[package]]
+name = "openssl-macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "openssl-probe"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
+
+[[package]]
+name = "openssl-sys"
+version = "0.9.112"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57d55af3b3e226502be1526dfdba67ab0e9c96fc293004e79576b2b9edb0dbdb"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+ "vcpkg",
+]
+
 [[package]]
 name = "option-ext"
 version = "0.2.0"
@@ -2727,6 +2902,49 @@ version = "0.8.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
 
+[[package]]
+name = "reqwest"
+version = "0.12.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
+dependencies = [
+ "base64 0.22.1",
+ "bytes",
+ "encoding_rs",
+ "futures-core",
+ "futures-util",
+ "h2",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-rustls",
+ "hyper-tls",
+ "hyper-util",
+ "js-sys",
+ "log",
+ "mime",
+ "native-tls",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tokio-native-tls",
+ "tokio-util",
+ "tower",
+ "tower-http",
+ "tower-service",
+ "url",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "wasm-streams 0.4.2",
+ "web-sys",
+]
+
 [[package]]
 name = "reqwest"
 version = "0.13.2"
@@ -2757,7 +2975,7 @@ dependencies = [
  "url",
  "wasm-bindgen",
  "wasm-bindgen-futures",
- "wasm-streams",
+ "wasm-streams 0.5.0",
  "web-sys",
 ]
 
@@ -2785,6 +3003,20 @@ dependencies = [
  "windows-sys 0.60.2",
 ]
 
+[[package]]
+name = "ring"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom 0.2.17",
+ "libc",
+ "untrusted",
+ "windows-sys 0.52.0",
+]
+
 [[package]]
 name = "rustc-hash"
 version = "2.1.2"
@@ -2800,12 +3032,64 @@ dependencies = [
  "semver",
 ]
 
+[[package]]
+name = "rustix"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
+dependencies = [
+ "bitflags 2.11.0",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "rustls"
+version = "0.23.37"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "758025cb5fccfd3bc2fd74708fd4682be41d99e5dff73c377c0646c6012c73a4"
+dependencies = [
+ "once_cell",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-pki-types"
+version = "1.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be040f8b0a225e40375822a563fa9524378b9d63112f53e19ffff34df5d33fdd"
+dependencies = [
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-webpki"
+version = "0.103.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
 [[package]]
 name = "rustversion"
 version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
 
+[[package]]
+name = "ryu"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f"
+
 [[package]]
 name = "same-file"
 version = "1.0.6"
@@ -2815,6 +3099,15 @@ dependencies = [
  "winapi-util",
 ]
 
+[[package]]
+name = "schannel"
+version = "0.1.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91c1b7e4904c873ef0710c1f407dde2e6287de2bebc1bbbf7d430bb7cbffd939"
+dependencies = [
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "schemars"
 version = "0.8.22"
@@ -2872,6 +3165,29 @@ version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
+[[package]]
+name = "security-framework"
+version = "3.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7f4bc775c73d9a02cde8bf7b2ec4c9d12743edf609006c7facc23998404cd1d"
+dependencies = [
+ "bitflags 2.11.0",
+ "core-foundation 0.10.1",
+ "core-foundation-sys",
+ "libc",
+ "security-framework-sys",
+]
+
+[[package]]
+name = "security-framework-sys"
+version = "2.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2691df843ecc5d231c0b14ece2acc3efb62c0a398c7e1d875f3983ce020e3"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
 [[package]]
 name = "selectors"
 version = "0.24.0"
@@ -3014,6 +3330,18 @@ dependencies = [
  "serde_core",
 ]
 
+[[package]]
+name = "serde_urlencoded"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd"
+dependencies = [
+ "form_urlencoded",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
 [[package]]
 name = "serde_with"
 version = "3.18.0"
@@ -3294,6 +3622,12 @@ version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
 
+[[package]]
+name = "subtle"
+version = "2.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
+
 [[package]]
 name = "swift-rs"
 version = "1.0.7"
@@ -3347,6 +3681,27 @@ dependencies = [
  "syn 2.0.117",
 ]
 
+[[package]]
+name = "system-configuration"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a13f3d0daba03132c0aa9767f98351b3488edc2c100cda2d2ec2b04f3d8d3c8b"
+dependencies = [
+ "bitflags 2.11.0",
+ "core-foundation 0.9.4",
+ "system-configuration-sys",
+]
+
+[[package]]
+name = "system-configuration-sys"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e1d1b10ced5ca923a1fcb8d03e96b8d3268065d724548c0211415ff6ac6bac4"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
 [[package]]
 name = "system-deps"
 version = "6.2.2"
@@ -3368,7 +3723,7 @@ checksum = "9103edf55f2da3c82aea4c7fab7c4241032bfeea0e71fa557d98e00e7ce7cc20"
 dependencies = [
  "bitflags 2.11.0",
  "block2",
- "core-foundation",
+ "core-foundation 0.10.1",
  "core-graphics",
  "crossbeam-channel",
  "dispatch2",
@@ -3445,7 +3800,7 @@ dependencies = [
  "percent-encoding",
  "plist",
  "raw-window-handle",
- "reqwest",
+ "reqwest 0.13.2",
  "serde",
  "serde_json",
  "serde_repr",
@@ -3719,6 +4074,19 @@ dependencies = [
  "toml 0.9.12+spec-1.1.0",
 ]
 
+[[package]]
+name = "tempfile"
+version = "3.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
+dependencies = [
+ "fastrand",
+ "getrandom 0.4.2",
+ "once_cell",
+ "rustix",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "tendril"
 version = "0.4.3"
@@ -3830,11 +4198,45 @@ dependencies = [
  "bytes",
  "libc",
  "mio",
+ "parking_lot",
  "pin-project-lite",
+ "signal-hook-registry",
  "socket2",
+ "tokio-macros",
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "tokio-macros"
+version = "2.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "tokio-native-tls"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbae76ab933c85776efabc971569dd6119c580d8f5d448769dec1764bf796ef2"
+dependencies = [
+ "native-tls",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-rustls"
+version = "0.26.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1729aa945f29d91ba541258c8df89027d5792d85a8841fb65e8bf0f4ede4ef61"
+dependencies = [
+ "rustls",
+ "tokio",
+]
+
 [[package]]
 name = "tokio-util"
 version = "0.7.18"
@@ -4116,6 +4518,12 @@ version = "0.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
 
+[[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+
 [[package]]
 name = "url"
 version = "2.5.8"
@@ -4165,6 +4573,12 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
+
 [[package]]
 name = "version-compare"
 version = "0.2.1"
@@ -4323,6 +4737,19 @@ dependencies = [
  "wasmparser",
 ]
 
+[[package]]
+name = "wasm-streams"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "15053d8d85c7eccdbefef60f06769760a563c7f0a9d6902a13d35c7800b0ad65"
+dependencies = [
+ "futures-util",
+ "js-sys",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
 [[package]]
 name = "wasm-streams"
 version = "0.5.0"
@@ -4599,6 +5026,17 @@ dependencies = [
  "windows-link 0.1.3",
 ]
 
+[[package]]
+name = "windows-registry"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02752bf7fbdcce7f2a27a742f798510f3e5ad88dbe84871e5168e2120c3d5720"
+dependencies = [
+ "windows-link 0.2.1",
+ "windows-result 0.4.1",
+ "windows-strings 0.5.1",
+]
+
 [[package]]
 name = "windows-result"
 version = "0.3.4"
@@ -4644,6 +5082,15 @@ dependencies = [
  "windows-targets 0.42.2",
 ]
 
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets 0.52.6",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.59.0"
@@ -5132,6 +5579,12 @@ dependencies = [
  "synstructure",
 ]
 
+[[package]]
+name = "zeroize"
+version = "1.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
+
 [[package]]
 name = "zerotrie"
 version = "0.2.4"
@@ -5165,8 +5618,37 @@ dependencies = [
  "syn 2.0.117",
 ]
 
+[[package]]
+name = "zip"
+version = "2.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fabe6324e908f85a1c52063ce7aa26b68dcb7eb6dbc83a2d148403c9bc3eba50"
+dependencies = [
+ "arbitrary",
+ "crc32fast",
+ "crossbeam-utils",
+ "displaydoc",
+ "flate2",
+ "indexmap 2.13.1",
+ "memchr",
+ "thiserror 2.0.18",
+ "zopfli",
+]
+
 [[package]]
 name = "zmij"
 version = "1.0.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"
+
+[[package]]
+name = "zopfli"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f05cd8797d63865425ff89b5c4a48804f35ba0ce8d125800027ad6017d2b5249"
+dependencies = [
+ "bumpalo",
+ "crc32fast",
+ "log",
+ "simd-adler32",
+]

src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "local-transcription"
-version = "1.4.0"
+version = "2.0.15"
 description = "Real-time speech-to-text transcription for streamers"
 authors = ["Local Transcription Contributors"]
 edition = "2021"
@@ -19,3 +19,12 @@ tauri-plugin-dialog = "2"
 tauri-plugin-process = "2"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+reqwest = { version = "0.12", features = ["json", "stream"] }
+futures-util = "0.3"
+zip = { version = "2", default-features = false, features = ["deflate"] }
+bytes = "1"
+tokio = { version = "1", features = ["full"] }
+chrono = "0.4"
+
+[dev-dependencies]
+tempfile = "3"

