merge: resolve conflicts with latest main

CHANGELOG.md

@@ -71,9 +71,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - Self-documenting help system with `make help`
   - Colored output for better readability
   - Supports parallel development server execution
+- **Audiobook Tab** - New long-form narration workflow in the app
+  - Import/paste `.txt` book content and review/edit before generation
+  - Generate a quick 5-sentence preview before full run
+  - Chunk long text automatically and process chunk-by-chunk with retry support
+  - Auto-create and update a Story during generation, with export shortcut
+- **Text chunking utility** - Added reusable sentence-aware chunking for large text inputs (`app/src/lib/utils/textChunking.ts`)
 
 ### Changed
 - **README** - Added Makefile reference and updated Quick Start with Makefile-based setup instructions alongside manual setup
+- **Navigation** - Added Audiobook route/tab to the app sidebar
+- **Generation API types** - Added optional `instruct` field to `GenerationRequest`
+- **App styling** - Added `scrollbar-visible` utility styles for long-scroll panels/editors
 
 ---
 

app/src/components/Sidebar.tsx

@@ -1,5 +1,5 @@
-import { Link, useMatchRoute } from '@tanstack/react-router';
-import { Box, BookOpen, Loader2, Mic, Server, Speaker, Volume2 } from 'lucide-react';
+import { Link, useMatchRoute, useRouterState } from '@tanstack/react-router';
+import { BookOpen, BookText, Box, Loader2, Mic, Server, Speaker, Volume2 } from 'lucide-react';
 import voiceboxLogo from '@/assets/voicebox-logo.png';
 import { cn } from '@/lib/utils/cn';
 import { useGenerationStore } from '@/stores/generationStore';
@@ -12,6 +12,7 @@ interface SidebarProps {
 const tabs = [
   { id: 'main', path: '/', icon: Volume2, label: 'Generate' },
   { id: 'stories', path: '/stories', icon: BookOpen, label: 'Stories' },
+  { id: 'audiobook', path: '/audiobook', icon: BookText, label: 'Audiobook' },
   { id: 'voices', path: '/voices', icon: Mic, label: 'Voices' },
   { id: 'audio', path: '/audio', icon: Speaker, label: 'Audio' },
   { id: 'models', path: '/models', icon: Box, label: 'Models' },
@@ -23,6 +24,9 @@ export function Sidebar({ isMacOS }: SidebarProps) {
   const audioUrl = usePlayerStore((state) => state.audioUrl);
   const isPlayerVisible = !!audioUrl;
   const matchRoute = useMatchRoute();
+  const pathname = useRouterState({
+    select: (state) => state.location.pathname,
+  });
 
   return (
     <div
@@ -41,10 +45,7 @@ export function Sidebar({ isMacOS }: SidebarProps) {
         {tabs.map((tab) => {
           const Icon = tab.icon;
           // For index route, use exact match; for others, use default matching
-          const isActive =
-            tab.path === '/'
-              ? matchRoute({ to: '/', exact: true })
-              : matchRoute({ to: tab.path });
+          const isActive = tab.path === '/' ? pathname === '/' : matchRoute({ to: tab.path });
 
           return (
             <Link

app/src/index.css

@@ -125,6 +125,32 @@
     text-orientation: mixed;
     letter-spacing: 0.1em;
   }
+
+  .scrollbar-visible {
+    scrollbar-width: thin;
+    -ms-overflow-style: auto;
+    scrollbar-color: #d8ab4f #2b2b2b;
+  }
+
+  .scrollbar-visible::-webkit-scrollbar {
+    display: block;
+    width: 10px;
+    height: 10px;
+  }
+
+  .scrollbar-visible::-webkit-scrollbar-track {
+    background: #2b2b2b;
+  }
+
+  .scrollbar-visible::-webkit-scrollbar-thumb {
+    background: #d8ab4f;
+    border-radius: 9999px;
+    border: 2px solid #131313;
+  }
+
+  .scrollbar-visible::-webkit-scrollbar-thumb:hover {
+    background: #e2b85e;
+  }
 }
 
