fix(splitter): 🐛 Add file availability pre-check and upload validation for Windows

docs/IPC_API.md

@@ -80,7 +80,6 @@ Handle file operations (upload, download, dialog).
 |--------|-------------|
 | `window.api.file.selectDialog()` | Open file selection dialog |
 | `window.api.file.upload(taskId, filePath)` | Upload file |
-| `window.api.file.uploadMultiple(taskId, filePaths[])` | Upload multiple files |
 | `window.api.file.uploadFileContent(taskId, fileName, fileBuffer)` | Upload file content as ArrayBuffer |
 | `window.api.file.getImagePath(taskId, page)` | Get image path for a page |
 | `window.api.file.downloadMarkdown(taskId)` | Download merged markdown file |

src/core/domain/repositories/TaskRepository.ts

@@ -28,16 +28,16 @@ const findById = async (id: string) => {
 const create = async (task: Task) => {
   return await prisma.task.create({
     data: {
-      id: uuidv4(),
+      id: task?.id || uuidv4(),
       filename: task?.filename || '',
       type: task?.type || '',
       page_range: task?.page_range || '',
       pages: task?.pages || 0,
       provider: task?.provider || 0,
       model: task?.model || '',
       model_name: task?.model_name || '',
-      progress: 0,
-      status: 0,
+      progress: task?.progress ?? 0,
+      status: task?.status ?? 0,
     }
   });
 };

src/core/infrastructure/adapters/split/FileWaitUtil.ts

@@ -0,0 +1,91 @@
+import { promises as fs } from 'fs';
+import path from 'path';
+
+/**
+ * Utility for waiting on file availability.
+ *
+ * On Windows, antivirus software may temporarily lock newly copied files for scanning,
+ * or filesystem operations may have slight delays. This utility retries file access
+ * checks before proceeding with actual file processing.
+ */
+export class FileWaitUtil {
+  private static readonly MAX_ATTEMPTS = 5;
+  private static readonly DELAY_MS = 1000;
+
+  /**
+   * Wait for a file to become available and non-empty.
+   *
+   * @param filePath - Full path to the file
+   * @param uploadsDir - Base uploads directory for diagnostic logging
+   * @param taskId - Task ID for diagnostic logging
+   * @param filename - Original filename for error messages
+   * @param label - Log label (e.g., 'PDFSplitter', 'ImageSplitter')
+   * @throws Error if the file is not found after all retries
+   */
+  static async waitForFile(
+    filePath: string,
+    uploadsDir: string,
+    taskId: string,
+    filename: string,
+    label: string
+  ): Promise<void> {
+    for (let attempt = 1; attempt <= this.MAX_ATTEMPTS; attempt++) {
+      try {
+        await fs.access(filePath);
+        const stats = await fs.stat(filePath);
+        if (stats.size > 0) {
+          if (attempt > 1) {
+            console.log(
+              `[${label}] File became available on attempt ${attempt}: ${filePath}`
+            );
+          }
+          return;
+        }
+        console.warn(
+          `[${label}] File exists but is empty (attempt ${attempt}/${this.MAX_ATTEMPTS}): ${filePath}`
+        );
+      } catch {
+        console.warn(
+          `[${label}] File not accessible (attempt ${attempt}/${this.MAX_ATTEMPTS}): ${filePath}`
+        );
+      }
+
+      if (attempt < this.MAX_ATTEMPTS) {
+        await new Promise((resolve) => setTimeout(resolve, this.DELAY_MS));
+      }
+    }
+
+    // Log diagnostic info before throwing
+    await this.logDiagnostics(uploadsDir, taskId, filename, label);
+
+    throw new Error(
+      `${label === 'PDFSplitter' ? 'PDF' : 'Image'} file not found: ${filename}. The file may have been moved or deleted.`
+    );
+  }
+
+  /**
+   * Log diagnostic information about the task directory contents.
+   */
+  private static async logDiagnostics(
+    uploadsDir: string,
+    taskId: string,
+    filename: string,
+    label: string
+  ): Promise<void> {
+    const taskDir = path.join(uploadsDir, taskId);
+    try {
+      const dirExists = await fs.stat(taskDir).then(() => true).catch(() => false);
+      if (dirExists) {
+        const files = await fs.readdir(taskDir);
+        console.error(
+          `[${label}] Task directory exists but target file not found. ` +
+          `Dir: ${taskDir}, Files in dir: [${files.join(', ')}], Expected: ${filename}`
+        );
+      } else {
+        console.error(`[${label}] Task directory does not exist: ${taskDir}`);
+      }
+    } catch (diagError) {
+      console.error(`[${label}] Diagnostic check failed:`, diagError);
+    }
+  }
+}

