Feat/pdf layout

server/.spec-workflow/user-templates/README.md

@@ -0,0 +1,64 @@
+# User Templates
+
+This directory allows you to create custom templates that override the default Spec Workflow templates.
+
+## How to Use Custom Templates
+
+1. **Create your custom template file** in this directory with the exact same name as the default template you want to override:
+   - `requirements-template.md` - Override requirements document template
+   - `design-template.md` - Override design document template  
+   - `tasks-template.md` - Override tasks document template
+   - `product-template.md` - Override product steering template
+   - `tech-template.md` - Override tech steering template
+   - `structure-template.md` - Override structure steering template
+
+2. **Template Loading Priority**:
+   - The system first checks this `user-templates/` directory
+   - If a matching template is found here, it will be used
+   - Otherwise, the default template from `templates/` will be used
+
+## Example Custom Template
+
+To create a custom requirements template:
+
+1. Create a file named `requirements-template.md` in this directory
+2. Add your custom structure, for example:
+
+```markdown
+# Requirements Document
+
+## Executive Summary
+[Your custom section]
+
+## Business Requirements
+[Your custom structure]
+
+## Technical Requirements
+[Your custom fields]
+
+## Custom Sections
+[Add any sections specific to your workflow]
+```
+
+## Template Variables
+
+Templates can include placeholders that will be replaced when documents are created:
+- `{{projectName}}` - The name of your project
+- `{{featureName}}` - The name of the feature being specified
+- `{{date}}` - The current date
+- `{{author}}` - The document author
+
+## Best Practices
+
+1. **Start from defaults**: Copy a default template from `../templates/` as a starting point
+2. **Keep structure consistent**: Maintain similar section headers for tool compatibility
+3. **Document changes**: Add comments explaining why sections were added/modified
+4. **Version control**: Track your custom templates in version control
+5. **Test thoroughly**: Ensure custom templates work with the spec workflow tools
+
+## Notes
+
+- Custom templates are project-specific and not included in the package distribution
+- The `templates/` directory contains the default templates which are updated with each version
+- Your custom templates in this directory are preserved during updates
+- If a custom template has errors, the system will fall back to the default template

server/integrations/dataSource/index.ts

@@ -32,7 +32,7 @@ import {
 } from "./errors"
 import { describeImageWithllm } from "@/lib/describeImageWithllm"
 import { promises as fsPromises } from "fs"
-import { extractTextAndImagesWithChunksFromPDF } from "@/pdfChunks"
+import { extractTextAndImagesWithChunksFromPDFviaGemini } from "@/lib/chunkPdfWithGemini"
 import { extractTextAndImagesWithChunksFromDocx } from "@/docxChunks"
 import { extractTextAndImagesWithChunksFromPptx } from "@/pptChunks"
 import imageType from "image-type"
@@ -208,7 +208,7 @@ const processPdfContent = async (
   try {
     const docId = `dsf-${createId()}`
     const { text_chunks, image_chunks, text_chunk_pos, image_chunk_pos } =
-      await extractTextAndImagesWithChunksFromPDF(pdfBuffer, docId, true)
+      await extractTextAndImagesWithChunksFromPDFviaGemini(pdfBuffer, docId)
     if (text_chunks.length === 0 && image_chunks.length === 0) {
       throw new ContentExtractionError(
         "No chunks generated from PDF content",

server/integrations/google/worker-utils.ts

@@ -19,7 +19,7 @@ import {
 import * as XLSX from "xlsx"
 import { extractTextAndImagesWithChunksFromDocx } from "@/docxChunks"
 import { extractTextAndImagesWithChunksFromPptx } from "@/pptChunks"
-import { extractTextAndImagesWithChunksFromPDF } from "@/pdfChunks"
+import { extractTextAndImagesWithChunksFromPDFviaGemini } from "@/lib/chunkPdfWithGemini"
 
 const Logger = getLogger(Subsystem.Integrations).child({ module: "google" })
 
@@ -49,10 +49,9 @@ const processPdfFile = async (
 ): Promise<string[]> => {
   try {
     // Handle non-spreadsheet files as before
-    const pdfResult = await extractTextAndImagesWithChunksFromPDF(
+    const pdfResult = await extractTextAndImagesWithChunksFromPDFviaGemini(
       pdfBuffer,
       attachmentId,
-      false, // Don't extract images for email attachments
     )
     return pdfResult.text_chunks.filter((v) => v.trim())
   } catch (error) {

server/integrations/microsoft/attachment-utils.ts

@@ -17,7 +17,7 @@ import {
 import * as XLSX from "xlsx"
 import { extractTextAndImagesWithChunksFromDocx } from "@/docxChunks"
 import { extractTextAndImagesWithChunksFromPptx } from "@/pptChunks"
-import { extractTextAndImagesWithChunksFromPDF } from "@/pdfChunks"
+import { extractTextAndImagesWithChunksFromPDFviaGemini } from "@/lib/chunkPdfWithGemini"
 import { makeGraphApiCall, type MicrosoftGraphClient } from "./client"
 
 const Logger = getLogger(Subsystem.Integrations).child({
@@ -48,10 +48,9 @@ const processPdfFile = async (
   attachmentId: string,
 ): Promise<string[]> => {
   try {
-    const pdfResult = await extractTextAndImagesWithChunksFromPDF(
+    const pdfResult = await extractTextAndImagesWithChunksFromPDFviaGemini(
       pdfBuffer,
       attachmentId,
-      false, // Don't extract images for email attachments
     )
     return pdfResult.text_chunks.filter((v) => v.trim())
   } catch (error) {