 @keyframes fadeInScale {

app/src/lib/utils/textChunking.ts

@@ -0,0 +1,99 @@
+export interface TextChunk {
+  id: string;
+  text: string;
+  charCount: number;
+  wordCount: number;
+}
+
+function normalizeText(text: string): string {
+  return text.replace(/\r\n/g, '\n').replace(/\r/g, '\n').trim();
+}
+
+function splitParagraphIntoSentences(paragraph: string): string[] {
+  const trimmed = paragraph.trim();
+  if (!trimmed) {
+    return [];
+  }
+
+  const matches = trimmed.match(/[^.!?]+[.!?]+(?:["')\]]+)?|[^.!?]+$/g);
+  if (!matches || matches.length === 0) {
+    return [trimmed];
+  }
+
+  return matches.map((sentence) => sentence.trim()).filter(Boolean);
+}
+
+export function chunkText(
+  rawText: string,
+  targetChunkSize: number,
+  maxChunkSize: number,
+): TextChunk[] {
+  const text = normalizeText(rawText);
+  if (!text) {
+    return [];
+  }
+
+  const safeTarget = Math.max(200, Math.min(targetChunkSize, maxChunkSize));
+  const paragraphs = text
+    .split(/\n{2,}/)
+    .map((paragraph) => paragraph.trim())
+    .filter(Boolean);
+
+  const chunks: string[] = [];
+  let current = '';
+
+  const pushCurrent = () => {
+    const normalized = current.trim();
+    if (!normalized) {
+      return;
+    }
+    chunks.push(normalized);
+    current = '';
+  };
+
+  for (const paragraph of paragraphs) {
+    const sentences = splitParagraphIntoSentences(paragraph);
+
+    for (const sentence of sentences) {
+      // Keep sentence integrity. If one sentence exceeds maxChunkSize,
+      // keep it as a single oversized chunk and let UI ask for manual edit.
+      if (sentence.length > maxChunkSize) {
+        pushCurrent();
+        chunks.push(sentence);
+        continue;
+      }
+
+      if (!current) {
+        current = sentence;
+        continue;
+      }
+
+      const candidate = `${current} ${sentence}`;
+      if (candidate.length <= safeTarget) {
+        current = candidate;
+        continue;
+      }
+
+      if (candidate.length <= maxChunkSize && current.length < Math.floor(safeTarget * 0.75)) {
+        current = candidate;
+        continue;
+      }
+
+      pushCurrent();
+      current = sentence;
+    }
+
+    if (current.length >= Math.floor(safeTarget * 0.8)) {
+      pushCurrent();
+    }
+  }
+
+  pushCurrent();
+
+  return chunks.map((chunkTextValue, index) => ({
+    id: `chunk-${index + 1}`,
+    text: chunkTextValue,
+    charCount: chunkTextValue.length,
+    wordCount: chunkTextValue.split(/\s+/).filter(Boolean).length,
+  }));
+}

app/src/router.tsx

@@ -1,5 +1,6 @@
 import { createRootRoute, createRoute, createRouter, Outlet } from '@tanstack/react-router';
 import { AppFrame } from '@/components/AppFrame/AppFrame';
+import { AudiobookTab } from '@/components/AudiobookTab/AudiobookTab';
 import { AudioTab } from '@/components/AudioTab/AudioTab';
 import { MainEditor } from '@/components/MainEditor/MainEditor';
 import { ModelsTab } from '@/components/ModelsTab/ModelsTab';
@@ -10,6 +11,7 @@ import { Toaster } from '@/components/ui/toaster';
 import { VoicesTab } from '@/components/VoicesTab/VoicesTab';
 import { useModelDownloadToast } from '@/lib/hooks/useModelDownloadToast';
 import { MODEL_DISPLAY_NAMES, useRestoreActiveTasks } from '@/lib/hooks/useRestoreActiveTasks';
+
 // Simple platform check that works in both web and Tauri
 const isMacOS = () => navigator.platform.toLowerCase().includes('mac');
 