src-tauri/capabilities/default.json

@@ -0,0 +1,14 @@
+{
+  "identifier": "default",
+  "description": "Default permissions for the main window",
+  "windows": ["main"],
+  "permissions": [
+    "core:default",
+    "core:event:default",
+    "core:event:allow-listen",
+    "core:event:allow-emit",
+    "shell:default",
+    "dialog:default",
+    "process:default"
+  ]
+}

src-tauri/gen/schemas/capabilities.json

@@ -1 +1 @@
-{}
+{"default":{"identifier":"default","description":"Default permissions for the main window","local":true,"windows":["main"],"permissions":["core:default","core:event:default","core:event:allow-listen","core:event:allow-emit","shell:default","dialog:default","process:default"]}}

src-tauri/src/lib.rs

@@ -1,9 +1,98 @@
+mod sidecar;
+
+use std::sync::Mutex;
+use tauri::Manager;
+
+/// App log directory, set during setup.
+static LOG_DIR: std::sync::OnceLock<std::path::PathBuf> = std::sync::OnceLock::new();
+
+/// Write a log message to the app's log file (for debugging).
+#[tauri::command]
+fn write_log(message: String) {
+    if let Some(log_dir) = LOG_DIR.get() {
+        let log_path = log_dir.join("frontend.log");
+        use std::io::Write;
+        if let Ok(mut f) = std::fs::OpenOptions::new()
+            .create(true)
+            .append(true)
+            .open(&log_path)
+        {
+            let _ = writeln!(f, "[{}] {}", chrono::Local::now().format("%H:%M:%S%.3f"), message);
+        }
+    }
+    eprintln!("[frontend] {}", message);
+}
+
 #[cfg_attr(mobile, tauri::mobile_entry_point)]
 pub fn run() {
     tauri::Builder::default()
         .plugin(tauri_plugin_shell::init())
         .plugin(tauri_plugin_dialog::init())
         .plugin(tauri_plugin_process::init())
-        .run(tauri::generate_context!())
-        .expect("error while running tauri application");
+        .manage(sidecar::ManagedSidecar(std::sync::Arc::new(Mutex::new(
+            sidecar::SidecarManager::new(),
+        ))))
+        .setup(|app| {
+            let resource_dir = app
+                .path()
+                .resource_dir()
+                .expect("failed to resolve resource dir");
+            let data_dir = app
+                .path()
+                .app_data_dir()
+                .expect("failed to resolve app data dir");
+
+            std::fs::create_dir_all(&data_dir).expect("failed to create app data dir");
+
+            // Set up logging
+            LOG_DIR.set(data_dir.clone()).ok();
+            let log_path = data_dir.join("app.log");
+            if let Ok(mut f) = std::fs::OpenOptions::new()
+                .create(true)
+                .append(true)
+                .open(&log_path)
+            {
+                use std::io::Write;
+                let _ = writeln!(f, "\n=== App started at {} ===", chrono::Local::now());
+                let _ = writeln!(f, "Resource dir: {}", resource_dir.display());
+                let _ = writeln!(f, "Data dir: {}", data_dir.display());
+            }
+
+            sidecar::init_dirs(resource_dir, data_dir);
+            Ok(())
+        })
+        .invoke_handler(tauri::generate_handler![
+            sidecar::check_sidecar,
+            sidecar::download_sidecar,
+            sidecar::check_sidecar_update,
+            sidecar::get_sidecar_port,
+            sidecar::start_sidecar,
+            sidecar::stop_sidecar,
+            sidecar::reset_sidecar,
+            write_log,
+        ])
+        .build(tauri::generate_context!())
+        .expect("error while building tauri application")
+        .run(|app, event| {
+            match event {
+                tauri::RunEvent::Exit => {
+                    if let Some(state) = app.try_state::<sidecar::ManagedSidecar>() {
+                        if let Ok(mut mgr) = state.0.lock() {
+                            eprintln!("[app] Stopping sidecar on exit...");
+                            mgr.stop();
+                        }
+                    }
+                }
+                tauri::RunEvent::ExitRequested { .. } => {
+                    // Also stop sidecar on exit request (Cmd+Q on macOS)
+                    if let Some(state) = app.try_state::<sidecar::ManagedSidecar>() {
+                        if let Ok(mut mgr) = state.0.lock() {
+                            eprintln!("[app] Stopping sidecar on exit request...");
+                            mgr.stop();
+                        }
+                    }
+                }
+                _ => {}
+            }
+        });
 }

src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "productName": "Local Transcription",
-  "version": "1.4.0",
-  "identifier": "com.localtranscription.app",
+  "version": "2.0.15",
+  "identifier": "net.anhonesthost.local-transcription",
   "build": {
     "frontendDist": "../dist",
     "devUrl": "http://localhost:1420",
@@ -30,6 +30,7 @@
       "icons/32x32.png",
       "icons/128x128.png",
       "icons/128x128@2x.png",
+      "icons/icon.icns",
       "icons/icon.ico",
       "icons/icon.png"
     ]

src/App.svelte

@@ -5,13 +5,22 @@
   import Controls from "$lib/components/Controls.svelte";
   import TranscriptionDisplay from "$lib/components/TranscriptionDisplay.svelte";
   import Settings from "$lib/components/Settings.svelte";
+  import SidecarSetup from "$lib/components/SidecarSetup.svelte";
   import { backendStore } from "$lib/stores/backend";
   import { configStore } from "$lib/stores/config";
 
+  type SidecarState = "checking" | "needs_setup" | "update_available" | "starting" | "connected";
+
   let showSettings = $state(false);
+  let sidecarState = $state<SidecarState>("checking");
+  let debugLog = $state("");
+  let availableUpdate = $state("");
+  let appVersion = $state("");
 
   let obsDisplayUrl = $derived(backendStore.obsUrl);
   let syncDisplayUrl = $derived(backendStore.syncUrl);
+  let isConnected = $derived(backendStore.connectionState === "connected");
+  let connectionState = $derived(backendStore.connectionState);
 
   function openSettings() {
     showSettings = true;
@@ -21,9 +30,94 @@
     showSettings = false;
   }
 
-  onMount(() => {
+  let tauriInvoke: ((cmd: string, args?: Record<string, unknown>) => Promise<unknown>) | null = null;
+
+  function log(msg: string) {
+    console.log(`[App] ${msg}`);
+    debugLog = msg;
+    // Also write to file via Tauri if available
+    tauriInvoke?.("write_log", { message: msg });
+  }
+
+  async function checkAndLaunchSidecar() {
+    try {
+      log("Importing Tauri API...");
+      const { invoke } = await import("@tauri-apps/api/core");
+      tauriInvoke = invoke;
+
+      log("Checking if sidecar is installed...");
+      sidecarState = "checking";
+      const installed = await invoke<boolean>("check_sidecar");
+      log(`Sidecar installed: ${installed}`);
+
+      if (!installed) {
+        sidecarState = "needs_setup";
+        return;
+      }
+
+      // Check for sidecar updates before launching
+      try {
+        log("Checking for sidecar updates...");
+        const update = await invoke<string | null>("check_sidecar_update");
+        if (update) {
+          log(`Sidecar update available: ${update}`);
+          availableUpdate = update;
+          sidecarState = "update_available";
+          return;
+        }
+      } catch (err) {
+        log(`Update check failed (non-fatal): ${err}`);
+      }
+
+      await launchSidecar();
+    } catch (err) {
+      // Not running in Tauri (browser dev mode) - skip sidecar check
+      // and connect directly to localhost:8081
+      log(`Tauri not available (${err}), using dev mode`);
+      sidecarState = "starting";
+      backendStore.setPort(8081);
       backendStore.connect();
-    configStore.loadConfig();
+      configStore.fetchConfig();
+    }
+  }
+
+  async function launchSidecar() {
+    try {
+      const { invoke } = await import("@tauri-apps/api/core");
+
+      log("Starting sidecar...");
+      sidecarState = "starting";
+      await invoke("start_sidecar");
+
+      log("Getting sidecar port...");
+      const port = await invoke<number>("get_sidecar_port");
+      log(`Sidecar ready on port ${port}`);
+      backendStore.setPort(port);
+      backendStore.connect();
+      configStore.fetchConfig();
+    } catch (err) {
+      // If sidecar launch fails, still try connecting to default port
+      log(`Sidecar launch failed: ${err}, trying default port`);
+      sidecarState = "starting";
+      backendStore.connect();
+      configStore.fetchConfig();
+    }
+  }
+
+  async function onSidecarReady() {
+    await launchSidecar();
+  }
+
+  onMount(() => {
+    // Get app version from Tauri
+    import("@tauri-apps/api/app").then(({ getVersion }) =>
+      getVersion().then((v) => { appVersion = v; })
+    ).catch(() => {
+      // Browser dev mode -- read from package.json or use fallback
+      appVersion = "dev";
+    });
+
+    checkAndLaunchSidecar();
 
     return () => {
       backendStore.disconnect();
@@ -31,6 +125,72 @@
   });
 </script>
 