src/core/infrastructure/adapters/split/ImageSplitter.ts

@@ -3,6 +3,7 @@ import path from 'path';
 import { ISplitter, SplitResult, PageInfo } from '../../../domain/split/ISplitter.js';
 import { Task } from '../../../../shared/types/index.js';
 import { ImagePathUtil } from './ImagePathUtil.js';
+import { FileWaitUtil } from './FileWaitUtil.js';
 
 /**
  * Image splitter implementation for single-page image files.
@@ -41,10 +42,10 @@ export class ImageSplitter implements ISplitter {
     const filename = task.filename;
     const sourcePath = path.join(this.uploadsDir, taskId, filename);
 
-    try {
-      // Validate source file exists
-      await fs.access(sourcePath);
+    // Pre-check: wait for file to become available (handles antivirus scanning delays on Windows)
+    await FileWaitUtil.waitForFile(sourcePath, this.uploadsDir, taskId, filename, 'ImageSplitter');
 
+    try {
       // Get file extension (preserve original format)
       const ext = path.extname(filename).toLowerCase();
       if (!ext) {

src/core/infrastructure/adapters/split/PDFSplitter.ts

@@ -6,6 +6,7 @@ import { ISplitter, SplitResult, PageInfo } from '../../../domain/split/ISplitte
 import { Task } from '../../../../shared/types/index.js';
 import { PageRangeParser } from '../../../domain/split/PageRangeParser.js';
 import { ImagePathUtil } from './ImagePathUtil.js';
+import { FileWaitUtil } from './FileWaitUtil.js';
 import { WORKER_CONFIG } from '../../config/worker.config.js';
 
 /**
@@ -43,6 +44,10 @@ export class PDFSplitter implements ISplitter {
     const filename = task.filename;
     const sourcePath = path.join(this.uploadsDir, taskId, filename);
 
+    // Pre-check: verify source file exists before processing
+    // Retry with short delays to handle antivirus scanning or filesystem sync delays
+    await FileWaitUtil.waitForFile(sourcePath, this.uploadsDir, taskId, filename, 'PDFSplitter');
+
     try {
       // Step 1: Get total page count with retry
       const totalPages = await this.getPDFPageCountWithRetry(sourcePath);

src/core/infrastructure/adapters/split/__tests__/ImageSplitter.test.ts

@@ -1,13 +1,23 @@
 import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest';
 import { ImageSplitter } from '../ImageSplitter.js';
 import { ImagePathUtil } from '../ImagePathUtil.js';
+import { FileWaitUtil } from '../FileWaitUtil.js';
 import { promises as fs } from 'fs';
 import path from 'path';
 
+// Mock FileWaitUtil
+vi.mock('../FileWaitUtil.js', () => ({
+  FileWaitUtil: {
+    waitForFile: vi.fn(),
+  },
+}));
+
 // Mock fs promises
 vi.mock('fs', () => ({
   promises: {
     access: vi.fn(),
+    stat: vi.fn(),
+    readdir: vi.fn(),
     mkdir: vi.fn(),
     copyFile: vi.fn(),
     rm: vi.fn(),
@@ -27,6 +37,9 @@ describe('ImageSplitter', () => {
 