@@ -86,6 +88,13 @@ const storiesRoute = createRoute({
   component: StoriesTab,
 });
 
+// Audiobook route
+const audiobookRoute = createRoute({
+  getParentRoute: () => rootRoute,
+  path: '/audiobook',
+  component: AudiobookTab,
+});
+
 // Voices route
 const voicesRoute = createRoute({
   getParentRoute: () => rootRoute,
@@ -118,6 +127,7 @@ const serverRoute = createRoute({
 const routeTree = rootRoute.addChildren([
   indexRoute,
   storiesRoute,
+  audiobookRoute,
   voicesRoute,
   audioRoute,
   modelsRoute,

backend/main.py

@@ -222,75 +222,6 @@ async def health():
     )
 
 
-@app.get("/health/filesystem", response_model=models.FilesystemHealthResponse)
-async def filesystem_health():
-    """Check filesystem health: directory existence, write permissions, and disk space."""
-    import shutil
-
-    dirs_to_check = {
-        "generations": config.get_generations_dir(),
-        "profiles": config.get_profiles_dir(),
-        "data": config.get_data_dir(),
-    }
-
-    checks: list[models.DirectoryCheck] = []
-    all_ok = True
-
-    for _label, dir_path in dirs_to_check.items():
-        exists = dir_path.exists()
-        writable = False
-        error = None
-        if exists:
-            # Probe writability with a temp file
-            probe = dir_path / ".voicebox_probe"
-            try:
-                probe.write_text("ok")
-                probe.unlink()
-                writable = True
-            except PermissionError:
-                error = "Permission denied"
-            except OSError as e:
-                error = str(e)
-            finally:
-                try:
-                    probe.unlink(missing_ok=True)
-                except Exception:
-                    pass
-        else:
-            error = "Directory does not exist"
-
-        if not exists or not writable:
-            all_ok = False
-
-        checks.append(
-            models.DirectoryCheck(
-                path=str(dir_path),
-                exists=exists,
-                writable=writable,
-                error=error,
-            )
-        )
-
-    # Disk space for the data directory
-    disk_free_mb = None
-    disk_total_mb = None
-    try:
-        usage = shutil.disk_usage(str(config.get_data_dir()))
-        disk_free_mb = round(usage.free / (1024 * 1024), 1)
-        disk_total_mb = round(usage.total / (1024 * 1024), 1)
-        if disk_free_mb < 500:
-            all_ok = False
-    except OSError:
-        all_ok = False
-
-    return models.FilesystemHealthResponse(
-        healthy=all_ok,
-        disk_free_mb=disk_free_mb,
-        disk_total_mb=disk_total_mb,
-        directories=checks,
-    )
-
-
 # ============================================
 # VOICE PROFILE ENDPOINTS
 # ============================================
@@ -797,30 +728,7 @@ async def generate_speech(
         audio_path = config.get_generations_dir() / f"{generation_id}.wav"
 
         from .utils.audio import save_audio
-        import errno
-
-        try:
-            save_audio(audio, str(audio_path), sample_rate)
-        except BrokenPipeError:
-            raise HTTPException(
-                status_code=500,
-                detail="Audio save failed: broken pipe (the output stream was closed unexpectedly)",
-            )
-        except OSError as save_err:
-            err_no = getattr(save_err, "errno", None) or (
-                getattr(save_err.__cause__, "errno", None)
-                if save_err.__cause__
-                else None
-            )
-            if err_no == errno.ENOENT:
-                msg = f"Audio save failed: directory not found — {audio_path.parent}"
-            elif err_no == errno.EACCES:
-                msg = f"Audio save failed: permission denied — {audio_path.parent}"
-            elif err_no == errno.ENOSPC:
-                msg = "Audio save failed: no disk space remaining"
-            else:
-                msg = f"Audio save failed: {save_err}"
-            raise HTTPException(status_code=500, detail=msg)
+        save_audio(audio, str(audio_path), sample_rate)
 