+{#if sidecarState === "checking"}
+  <div class="connecting-overlay" style="background:#1e1e1e;color:#e0e0e0;display:flex;align-items:center;justify-content:center;height:100%;width:100%;">
+    <div class="connecting-content" style="text-align:center;">
+      <div class="connecting-icon">
+        <div class="spinner"></div>
+      </div>
+      <h2 style="font-size:20px;margin:16px 0 8px;">Local Transcription</h2>
+      <p style="color:#a0a0a0;font-size:14px;">Checking setup...</p>
+      {#if debugLog}
+        <p style="color:#707070;font-size:11px;margin-top:12px;">{debugLog}</p>
+      {/if}
+    </div>
+  </div>
+
+{:else if sidecarState === "needs_setup"}
+  <SidecarSetup onComplete={onSidecarReady} />
+
+{:else if sidecarState === "update_available"}
+  <div class="connecting-overlay" style="background:#1e1e1e;color:#e0e0e0;display:flex;align-items:center;justify-content:center;height:100%;width:100%;">
+    <div class="connecting-content" style="text-align:center;max-width:400px;">
+      <h2 style="font-size:20px;margin:0 0 12px;">Sidecar Update Available</h2>
+      <p style="color:#a0a0a0;font-size:14px;margin:0 0 20px;">
+        A new version of the transcription engine is available ({availableUpdate}).
+      </p>
+      <div style="display:flex;gap:10px;justify-content:center;">
+        <button
+          style="padding:8px 20px;border:1px solid #555;border-radius:6px;background:transparent;color:#e0e0e0;cursor:pointer;"
+          onclick={() => launchSidecar()}
+        >Skip</button>
+        <button
+          style="padding:8px 20px;border:none;border-radius:6px;background:#4CAF50;color:white;cursor:pointer;font-weight:500;"
+          onclick={() => { sidecarState = "needs_setup"; }}
+        >Update Now</button>
+      </div>
+    </div>
+  </div>
+
+{:else if !isConnected}
+  <div class="connecting-overlay" style="background:#1e1e1e;color:#e0e0e0;display:flex;align-items:center;justify-content:center;height:100%;width:100%;">
+    <div class="connecting-content" style="text-align:center;">
+      <div class="connecting-icon">
+        {#if connectionState === "error"}
+          <svg width="48" height="48" viewBox="0 0 24 24" fill="none" stroke="#e74c3c" stroke-width="2">
+            <circle cx="12" cy="12" r="10"/>
+            <line x1="15" y1="9" x2="9" y2="15"/>
+            <line x1="9" y1="9" x2="15" y2="15"/>
+          </svg>
+        {:else}
+          <div class="spinner"></div>
+        {/if}
+      </div>
+      <h2 style="font-size:20px;margin:16px 0 8px;">Local Transcription</h2>
+      {#if connectionState === "error"}
+        <p style="color:#a0a0a0;">Cannot connect to backend</p>
+        <p class="hint">Make sure the Python backend is running:<br>
+          <code>uv run python -m backend.main_headless</code></p>
+      {:else}
+        <p style="color:#a0a0a0;">Connecting to backend...</p>
+      {/if}
+      {#if debugLog}
+        <p style="color:#707070;font-size:11px;margin-top:12px;">{debugLog}</p>
+      {/if}
+    </div>
+  </div>
+
+{:else}
   <div class="app-shell">
     <Header onSettingsClick={openSettings} />
     <StatusBar />
@@ -50,14 +210,76 @@
     <TranscriptionDisplay />
     <Controls />
 
-  <div class="version-label">v{backendStore.version}</div>
+    <div class="version-label">v{appVersion || backendStore.version}</div>
   </div>
 
   {#if showSettings}
     <Settings onClose={closeSettings} />
   {/if}
+{/if}
 
 <style>
+  .connecting-overlay {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    height: 100%;
+    width: 100%;
+    background-color: var(--bg-primary);
+  }
+
+  .connecting-content {
+    text-align: center;
+    color: var(--text-primary);
+  }
+
+  .connecting-content h2 {
+    margin: 16px 0 8px;
+    font-size: 20px;
+    font-weight: 600;
+  }
+
+  .connecting-content p {
+    margin: 4px 0;
+    color: var(--text-secondary);
+    font-size: 14px;
+  }
+
+  .connecting-content .hint {
+    margin-top: 16px;
+    font-size: 12px;
+    color: var(--text-muted);
+  }
+
+  .connecting-content code {
+    display: inline-block;
+    margin-top: 4px;
+    padding: 4px 8px;
+    background: var(--bg-tertiary);
+    border-radius: 4px;
+    font-size: 12px;
+    color: var(--text-primary);
+  }
+
+  .connecting-icon {
+    display: flex;
+    justify-content: center;
+    margin-bottom: 8px;
+  }
+
+  .spinner {
+    width: 40px;
+    height: 40px;
+    border: 3px solid var(--border-color);
+    border-top-color: var(--accent-color, #4CAF50);
+    border-radius: 50%;
+    animation: spin 0.8s linear infinite;
+  }
+
+  @keyframes spin {
+    to { transform: rotate(360deg); }
+  }
+
   .app-shell {
     display: flex;
     flex-direction: column;

src/lib/components/Controls.svelte

@@ -0,0 +1,172 @@
+<script lang="ts">
+  import { backendStore } from "$lib/stores/backend";
+  import { configStore } from "$lib/stores/config";
+  import { transcriptionStore } from "$lib/stores/transcriptions";
+
+  let isTranscribing = $derived(backendStore.appState === "transcribing");
+  let isReady = $derived(
+    backendStore.appState === "ready" || backendStore.appState === "transcribing"
+  );
+  let isLoading = $state(false);
+
+  let remoteMode = $derived(configStore.config.remote.mode);
+  let byokApiKey = $derived(configStore.config.remote.byok_api_key);
+  let authToken = $derived(configStore.config.remote.auth_token);
+
+  let cloudConfigured = $derived(
+    remoteMode === "local" ||
+    (remoteMode === "byok" && byokApiKey.trim() !== "") ||
+    (remoteMode === "managed" && authToken.trim() !== "")
+  );
+
+  let errorMessage = $state("");
+
+  async function toggleTranscription() {
+    if (isLoading) return;
+    isLoading = true;
+    errorMessage = "";
+    try {
+      if (isTranscribing) {
+        await backendStore.apiPost("/api/stop");
+      } else {
+        await backendStore.apiPost("/api/start");
+      }
+    } catch (err: unknown) {
+      const msg = err instanceof Error ? err.message : String(err);
+      // Ignore "Already transcribing/not transcribing" -- just sync the state
+      if (!msg.includes("400")) {
+        console.error("Failed to toggle transcription:", msg);
+        errorMessage = msg;
+      }
+    } finally {
+      // Always poll status to sync UI with actual backend state,
+      // even if the API call failed (e.g. "Already transcribing")
+      await backendStore.pollStatus();
+      isLoading = false;
+    }
+  }
+
+  async function clearTranscriptions() {
+    try {
+      await backendStore.apiPost("/api/clear");
+      transcriptionStore.clearAll();
+    } catch (err) {
+      console.error("Failed to clear:", err);
+    }
+  }
+
+  async function saveTranscriptions() {
+    try {
+      // Get transcription text from backend or local store
+      let text: string;
+      try {
+        const data = await backendStore.apiGet<{ text: string }>("/api/transcriptions");
+        text = data.text || transcriptionStore.getPlainText();
+      } catch {
+        text = transcriptionStore.getPlainText();
+      }
+
+      if (!text.trim()) {
+        console.warn("No transcriptions to save");
+        return;
+      }
+
+      // Try Tauri dialog for native save, fall back to browser download
+      try {
+        const { save } = await import("@tauri-apps/plugin-dialog");
+        const filePath = await save({
+          defaultPath: "transcription.txt",
+          filters: [
+            { name: "Text Files", extensions: ["txt"] },
+            { name: "All Files", extensions: ["*"] },
+          ],
+        });
+        if (filePath) {
+          // Write via backend API
+          await backendStore.apiPost("/api/save-file", { path: filePath, text });
+        }
+      } catch {
+        // Fallback: browser-style download
+        const blob = new Blob([text], { type: "text/plain" });
+        const url = URL.createObjectURL(blob);
+        const a = document.createElement("a");
+        a.href = url;
+        a.download = "transcription.txt";
+        a.click();
+        URL.revokeObjectURL(url);
+      }
+    } catch (err) {
+      console.error("Failed to save:", err);
+    }
+  }
+</script>
+
+<div class="controls">
+  <button
+    class={isTranscribing ? "danger" : "primary"}
+    onclick={toggleTranscription}
+    disabled={!isReady || isLoading || !cloudConfigured}
+  >
+    {#if isLoading}
+      ...
+    {:else if isTranscribing}
+      Stop Transcription
+    {:else}
+      Start Transcription
+    {/if}
+  </button>
+
+  <button onclick={clearTranscriptions} disabled={!backendStore.connected}>
+    Clear
+  </button>
+
+  <button onclick={saveTranscriptions} disabled={!backendStore.connected}>
+    Save
+  </button>
+
+  {#if errorMessage}
+    <span class="error-msg">{errorMessage}</span>
+  {/if}
+
+  {#if !cloudConfigured && isReady}
+    <div class="cloud-warning">
+      {#if remoteMode === "byok"}
+        <span>API key required. Get one at
+          <a href="https://console.deepgram.com" target="_blank" rel="noopener">console.deepgram.com</a>,
+          then enter it in Settings.</span>
+      {:else if remoteMode === "managed"}
+        <span>Login required. Open Settings to log in.</span>
+      {/if}
+    </div>
+  {/if}
+</div>
+
+<style>
+  .error-msg {
+    color: #f44336;
+    font-size: 12px;
+    margin-left: 8px;
+  }
+
+  .cloud-warning {
+    font-size: 12px;
+    color: #ff9800;
+    margin-left: 8px;
+    flex: 1;
+  }
+
+  .cloud-warning a {
+    color: #4fc3f7;
+    text-decoration: underline;
+  }
+
+  .controls {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    padding: 10px 20px;
+    background-color: var(--bg-secondary);
+    border-top: 1px solid var(--border-color);
+    flex-shrink: 0;
+  }
+</style>