     // Reset mocks
     vi.clearAllMocks();
+
+    // Setup default mock for FileWaitUtil (file available immediately)
+    vi.mocked(FileWaitUtil.waitForFile).mockResolvedValue(undefined);
   });
 
   afterEach(() => {
@@ -189,7 +202,10 @@ describe('ImageSplitter', () => {
         filename: 'missing.jpg',
       };
 
-      vi.mocked(fs.access).mockRejectedValue(new Error('ENOENT: no such file'));
+      // Mock FileWaitUtil to reject (file not found)
+      vi.mocked(FileWaitUtil.waitForFile).mockRejectedValue(
+        new Error('Image file not found: missing.jpg. The file may have been moved or deleted.')
+      );
 
       await expect(splitter.split(task)).rejects.toThrow(/Image file not found/);
     });
@@ -200,7 +216,9 @@ describe('ImageSplitter', () => {
         filename: 'photo.jpg',
       };
 
-      vi.mocked(fs.access).mockRejectedValue(new Error('EACCES: permission denied'));
+      // FileWaitUtil passes, but file copy fails with permission denied
+      vi.mocked(fs.mkdir).mockResolvedValue(undefined);
+      vi.mocked(fs.copyFile).mockRejectedValue(new Error('EACCES: permission denied'));
 
       await expect(splitter.split(task)).rejects.toThrow(/Permission denied/);
     });

src/core/infrastructure/adapters/split/__tests__/PDFSplitter.test.ts

@@ -16,6 +16,13 @@ vi.mock('pdf-lib', () => ({
   },
 }));
 
+// Mock FileWaitUtil
+vi.mock('../FileWaitUtil.js', () => ({
+  FileWaitUtil: {
+    waitForFile: vi.fn(),
+  },
+}));
+
 // Mock fs promises
 vi.mock('fs', () => ({
   promises: {
@@ -24,11 +31,15 @@ vi.mock('fs', () => ({
     rm: vi.fn(),
     unlink: vi.fn(),
     readFile: vi.fn(),
+    access: vi.fn(),
+    stat: vi.fn(),
+    readdir: vi.fn(),
   },
 }));
 
 import { pdfToPng } from 'pdf-to-png-converter';
 import { PDFDocument } from 'pdf-lib';
+import { FileWaitUtil } from '../FileWaitUtil.js';
 
 describe('PDFSplitter', () => {
   const uploadsDir = '/mock/uploads';
@@ -44,6 +55,9 @@ describe('PDFSplitter', () => {
     // Reset mocks
     vi.clearAllMocks();
 
+    // Setup default mock for FileWaitUtil (file available immediately)
+    vi.mocked(FileWaitUtil.waitForFile).mockResolvedValue(undefined);
+
     // Setup default mocks for PDFDocument
     vi.mocked(fs.readFile).mockResolvedValue(Buffer.from('mock-pdf-bytes'));
     vi.mocked(PDFDocument.load).mockResolvedValue({
@@ -191,8 +205,10 @@ describe('PDFSplitter', () => {
         page_range: '',
       };
 
-      // Mock fs.readFile to throw file not found error
-      vi.mocked(fs.readFile).mockRejectedValue(new Error('ENOENT: no such file'));
+      // Mock FileWaitUtil to reject (file not found)
+      vi.mocked(FileWaitUtil.waitForFile).mockRejectedValue(
+        new Error('PDF file not found: missing.pdf. The file may have been moved or deleted.')
+      );
 
       await expect(splitter.split(task)).rejects.toThrow(/PDF file not found/);
     });

src/core/infrastructure/adapters/split/index.ts

@@ -1,5 +1,6 @@
 // Infrastructure layer exports - implementations with external dependencies
 export { ImagePathUtil } from './ImagePathUtil.js';
+export { FileWaitUtil } from './FileWaitUtil.js';
 export { PDFSplitter } from './PDFSplitter.js';
 export { ImageSplitter } from './ImageSplitter.js';
 export { SplitterFactory } from './SplitterFactory.js';