         # Create history entry
         generation = await history.create_generation(

backend/models.py

@@ -131,22 +131,6 @@ class HealthResponse(BaseModel):
     backend_variant: Optional[str] = None  # Binary variant (cpu or cuda)
 
 
-class DirectoryCheck(BaseModel):
-    """Health status for a single directory."""
-    path: str
-    exists: bool
-    writable: bool
-    error: Optional[str] = None
-
-
-class FilesystemHealthResponse(BaseModel):
-    """Response model for filesystem health check."""
-    healthy: bool
-    disk_free_mb: Optional[float] = None
-    disk_total_mb: Optional[float] = None
-    directories: List[DirectoryCheck]
-
-
 class ModelStatus(BaseModel):
     """Response model for model status."""
     model_name: str

backend/utils/audio.py

@@ -70,43 +70,14 @@ def save_audio(
     sample_rate: int = 24000,
 ) -> None:
     """
-    Save audio file with atomic write and error handling.
-
-    Writes to a temporary file first, then atomically renames to the
-    target path.  This prevents corrupted/partial WAV files if the
-    process is interrupted mid-write.
-
+    Save audio file.
+    
     Args:
         audio: Audio array
         path: Output path
         sample_rate: Sample rate
-
-    Raises:
-        OSError: If file cannot be written
     """
-    from pathlib import Path
-    import os
-
-    temp_path = f"{path}.tmp"
-    try:
-        # Ensure parent directory exists
-        Path(path).parent.mkdir(parents=True, exist_ok=True)
-
-        # Write to temporary file first
-        sf.write(temp_path, audio, sample_rate)
-
-        # Atomic rename to final path
-        os.replace(temp_path, path)
-
-    except Exception as e:
-        # Clean up temp file on failure
-        try:
-            if Path(temp_path).exists():
-                Path(temp_path).unlink()
-        except Exception:
-            pass  # Best effort cleanup
-
-        raise OSError(f"Failed to save audio to {path}: {e}") from e
+    sf.write(path, audio, sample_rate)
 
 
 def trim_tts_output(

bun.lock

@@ -13,7 +13,7 @@
     },
     "app": {
       "name": "@voicebox/app",
-      "version": "0.1.11",
+      "version": "0.1.12",
       "dependencies": {
         "@dnd-kit/core": "^6.3.1",
         "@dnd-kit/sortable": "^10.0.0",
@@ -68,7 +68,7 @@
     },
     "landing": {
       "name": "@voicebox/landing",
-      "version": "0.1.11",
+      "version": "0.1.12",
       "dependencies": {
         "@radix-ui/react-separator": "^1.1.8",
         "@radix-ui/react-slot": "^1.2.4",
@@ -93,7 +93,7 @@
     },
     "tauri": {
       "name": "@voicebox/tauri",
-      "version": "0.1.11",
+      "version": "0.1.12",
       "dependencies": {
         "@tauri-apps/api": "^2.0.0",
         "@tauri-apps/plugin-dialog": "^2.0.0",
@@ -116,7 +116,7 @@
     },
     "web": {
       "name": "@voicebox/web",
-      "version": "0.1.11",
+      "version": "0.1.12",
       "dependencies": {
         "@tanstack/react-query": "^5.0.0",
         "react": "^18.3.0",
@@ -125,6 +125,7 @@
         "zustand": "^4.5.0",
       },
       "devDependencies": {
+        "@tailwindcss/vite": "^4.0.0",
         "@types/react": "^18.3.0",
         "@types/react-dom": "^18.3.0",
         "@typescript-eslint/eslint-plugin": "^7.0.0",