src/lib/components/Header.svelte

@@ -0,0 +1,82 @@
+<script lang="ts">
+  interface Props {
+    onSettingsClick: () => void;
+  }
+
+  let { onSettingsClick }: Props = $props();
+</script>
+
+<header class="app-header">
+  <h1 class="app-title">Local Transcription</h1>
+  <button class="settings-btn" onclick={onSettingsClick} title="Settings">
+    <svg
+      width="20"
+      height="20"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      stroke-width="2"
+      stroke-linecap="round"
+      stroke-linejoin="round"
+    >
+      <circle cx="12" cy="12" r="3"></circle>
+      <path
+        d="M19.4 15a1.65 1.65 0 0 0 .33 1.82l.06.06a2 2 0 0 1
+        0 2.83 2 2 0 0 1-2.83 0l-.06-.06a1.65 1.65 0 0
+        0-1.82-.33 1.65 1.65 0 0 0-1 1.51V21a2 2 0 0 1-2
+        2 2 2 0 0 1-2-2v-.09A1.65 1.65 0 0 0 9 19.4a1.65
+        1.65 0 0 0-1.82.33l-.06.06a2 2 0 0 1-2.83 0 2 2
+        0 0 1 0-2.83l.06-.06A1.65 1.65 0 0 0 4.68
+        15a1.65 1.65 0 0 0-1.51-1H3a2 2 0 0 1-2-2 2 2 0
+        0 1 2-2h.09A1.65 1.65 0 0 0 4.6 9a1.65 1.65 0 0
+        0-.33-1.82l-.06-.06a2 2 0 0 1 0-2.83 2 2 0 0 1
+        2.83 0l.06.06A1.65 1.65 0 0 0 9 4.68a1.65 1.65 0
+        0 0 1-1.51V3a2 2 0 0 1 2-2 2 2 0 0 1 2
+        2v.09a1.65 1.65 0 0 0 1 1.51 1.65 1.65 0 0 0
+        1.82-.33l.06-.06a2 2 0 0 1 2.83 0 2 2 0 0 1 0
+        2.83l-.06.06a1.65 1.65 0 0 0-.33 1.82V9a1.65 1.65
+        0 0 0 1.51 1H21a2 2 0 0 1 2 2 2 2 0 0
+        1-2 2h-.09a1.65 1.65 0 0 0-1.51 1z"
+      ></path>
+    </svg>
+  </button>
+</header>
+
+<style>
+  .app-header {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 12px 20px;
+    background-color: var(--bg-secondary);
+    border-bottom: 1px solid var(--border-color);
+    flex-shrink: 0;
+  }
+
+  .app-title {
+    font-size: 24px;
+    font-weight: 700;
+    color: var(--text-primary);
+    letter-spacing: -0.5px;
+  }
+
+  .settings-btn {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    width: 36px;
+    height: 36px;
+    padding: 0;
+    border: 1px solid var(--border-color);
+    border-radius: 8px;
+    background-color: transparent;
+    color: var(--text-secondary);
+    cursor: pointer;
+    transition: color 0.15s ease, background-color 0.15s ease;
+  }
+
+  .settings-btn:hover {
+    color: var(--text-primary);
+    background-color: var(--bg-tertiary);
+  }
+</style>

src/lib/components/SidecarSetup.svelte

@@ -0,0 +1,420 @@
+<script lang="ts">
+  import { invoke } from "@tauri-apps/api/core";
+  import { listen } from "@tauri-apps/api/event";
+  import { onMount } from "svelte";
+
+  interface Props {
+    onComplete: () => void;
+  }
+
+  let { onComplete }: Props = $props();
+
+  type SetupState = "choose" | "downloading" | "error" | "success";
+
+  let setupState = $state<SetupState>("choose");
+  let variant = $state<"cpu" | "cuda">("cpu");
+  let progress = $state(0);
+  let progressMessage = $state("");
+  let errorMessage = $state("");
+
+  let unlisten: (() => void) | null = null;
+
+  onMount(() => {
+    return () => {
+      if (unlisten) {
+        unlisten();
+        unlisten = null;
+      }
+    };
+  });
+
+  async function startDownload() {
+    setupState = "downloading";
+    progress = 0;
+    progressMessage = "Starting download...";
+    errorMessage = "";
+
+    try {
+      // Listen for progress events from the Tauri backend
+      unlisten = await listen<{ downloaded: number; total: number; phase: string; message: string }>(
+        "sidecar-download-progress",
+        (event) => {
+          const { downloaded, total, message } = event.payload;
+          progress = total > 0 ? (downloaded / total) * 100 : 0;
+          progressMessage = message;
+        }
+      );
+
+      await invoke("download_sidecar", { variant });
+
+      // Download complete
+      setupState = "success";
+      if (unlisten) {
+        unlisten();
+        unlisten = null;
+      }
+
+      // Brief pause to show success, then proceed
+      setTimeout(() => {
+        onComplete();
+      }, 1500);
+    } catch (err) {
+      setupState = "error";
+      errorMessage = err instanceof Error ? err.message : String(err);
+      if (unlisten) {
+        unlisten();
+        unlisten = null;
+      }
+    }
+  }
+
+  function retry() {
+    setupState = "choose";
+    progress = 0;
+    progressMessage = "";
+    errorMessage = "";
+  }
+</script>
+
+<div class="setup-overlay">
+  <div class="setup-card">
+    <div class="setup-header">
+      <h1 class="app-title">Local Transcription</h1>
+      <h2 class="setup-heading">First-Time Setup</h2>
+    </div>
+
+    {#if setupState === "choose"}
+      <p class="setup-description">
+        Choose a transcription engine. You can change this later in Settings.
+      </p>
+
+      <div class="variant-options">
+        <label class="variant-option" class:selected={variant === "cloud"}>
+          <input
+            type="radio"
+            name="variant"
+            value="cloud"
+            bind:group={variant}
+          />
+          <div class="variant-info">
+            <span class="variant-name">Cloud (Deepgram)</span>
+            <span class="variant-desc">~50 MB download</span>
+            <span class="variant-detail">
+              Fast, accurate streaming transcription via Deepgram's servers.
+              Requires internet and a Deepgram API key.
+              Best for most users — low resource usage, works on any hardware.
+            </span>
+            <span class="variant-tag recommended">Recommended</span>
+          </div>
+        </label>
+
+        <label class="variant-option" class:selected={variant === "cpu"}>
+          <input
+            type="radio"
+            name="variant"
+            value="cpu"
+            bind:group={variant}
+          />
+          <div class="variant-info">
+            <span class="variant-name">Local - CPU</span>
+            <span class="variant-desc">~500 MB download</span>
+            <span class="variant-detail">
+              Runs Whisper AI models locally on your CPU. No internet needed
+              after download. Good for privacy or offline use, but slower and
+              uses more system resources than cloud.
+            </span>
+          </div>
+        </label>
+
+      </div>
+
+      <button class="download-btn" onclick={startDownload}>
+        Download & Install
+      </button>
+
+    {:else if setupState === "downloading"}
+      <div class="progress-section">
+        <p class="progress-message">{progressMessage}</p>
+        <div class="progress-bar-track">
+          <div
+            class="progress-bar-fill"
+            style="width: {progress}%"
+          ></div>
+        </div>
+        <p class="progress-percent">{Math.round(progress)}%</p>
+      </div>
+
+    {:else if setupState === "error"}
+      <div class="error-section">
+        <div class="error-icon">
+          <svg width="48" height="48" viewBox="0 0 24 24" fill="none" stroke="#f44336" stroke-width="2">
+            <circle cx="12" cy="12" r="10"/>
+            <line x1="15" y1="9" x2="9" y2="15"/>
+            <line x1="9" y1="9" x2="15" y2="15"/>
+          </svg>
+        </div>
+        <p class="error-title">Download Failed</p>
+        <p class="error-message">{errorMessage}</p>
+        <button class="retry-btn" onclick={retry}>
+          Try Again
+        </button>
+      </div>
+
+    {:else if setupState === "success"}
+      <div class="success-section">
+        <div class="success-icon">
+          <svg width="48" height="48" viewBox="0 0 24 24" fill="none" stroke="#4CAF50" stroke-width="2">
+            <circle cx="12" cy="12" r="10"/>
+            <polyline points="16 9 10.5 15 8 12.5"/>
+          </svg>
+        </div>
+        <p class="success-title">Setup Complete</p>
+        <p class="success-message">The transcription engine is ready to go.</p>
+      </div>
+    {/if}
+  </div>
+</div>
+
+<style>
+  .setup-overlay {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    height: 100%;
+    width: 100%;
+    background-color: #1e1e1e;
+  }
+
+  .setup-card {
+    background-color: #2a2a2a;
+    border-radius: 12px;
+    padding: 40px;
+    max-width: 480px;
+    width: 100%;
+    margin: 20px;
+    box-shadow: 0 8px 32px rgba(0, 0, 0, 0.4);
+  }
+
+  .setup-header {
+    text-align: center;
+    margin-bottom: 24px;
+  }
+
+  .app-title {
+    font-size: 24px;
+    font-weight: 700;
+    color: #e0e0e0;
+    margin-bottom: 4px;
+  }
+
+  .setup-heading {
+    font-size: 16px;
+    font-weight: 500;
+    color: #a0a0a0;
+  }
+
+  .setup-description {
+    font-size: 14px;
+    color: #a0a0a0;
+    line-height: 1.6;
+    text-align: center;
+    margin-bottom: 24px;
+  }
+
+  .variant-options {
+    display: flex;
+    flex-direction: column;
+    gap: 12px;
+    margin-bottom: 24px;
+  }
+
+  .variant-option {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+    padding: 14px 16px;
+    border: 2px solid #444;
+    border-radius: 8px;
+    cursor: pointer;
+    transition: border-color 0.15s ease, background-color 0.15s ease;
+  }
+
+  .variant-option:hover {
+    background-color: #333;
+    border-color: #555;
+  }
+
+  .variant-option.selected {
+    border-color: #4CAF50;
+    background-color: rgba(76, 175, 80, 0.08);
+  }
+
+  .variant-option input[type="radio"] {
+    width: 18px;
+    height: 18px;
+    flex-shrink: 0;
+  }
+
+  .variant-info {
+    display: flex;
+    flex-direction: column;
+    gap: 2px;
+  }
+
+  .variant-name {
+    font-size: 14px;
+    font-weight: 600;
+    color: #e0e0e0;
+  }
+
+  .variant-desc {
+    font-size: 12px;
+    color: #888;
+  }
+
+  .variant-detail {
+    font-size: 11px;
+    color: #666;
+    line-height: 1.4;
+    margin-top: 2px;
+  }
+
+  .variant-tag {
+    display: inline-block;
+    font-size: 10px;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+    padding: 2px 6px;
+    border-radius: 3px;
+    margin-top: 4px;
+    width: fit-content;
+  }
+
+  .variant-tag.recommended {
+    background: rgba(76, 175, 80, 0.15);
+    color: #4CAF50;
+  }
+
+  .download-btn {
+    display: block;
+    width: 100%;
+    padding: 12px 24px;
+    font-size: 15px;
+    font-weight: 600;
+    color: white;
+    background-color: #4CAF50;
+    border: none;
+    border-radius: 8px;
+    cursor: pointer;
+    transition: background-color 0.15s ease;
+  }
+
+  .download-btn:hover {
+    background-color: #45a049;
+  }
+
+  .download-btn:active {
+    transform: scale(0.98);
+  }
+
+  /* Progress state */
+  .progress-section {
+    text-align: center;
+    padding: 20px 0;
+  }
+
+  .progress-message {
+    font-size: 14px;
+    color: #a0a0a0;
+    margin-bottom: 16px;
+  }
+
+  .progress-bar-track {
+    width: 100%;
+    height: 8px;
+    background-color: #3a3a3a;
+    border-radius: 4px;
+    overflow: hidden;
+    margin-bottom: 8px;
+  }
+
+  .progress-bar-fill {
+    height: 100%;
+    background-color: #4CAF50;
+    border-radius: 4px;
+    transition: width 0.3s ease;
+  }
+
+  .progress-percent {
+    font-size: 13px;
+    color: #707070;
+  }
+
+  /* Error state */
+  .error-section {
+    text-align: center;
+    padding: 10px 0;
+  }
+
+  .error-icon {
+    display: flex;
+    justify-content: center;
+    margin-bottom: 12px;
+  }
+
+  .error-title {
+    font-size: 18px;
+    font-weight: 600;
+    color: #f44336;
+    margin-bottom: 8px;
+  }
+
+  .error-message {
+    font-size: 13px;
+    color: #a0a0a0;
+    margin-bottom: 20px;
+    word-break: break-word;
+  }
+
+  .retry-btn {
+    display: inline-block;
+    padding: 10px 28px;
+    font-size: 14px;
+    font-weight: 600;
+    color: white;
+    background-color: #4CAF50;
+    border: none;
+    border-radius: 8px;
+    cursor: pointer;
+    transition: background-color 0.15s ease;
+  }
+
+  .retry-btn:hover {
+    background-color: #45a049;
+  }
+
+  /* Success state */
+  .success-section {
+    text-align: center;
+    padding: 20px 0;
+  }
+
+  .success-icon {
+    display: flex;
+    justify-content: center;
+    margin-bottom: 12px;
+  }
+
+  .success-title {
+    font-size: 18px;
+    font-weight: 600;
+    color: #4CAF50;
+    margin-bottom: 4px;
+  }
+
+  .success-message {
+    font-size: 14px;
+    color: #a0a0a0;
+  }
+</style>