src/main/ipc/__tests__/handlers.test.ts

@@ -134,7 +134,6 @@ vi.mock('../../../shared/ipc/channels.js', () => ({
       DOWNLOAD_MARKDOWN: 'file:downloadMarkdown',
       SELECT_DIALOG: 'file:selectDialog',
       UPLOAD: 'file:upload',
-      UPLOAD_MULTIPLE: 'file:uploadMultiple',
       UPLOAD_FILE_CONTENT: 'file:uploadFileContent',
     },
     COMPLETION: {
@@ -153,7 +152,10 @@ vi.mock('fs', () => ({
     existsSync: vi.fn(() => true),
     mkdirSync: vi.fn(),
     copyFileSync: vi.fn(),
-    statSync: vi.fn(() => ({ size: 1024 }))
+    statSync: vi.fn(() => ({ size: 1024 })),
+    writeFileSync: vi.fn(),
+    accessSync: vi.fn(),
+    constants: { W_OK: 2 }
   }
 }))
 

src/main/ipc/handlers/__tests__/file.handler.test.ts

@@ -19,7 +19,9 @@ const mockFs = {
   mkdirSync: vi.fn(),
   copyFileSync: vi.fn(),
   statSync: vi.fn(),
-  writeFileSync: vi.fn()
+  writeFileSync: vi.fn(),
+  accessSync: vi.fn(),
+  constants: { W_OK: 2 }
 }
 
 const mockPath = {
@@ -66,7 +68,6 @@ vi.mock('../../../../shared/ipc/channels.js', () => ({
       DOWNLOAD_MARKDOWN: 'file:downloadMarkdown',
       SELECT_DIALOG: 'file:selectDialog',
       UPLOAD: 'file:upload',
-      UPLOAD_MULTIPLE: 'file:uploadMultiple',
       UPLOAD_FILE_CONTENT: 'file:uploadFileContent'
     }
   }
@@ -327,52 +328,6 @@ describe('File Handler', () => {
     })
   })
 
-  describe('file:uploadMultiple', () => {
-    it('should upload multiple files successfully', async () => {
-      mockFs.existsSync.mockReturnValue(true)
-
-      const handler = handlers.get('file:uploadMultiple')
-      const result = await handler!({}, 'task-123', ['/file1.pdf', '/file2.pdf'])
-
-      expect(result.success).toBe(true)
-      expect(result.data.files).toHaveLength(2)
-      expect(mockFs.copyFileSync).toHaveBeenCalledTimes(2)
-    })
-
-    it('should return error when taskId is missing', async () => {
-      const handler = handlers.get('file:uploadMultiple')
-      const result = await handler!({}, '', ['/file.pdf'])
-
-      expect(result).toEqual({
-        success: false,
-        error: 'Task ID and file path list are required'
-      })
-    })
-
-    it('should return error when filePaths is empty', async () => {
-      const handler = handlers.get('file:uploadMultiple')
-      const result = await handler!({}, 'task-1', [])
-
-      expect(result).toEqual({
-        success: false,
-        error: 'Task ID and file path list are required'
-      })
-    })
-
-    it('should skip non-existent files', async () => {
-      mockFs.existsSync
-        .mockReturnValueOnce(true)  // file1 exists
-        .mockReturnValueOnce(true)  // upload dir check
-        .mockReturnValueOnce(false) // file2 doesn't exist
-
-      const handler = handlers.get('file:uploadMultiple')
-      const result = await handler!({}, 'task-1', ['/file1.pdf', '/non-existent.pdf'])
-
-      expect(result.success).toBe(true)
-      expect(result.data.files).toHaveLength(1)
-    })
-  })
-
   describe('file:uploadFileContent', () => {
     it('should save file content successfully', async () => {
       const fileBuffer = new ArrayBuffer(8)