src/lib/components/StatusBar.svelte

@@ -0,0 +1,106 @@
+<script lang="ts">
+  import { backendStore } from "$lib/stores/backend";
+  import { configStore } from "$lib/stores/config";
+
+  let statusColor = $derived.by(() => {
+    switch (backendStore.appState) {
+      case "initializing":
+        return "#ff9800";
+      case "ready":
+        return "#4caf50";
+      case "transcribing":
+        return "#f44336";
+      case "error":
+        return "#f44336";
+      default:
+        return "#888";
+    }
+  });
+
+  let isPulsing = $derived(backendStore.appState === "transcribing");
+  let userName = $derived(configStore.config.user.name);
+</script>
+
+<div class="status-bar">
+  <div class="status-left">
+    <span
+      class="status-indicator"
+      class:pulsing={isPulsing}
+      style="background-color: {statusColor}"
+    ></span>
+    <span class="state-message">{backendStore.stateMessage}</span>
+  </div>
+  <div class="status-right">
+    {#if backendStore.deviceInfo}
+      <span class="device-info">{backendStore.deviceInfo}</span>
+      <span class="separator">|</span>
+    {/if}
+    <span class="user-name">{userName}</span>
+  </div>
+</div>
+
+<style>
+  .status-bar {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 6px 20px;
+    background-color: var(--bg-secondary);
+    border-bottom: 1px solid var(--border-color);
+    font-size: 12px;
+    flex-shrink: 0;
+  }
+
+  .status-left {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+  }
+
+  .status-right {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    color: var(--text-secondary);
+  }
+
+  .status-indicator {
+    width: 10px;
+    height: 10px;
+    border-radius: 50%;
+    flex-shrink: 0;
+  }
+
+  .status-indicator.pulsing {
+    animation: pulse 1.5s ease-in-out infinite;
+  }
+
+  @keyframes pulse {
+    0%,
+    100% {
+      opacity: 1;
+      box-shadow: 0 0 0 0 rgba(244, 67, 54, 0.4);
+    }
+    50% {
+      opacity: 0.7;
+      box-shadow: 0 0 0 6px rgba(244, 67, 54, 0);
+    }
+  }
+
+  .state-message {
+    color: var(--text-primary);
+  }
+
+  .device-info {
+    color: var(--text-secondary);
+  }
+
+  .separator {
+    color: var(--text-muted);
+  }
+
+  .user-name {
+    color: var(--accent-green);
+    font-weight: 500;
+  }
+</style>

src/lib/components/TranscriptionDisplay.svelte

@@ -0,0 +1,110 @@
+<script lang="ts">
+  import { transcriptionStore } from "$lib/stores/transcriptions";
+  import { configStore } from "$lib/stores/config";
+
+  let container: HTMLDivElement | undefined = $state();
+  let showTimestamps = $derived(configStore.config.display.show_timestamps);
+  let items = $derived(transcriptionStore.items);
+
+  $effect(() => {
+    // Trigger on items length change to auto-scroll
+    const _len = items.length;
+    if (container) {
+      requestAnimationFrame(() => {
+        if (container) {
+          container.scrollTop = container.scrollHeight;
+        }
+      });
+    }
+  });
+</script>
+
+<div class="transcription-display" bind:this={container}>
+  {#each items as item (item.id)}
+    <div class="transcription-item" class:preview={item.isPreview}>
+      {#if showTimestamps && item.timestamp}
+        <span class="timestamp">[{item.timestamp}]</span>
+      {/if}
+      {#if item.userName}
+        <span class="user-name">{item.userName}:</span>
+      {/if}
+      {#if item.isPreview}
+        <span class="preview-indicator">[...]</span>
+      {/if}
+      <span class="text">{item.text}</span>
+    </div>
+  {:else}
+    <div class="empty-state">
+      Transcriptions will appear here...
+    </div>
+  {/each}
+</div>
+
+<style>
+  .transcription-display {
+    flex: 1;
+    overflow-y: auto;
+    padding: 12px 20px;
+    display: flex;
+    flex-direction: column;
+    gap: 6px;
+  }
+
+  .transcription-item {
+    padding: 6px 10px;
+    border-radius: 4px;
+    background-color: rgba(255, 255, 255, 0.03);
+    animation: fadeIn 0.2s ease-out;
+    line-height: 1.6;
+    word-wrap: break-word;
+  }
+
+  .transcription-item.preview {
+    font-style: italic;
+    opacity: 0.7;
+  }
+
+  .timestamp {
+    color: #888;
+    font-size: 0.85em;
+    margin-right: 8px;
+    font-family: monospace;
+  }
+
+  .user-name {
+    color: #4caf50;
+    font-weight: 700;
+    margin-right: 6px;
+  }
+
+  .preview-indicator {
+    color: #888;
+    font-size: 0.85em;
+    margin-right: 4px;
+  }
+
+  .text {
+    color: #ffffff;
+  }
+
+  .empty-state {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    height: 100%;
+    color: var(--text-muted);
+    font-size: 15px;
+    font-style: italic;
+  }
+
+  @keyframes fadeIn {
+    from {
+      opacity: 0;
+      transform: translateY(4px);
+    }
+    to {
+      opacity: 1;
+      transform: translateY(0);
+    }
+  }
+</style>

src/lib/stores/backend.svelte.ts

@@ -0,0 +1,311 @@
+/**
+ * Backend store - manages WebSocket connection and REST API communication
+ * with the Python backend server running on localhost.
+ *
+ * The backend port defaults to 8081 but can be updated at runtime via
+ * `setPort()`. The WebSocket connects to /ws/control for real-time push
+ * of transcriptions, previews, and state changes.
+ */
+
+export type ConnectionState = "connecting" | "connected" | "disconnected" | "error";
+export type AppState = "initializing" | "ready" | "transcribing" | "reloading" | "error";
+
+interface BackendState {
+  port: number;
+  connectionState: ConnectionState;
+  appState: AppState;
+  stateMessage: string;
+  deviceInfo: string;
+  wsConnection: WebSocket | null;
+  version: string;
+  lastError: string;
+}
+
+let state = $state<BackendState>({
+  port: 8081,
+  connectionState: "disconnected",
+  appState: "initializing",
+  stateMessage: "Connecting to backend...",
+  deviceInfo: "",
+  wsConnection: null,
+  version: "1.4.0",
+  lastError: "",
+});
+
+let reconnectTimer: ReturnType<typeof setTimeout> | null = null;
+let reconnectAttempts = 0;
+const MAX_RECONNECT_DELAY_MS = 30_000;
+const BASE_RECONNECT_DELAY_MS = 1_000;
+
+// ── URL helpers ──────────────────────────────────────────────────────
+
+function apiUrl(path: string): string {
+  const normalised = path.startsWith("/") ? path : `/${path}`;
+  return `http://localhost:${state.port}${normalised}`;
+}
+
+async function apiFetch(path: string, options?: RequestInit): Promise<Response> {
+  const url = apiUrl(path);
+  const method = options?.method?.toUpperCase() ?? "GET";
+  const headers = new Headers(options?.headers);
+  if (method !== "GET" && !headers.has("Content-Type")) {
+    headers.set("Content-Type", "application/json");
+  }
+  return fetch(url, { ...options, headers });
+}
+
+// ── Status polling ──────────────────────────────────────────────────
+
+let statusPollTimer: ReturnType<typeof setTimeout> | null = null;
+
+async function pollStatus() {
+  try {
+    const resp = await fetch(apiUrl("/api/status"));
+    if (resp.ok) {
+      const data = await resp.json();
+      if (data.state) {
+        state.appState = data.state as AppState;
+      }
+      if (data.engine_device) {
+        state.deviceInfo = data.engine_device;
+      }
+      if (data.version) {
+        state.version = data.version;
+      }
+    }
+  } catch {
+    // API not ready yet, will retry
+  }
+
+  // Keep polling every 2s while still initializing
+  if (state.appState === "initializing" && state.connectionState === "connected") {
+    statusPollTimer = setTimeout(pollStatus, 2000);
+  }
+}
+
+// ── WebSocket management ─────────────────────────────────────────────
+
+function connectWebSocket() {
+  // Tear down any existing connection
+  disconnect();
+
+  state.connectionState = "connecting";
+  reconnectAttempts = 0;
+
+  _openSocket();
+}
+
+function _openSocket() {
+  const wsUrl = `ws://localhost:${state.port}/ws/control`;
+
+  try {
+    const ws = new WebSocket(wsUrl);
+
+    ws.onopen = () => {
+      state.connectionState = "connected";
+      state.lastError = "";
+      reconnectAttempts = 0;
+      if (reconnectTimer) {
+        clearTimeout(reconnectTimer);
+        reconnectTimer = null;
+      }
+      // Poll status to catch engine ready state that may have been
+      // missed (engine can finish before WebSocket connects)
+      pollStatus();
+    };
+
+    ws.onmessage = (event) => {
+      try {
+        const data = JSON.parse(event.data);
+        handleWebSocketMessage(data);
+      } catch {
+        // ignore parse errors
+      }
+    };
+
+    ws.onclose = () => {
+      state.wsConnection = null;
+      if (state.connectionState !== "disconnected") {
+        state.connectionState = "error";
+        state.stateMessage = "Disconnected from backend";
+        _scheduleReconnect();
+      }
+    };
+
+    ws.onerror = () => {
+      state.lastError = "WebSocket error";
+      // onclose fires after this, which handles reconnect
+    };
+
+    state.wsConnection = ws;
+  } catch {
+    state.connectionState = "error";
+    state.stateMessage = "Failed to connect";
+    _scheduleReconnect();
+  }
+}
+
+function _scheduleReconnect() {
+  if (reconnectTimer) return;
+
+  const delay = Math.min(
+    BASE_RECONNECT_DELAY_MS * Math.pow(2, reconnectAttempts),
+    MAX_RECONNECT_DELAY_MS,
+  );
+  reconnectAttempts++;
+
+  reconnectTimer = setTimeout(() => {
+    reconnectTimer = null;
+    if (state.connectionState !== "disconnected") {
+      state.connectionState = "connecting";
+      _openSocket();
+    }
+  }, delay);
+}
+
+function disconnect() {
+  if (statusPollTimer) {
+    clearTimeout(statusPollTimer);
+    statusPollTimer = null;
+  }
+  if (reconnectTimer) {
+    clearTimeout(reconnectTimer);
+    reconnectTimer = null;
+  }
+  state.connectionState = "disconnected";
+  if (state.wsConnection) {
+    const ws = state.wsConnection;
+    ws.onclose = null;
+    ws.onerror = null;
+    ws.close();
+    state.wsConnection = null;
+  }
+}
+
+// ── WebSocket message handling ───────────────────────────────────────
+
+function handleWebSocketMessage(data: Record<string, unknown>) {
+  // Handle state changes locally
+  if (data.type === "state_changed") {
+    if (data.state) {
+      state.appState = data.state as AppState;
+    }
+    if (data.message) {
+      state.stateMessage = data.message as string;
+    }
+  }
+
+  if (data.type === "error") {
+    state.lastError = (data.message as string) ?? "Unknown error";
+  }
+
+  // Dispatch to window for other stores (transcriptions, etc.)
+  if (data.type === "transcription") {
+    window.dispatchEvent(
+      new CustomEvent("backend:transcription", { detail: data })
+    );
+  } else if (data.type === "preview") {
+    window.dispatchEvent(
+      new CustomEvent("backend:preview", { detail: data })
+    );
+  } else if (data.type === "credits_low") {
+    window.dispatchEvent(
+      new CustomEvent("backend:credits_low", { detail: data })
+    );
+  }
+}
+
+// ── Port management ──────────────────────────────────────────────────
+
+function setPort(newPort: number) {
+  if (newPort === state.port) return;
+  state.port = newPort;
+  // Reconnect with new port if we had a connection
+  if (state.connectionState !== "disconnected") {
+    connectWebSocket();
+  }
+}
+
+// ── Typed REST helpers ───────────────────────────────────────────────
+
+async function apiGet<T = unknown>(path: string): Promise<T> {
+  const resp = await apiFetch(path);
+  if (!resp.ok) throw new Error(`GET ${path} failed: ${resp.status}`);
+  return resp.json();
+}
+
+async function apiPost<T = unknown>(
+  path: string,
+  body?: unknown
+): Promise<T> {
+  const resp = await apiFetch(path, {
+    method: "POST",
+    body: body !== undefined ? JSON.stringify(body) : undefined,
+  });
+  if (!resp.ok) throw new Error(`POST ${path} failed: ${resp.status}`);
+  return resp.json();
+}
+
+async function apiPut<T = unknown>(
+  path: string,
+  body?: unknown
+): Promise<T> {
+  const resp = await apiFetch(path, {
+    method: "PUT",
+    body: body !== undefined ? JSON.stringify(body) : undefined,
+  });
+  if (!resp.ok) throw new Error(`PUT ${path} failed: ${resp.status}`);
+  return resp.json();
+}
+
+// ── Public API ───────────────────────────────────────────────────────
+
+export const backendStore = {
+  get port() {
+    return state.port;
+  },
+  get connectionState() {
+    return state.connectionState;
+  },
+  get connected() {
+    return state.connectionState === "connected";
+  },
+  get appState() {
+    return state.appState;
+  },
+  get stateMessage() {
+    return state.stateMessage;
+  },
+  get deviceInfo() {
+    return state.deviceInfo;
+  },
+  get version() {
+    return state.version;
+  },
+  get lastError() {
+    return state.lastError;
+  },
+  get apiBaseUrl() {
+    return `http://localhost:${state.port}`;
+  },
+  get wsUrl() {
+    return `ws://localhost:${state.port}/ws/control`;
+  },
+  get obsUrl() {
+    // OBS display runs on the web server port (one below the API port)
+    const obsPort = state.port > 0 ? state.port - 1 : 8080;
+    return `http://localhost:${obsPort}`;
+  },
+  get syncUrl() {
+    return "";
+  },
+  setPort,
+  connect: connectWebSocket,
+  disconnect,
+  pollStatus,
+  apiUrl,
+  apiFetch,
+  apiGet,
+  apiPost,
+  apiPut,
+};

src/lib/stores/backend.test.ts

@@ -0,0 +1,77 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import { backendStore } from "./backend.svelte.ts";
+
+// Mock WebSocket globally so the store module can reference it
+class MockWebSocket {
+  onopen: ((ev: Event) => void) | null = null;
+  onclose: ((ev: CloseEvent) => void) | null = null;
+  onmessage: ((ev: MessageEvent) => void) | null = null;
+  onerror: ((ev: Event) => void) | null = null;
+  close = vi.fn();
+}
+vi.stubGlobal("WebSocket", MockWebSocket);
+
+// Mock fetch to prevent real network calls
+vi.stubGlobal(
+  "fetch",
+  vi.fn(() =>
+    Promise.resolve({
+      ok: true,
+      json: () => Promise.resolve({}),
+    })
+  )
+);
+
+describe("backend store", () => {
+  beforeEach(() => {
+    backendStore.disconnect();
+    backendStore.setPort(8081);
+  });
+
+  it("test_exports_expected_properties", () => {
+    expect(backendStore).toHaveProperty("port");
+    expect(backendStore).toHaveProperty("connectionState");
+    expect(backendStore).toHaveProperty("connected");
+    expect(backendStore).toHaveProperty("appState");
+    expect(backendStore).toHaveProperty("stateMessage");
+    expect(backendStore).toHaveProperty("deviceInfo");
+    expect(backendStore).toHaveProperty("version");
+    expect(backendStore).toHaveProperty("lastError");
+    expect(backendStore).toHaveProperty("apiBaseUrl");
+    expect(backendStore).toHaveProperty("wsUrl");
+    expect(backendStore).toHaveProperty("obsUrl");
+    expect(backendStore).toHaveProperty("syncUrl");
+  });
+
+  it("test_exports_expected_methods", () => {
+    expect(typeof backendStore.setPort).toBe("function");
+    expect(typeof backendStore.connect).toBe("function");
+    expect(typeof backendStore.disconnect).toBe("function");
+    expect(typeof backendStore.apiUrl).toBe("function");
+    expect(typeof backendStore.apiFetch).toBe("function");
+    expect(typeof backendStore.apiGet).toBe("function");
+    expect(typeof backendStore.apiPost).toBe("function");
+    expect(typeof backendStore.apiPut).toBe("function");
+  });
+
+  it("test_obsUrl_derives_from_port", () => {
+    backendStore.setPort(8081);
+    expect(backendStore.obsUrl).toBe("http://localhost:8080");
+  });
+
+  it("test_apiBaseUrl_uses_port", () => {
+    backendStore.setPort(8081);
+    expect(backendStore.apiBaseUrl).toBe("http://localhost:8081");
+  });
+
+  it("test_wsUrl_uses_port", () => {
+    backendStore.setPort(8081);
+    expect(backendStore.wsUrl).toBe("ws://localhost:8081/ws/control");
+  });
+
+  it("test_initial_state", () => {
+    // After disconnect() in beforeEach, state should be disconnected
+    expect(backendStore.connectionState).toBe("disconnected");
+    expect(backendStore.appState).toBe("initializing");
+  });
+});

src/lib/stores/config.svelte.ts

@@ -0,0 +1,243 @@
+/**
+ * Config store - manages application configuration loaded from
+ * and saved to the Python backend via the backend store's API helpers.
+ *
+ * The backend accepts PUT /api/config with `{ settings: { "dot.key": value } }`.
+ */
+
+import { backendStore } from "$lib/stores/backend";
+
+export interface AppConfig {
+  user: {
+    name: string;
+    id: string;
+  };
+  audio: {
+    input_device: string;
+    sample_rate: number;
+  };
+  transcription: {
+    model: string;
+    device: string;
+    language: string;
+    compute_type: string;
+    enable_realtime_transcription: boolean;
+    realtime_model: string;
+    realtime_processing_pause: number;
+    silero_sensitivity: number;
+    silero_use_onnx: boolean;
+    webrtc_sensitivity: number;
+    post_speech_silence_duration: number;
+    min_length_of_recording: number;
+    min_gap_between_recordings: number;
+    pre_recording_buffer_duration: number;
+    beam_size: number;
+    initial_prompt: string;
+    no_log_file: boolean;
+    continuous_mode: boolean;
+  };
+  server_sync: {
+    enabled: boolean;
+    url: string;
+    room: string;
+    passphrase: string;
+  };
+  display: {
+    show_timestamps: boolean;
+    max_lines: number;
+    font_source: string;
+    font_family: string;
+    websafe_font: string;
+    google_font: string;
+    custom_font_file: string;
+    font_size: number;
+    theme: string;
+    fade_after_seconds: number;
+    user_color: string;
+    text_color: string;
+    background_color: string;
+  };
+  web_server: {
+    port: number;
+    host: string;
+  };
+  remote: {
+    mode: string;
+    server_url: string;
+    auth_token: string;
+    byok_api_key: string;
+    deepgram_model: string;
+    language: string;
+    fallback_to_local: boolean;
+  };
+  updates: {
+    auto_check: boolean;
+    gitea_url: string;
+    owner: string;
+    repo: string;
+    skipped_versions: string[];
+    last_check: string;
+    check_interval_hours: number;
+  };
+}
+
+function getDefaultConfig(): AppConfig {
+  return {
+    user: { name: "User", id: "" },
+    audio: { input_device: "default", sample_rate: 16000 },
+    transcription: {
+      model: "base.en",
+      device: "auto",
+      language: "en",
+      compute_type: "default",
+      enable_realtime_transcription: false,
+      realtime_model: "tiny.en",
+      realtime_processing_pause: 0.1,
+      silero_sensitivity: 0.4,
+      silero_use_onnx: true,
+      webrtc_sensitivity: 3,
+      post_speech_silence_duration: 0.3,
+      min_length_of_recording: 0.5,
+      min_gap_between_recordings: 0,
+      pre_recording_buffer_duration: 0.2,
+      beam_size: 5,
+      initial_prompt: "",
+      no_log_file: true,
+      continuous_mode: false,
+    },
+    server_sync: {
+      enabled: false,
+      url: "",
+      room: "default",
+      passphrase: "",
+    },
+    display: {
+      show_timestamps: true,
+      max_lines: 100,
+      font_source: "System Font",
+      font_family: "Courier",
+      websafe_font: "Arial",
+      google_font: "Roboto",
+      custom_font_file: "",
+      font_size: 12,
+      theme: "dark",
+      fade_after_seconds: 10,
+      user_color: "#4CAF50",
+      text_color: "#FFFFFF",
+      background_color: "#000000B3",
+    },
+    web_server: { port: 8080, host: "127.0.0.1" },
+    remote: {
+      mode: "byok",
+      server_url: "",
+      auth_token: "",
+      byok_api_key: "",
+      deepgram_model: "nova-2",
+      language: "en-US",
+      fallback_to_local: true,
+    },
+    updates: {
+      auto_check: true,
+      gitea_url: "https://repo.anhonesthost.net",
+      owner: "streamer-tools",
+      repo: "local-transcription",
+      skipped_versions: [],
+      last_check: "",
+      check_interval_hours: 24,
+    },
+  };
+}
+
+let config = $state<AppConfig>(getDefaultConfig());
+let loading = $state(false);
+let error = $state("");
+
+/**
+ * Fetch the full configuration tree from the backend.
+ * GET /api/config
+ */
+async function fetchConfig(): Promise<void> {
+  loading = true;
+  error = "";
+
+  try {
+    const data = await backendStore.apiGet<Record<string, unknown>>("/api/config");
+    // Deep merge with defaults to ensure all keys exist
+    config = deepMerge(getDefaultConfig(), data) as AppConfig;
+  } catch (err) {
+    error = err instanceof Error ? err.message : String(err);
+    console.error("[config] fetchConfig failed:", error);
+  } finally {
+    loading = false;
+  }
+}
+
+function deepMerge(target: Record<string, unknown>, source: Record<string, unknown>): Record<string, unknown> {
+  const result = { ...target };
+  for (const key of Object.keys(source)) {
+    if (
+      source[key] &&
+      typeof source[key] === "object" &&
+      !Array.isArray(source[key]) &&
+      target[key] &&
+      typeof target[key] === "object" &&
+      !Array.isArray(target[key])
+    ) {
+      result[key] = deepMerge(
+        target[key] as Record<string, unknown>,
+        source[key] as Record<string, unknown>
+      );
+    } else {
+      result[key] = source[key];
+    }
+  }
+  return result;
+}
+
+/**
+ * Send a batch of setting updates to the backend.
+ * PUT /api/config with body `{ settings: { "dot.key": value, ... } }`
+ *
+ * Keys use dot-notation, e.g. `{ "transcription.model": "small.en" }`.
+ *
+ * Returns the response payload on success, or throws on failure.
+ */
+async function updateConfig(
+  settings: Record<string, unknown>,
+): Promise<{ status: string; message: string; engine_reloaded: boolean }> {
+  loading = true;
+  error = "";
+
+  try {
+    const result = await backendStore.apiPut<{
+      status: string;
+      message: string;
+      engine_reloaded: boolean;
+    }>("/api/config", { settings });
+
+    // Refresh the local config tree so the UI stays in sync
+    await fetchConfig();
+
+    return result;
+  } catch (err) {
+    error = err instanceof Error ? err.message : String(err);
+    console.error("[config] updateConfig failed:", error);
+    throw err;
+  } finally {
+    loading = false;
+  }
+}
+
+export const configStore = {
+  get config() {
+    return config;
+  },
+  get loading() {
+    return loading;
+  },
+  get error() {
+    return error;
+  },
+  fetchConfig,
+  updateConfig,
+};

src/lib/stores/config.test.ts

@@ -0,0 +1,48 @@
+import { describe, it, expect, vi } from "vitest";
+
+// Mock fetch so the backend store module doesn't make real requests
+vi.stubGlobal(
+  "fetch",
+  vi.fn(() =>
+    Promise.resolve({
+      ok: true,
+      json: () => Promise.resolve({}),
+    })
+  )
+);
+
+// Mock WebSocket for the backend store dependency
+class MockWebSocket {
+  onopen: ((ev: Event) => void) | null = null;
+  onclose: ((ev: CloseEvent) => void) | null = null;
+  onmessage: ((ev: MessageEvent) => void) | null = null;
+  onerror: ((ev: Event) => void) | null = null;
+  close = vi.fn();
+}
+vi.stubGlobal("WebSocket", MockWebSocket);
+
+import { configStore } from "./config.svelte.ts";
+
+describe("config store", () => {
+  it("test_has_fetchConfig_method", () => {
+    expect(typeof configStore.fetchConfig).toBe("function");
+  });
+
+  it("test_has_updateConfig_method", () => {
+    expect(typeof configStore.updateConfig).toBe("function");
+  });
+
+  it("test_config_defaults_have_expected_keys", () => {
+    const cfg = configStore.config;
+    expect(cfg).toHaveProperty("user");
+    expect(cfg).toHaveProperty("audio");
+    expect(cfg).toHaveProperty("transcription");
+    expect(cfg).toHaveProperty("display");
+    expect(cfg).toHaveProperty("remote");
+    expect(cfg).toHaveProperty("updates");
+  });
+
+  it("test_remote_config_has_byok_api_key", () => {
+    expect(configStore.config.remote.byok_api_key).toBeDefined();
+  });
+});

src/lib/stores/file-extension.test.ts

@@ -0,0 +1,34 @@
+import { describe, it, expect } from "vitest";
+import * as fs from "node:fs";
+import * as path from "node:path";
+
+describe("store file extensions", () => {
+  it("test_store_files_use_svelte_ts_extension", () => {
+    const storesDir = path.resolve(__dirname);
+    const files = fs.readdirSync(storesDir);
+
+    // Find .ts files that are NOT .svelte.ts and NOT test files
+    const plainTsFiles = files.filter(
+      (f) =>
+        f.endsWith(".ts") &&
+        !f.endsWith(".svelte.ts") &&
+        !f.endsWith(".test.ts")
+    );
+
+    for (const file of plainTsFiles) {
+      const content = fs.readFileSync(path.join(storesDir, file), "utf-8");
+      expect(content).not.toMatch(
+        /\$state\s*[<(]/,
+        `${file} uses $state() but does not have .svelte.ts extension`
+      );
+      expect(content).not.toMatch(
+        /\$derived\s*[<(]/,
+        `${file} uses $derived() but does not have .svelte.ts extension`
+      );
+      expect(content).not.toMatch(
+        /\$effect\s*[<(]/,
+        `${file} uses $effect() but does not have .svelte.ts extension`
+      );
+    }
+  });
+});

src/lib/stores/transcriptions.svelte.ts

@@ -0,0 +1,109 @@
+/**
+ * Transcriptions store - manages the list of transcription items
+ * received from the backend via WebSocket.
+ */
+
+export interface TranscriptionItem {
+  id: string;
+  text: string;
+  userName: string;
+  timestamp: string;
+  isPreview: boolean;
+}
+
+let items = $state<TranscriptionItem[]>([]);
+let nextId = 0;
+
+function generateId(): string {
+  return `t-${Date.now()}-${nextId++}`;
+}
+
+function addTranscription(data: {
+  text?: string;
+  user_name?: string;
+  timestamp?: string;
+}) {
+  // When a final transcription arrives, remove any existing preview
+  const previewIndex = items.findIndex((item) => item.isPreview);
+  if (previewIndex !== -1) {
+    items.splice(previewIndex, 1);
+  }
+
+  items.push({
+    id: generateId(),
+    text: data.text ?? "",
+    userName: data.user_name ?? "",
+    timestamp: data.timestamp ?? "",
+    isPreview: false,
+  });
+
+  // Keep a reasonable limit
+  if (items.length > 500) {
+    items.splice(0, items.length - 500);
+  }
+}
+
+function setPreview(data: {
+  text?: string;
+  user_name?: string;
+  timestamp?: string;
+}) {
+  const existingIndex = items.findIndex((item) => item.isPreview);
+  const previewItem: TranscriptionItem = {
+    id: existingIndex !== -1 ? items[existingIndex].id : generateId(),
+    text: data.text ?? "",
+    userName: data.user_name ?? "",
+    timestamp: data.timestamp ?? "",
+    isPreview: true,
+  };
+
+  if (existingIndex !== -1) {
+    items[existingIndex] = previewItem;
+  } else {
+    items.push(previewItem);
+  }
+}
+
+function clearAll() {
+  items.length = 0;
+}
+
+function getPlainText(): string {
+  return items
+    .filter((item) => !item.isPreview)
+    .map((item) => {
+      let line = "";
+      if (item.timestamp) line += `[${item.timestamp}] `;
+      if (item.userName) line += `${item.userName}: `;
+      line += item.text;
+      return line;
+    })
+    .join("\n");
+}
+
+// Listen for backend events
+if (typeof window !== "undefined") {
+  window.addEventListener("backend:transcription", ((e: CustomEvent) => {
+    addTranscription(e.detail);
+  }) as EventListener);
+
+  window.addEventListener("backend:preview", ((e: CustomEvent) => {
+    setPreview(e.detail);
+  }) as EventListener);
+}
+
+export const transcriptionStore = {
+  get items() {
+    return items;
+  },
+  get currentPreview(): TranscriptionItem | null {
+    return items.find((item) => item.isPreview) ?? null;
+  },
+  get transcriptions(): TranscriptionItem[] {
+    return items.filter((item) => !item.isPreview);
+  },
+  addTranscription,
+  setPreview,
+  clearAll,
+  getPlainText,
+};

src/lib/stores/transcriptions.test.ts

@@ -0,0 +1,71 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+
+// Mock WebSocket for the backend store dependency (loaded transitively)
+class MockWebSocket {
+  onopen: ((ev: Event) => void) | null = null;
+  onclose: ((ev: CloseEvent) => void) | null = null;
+  onmessage: ((ev: MessageEvent) => void) | null = null;
+  onerror: ((ev: Event) => void) | null = null;
+  close = vi.fn();
+}
+vi.stubGlobal("WebSocket", MockWebSocket);
+
+vi.stubGlobal(
+  "fetch",
+  vi.fn(() =>
+    Promise.resolve({
+      ok: true,
+      json: () => Promise.resolve({}),
+    })
+  )
+);
+
+import { transcriptionStore } from "./transcriptions.svelte.ts";
+
+describe("transcriptions store", () => {
+  beforeEach(() => {
+    transcriptionStore.clearAll();
+  });
+
+  it("test_addTranscription", () => {
+    transcriptionStore.addTranscription({
+      text: "Hello world",
+      user_name: "TestUser",
+      timestamp: "12:00:00",
+    });
+
+    expect(transcriptionStore.items.length).toBe(1);
+    expect(transcriptionStore.items[0].text).toBe("Hello world");
+    expect(transcriptionStore.items[0].userName).toBe("TestUser");
+    expect(transcriptionStore.items[0].timestamp).toBe("12:00:00");
+    expect(transcriptionStore.items[0].isPreview).toBe(false);
+  });
+
+  it("test_clearAll", () => {
+    transcriptionStore.addTranscription({ text: "One" });
+    transcriptionStore.addTranscription({ text: "Two" });
+    expect(transcriptionStore.items.length).toBe(2);
+
+    transcriptionStore.clearAll();
+    expect(transcriptionStore.items.length).toBe(0);
+  });
+
+  it("test_getPlainText", () => {
+    transcriptionStore.addTranscription({
+      text: "Hello",
+      user_name: "Alice",
+      timestamp: "10:00",
+    });
+    transcriptionStore.addTranscription({
+      text: "World",
+      user_name: "Bob",
+      timestamp: "10:01",
+    });
+
+    const text = transcriptionStore.getPlainText();
+    expect(text).toContain("[10:00] Alice: Hello");
+    expect(text).toContain("[10:01] Bob: World");
+    // Lines separated by newline
+    expect(text.split("\n").length).toBe(2);
+  });
+});

version.py

@@ -1,7 +1,7 @@
 """Version information for Local Transcription."""
 
-__version__ = "1.4.0"
-__version_info__ = (1, 4, 0)
+__version__ = "2.0.15"
+__version_info__ = (2, 0, 15)
 
 # Version history:
 # 1.4.0 - Auto-update feature:

vite.config.ts

@@ -10,6 +10,7 @@ export default defineConfig({
     alias: {
       $lib: path.resolve("./src/lib"),
     },
+    extensions: [".svelte.ts", ".ts", ".svelte", ".js", ".mjs", ".mts"],
   },
   server: {
     port: 1420,
@@ -18,4 +19,8 @@ export default defineConfig({
       ignored: ["**/src-tauri/**", "**/client/**", "**/server/**", "**/backend/**", "**/gui/**"],
     },
   },
+  test: {
+    environment: "jsdom",
+    include: ["src/**/*.test.ts"],
+  },
 });