feat(思维导图助手)：思维导图助手过程2

mineru/cli/fast_api.py

@@ -12,6 +12,9 @@ import click
 import zipfile
 from pathlib import Path
 import glob
+
+os.environ.setdefault("PYTORCH_CUDA_ALLOC_CONF", "expandable_segments:True")
+
 from fastapi import Depends, FastAPI, HTTPException, UploadFile, File, Form, APIRouter, Header
 from fastapi.middleware.gzip import GZipMiddleware
 from fastapi.middleware.cors import CORSMiddleware
@@ -25,7 +28,9 @@ from base64 import b64encode
 # MinerU 内部导入
 from mineru.cli.common import aio_do_parse, read_fn, pdf_suffixes, image_suffixes, word_suffixes
 from mineru.utils.cli_parser import arg_parse
+from mineru.utils.config_reader import get_device
 from mineru.utils.guess_suffix_or_lang import guess_suffix_by_path
+from mineru.utils.model_utils import clean_memory
 from mineru.version import __version__
 
 # --- 日志配置 ---
@@ -89,6 +94,22 @@ def _update_task_progress(task_id: Optional[str], progress: int, stage: str):
         _store_task_progress(task_id, state)
 
 
+def _cleanup_runtime_memory():
+    """Release transient accelerator caches after each API parse request."""
+    try:
+        clean_memory(get_device())
+    except Exception as exc:
+        logger.warning(f"Failed to clean runtime memory: {exc}")
+
+
+def _format_parse_error(exc: Exception) -> str:
+    message = str(exc)
+    if "CUDA out of memory" in message or exc.__class__.__name__ in ("OutOfMemoryError", "RuntimeError"):
+        if "out of memory" in message.lower():
+            return "GPU显存不足，已尝试清理缓存。请减少最大页数、关闭公式/表格识别，或稍后重试。"
+    return f"Internal Error: {message}"
+
+
 class ProgressTracker:
     def __init__(self):
         self.progress = 0
@@ -467,6 +488,7 @@ async def parse_pdf(
         completed_state = _get_task_progress(task_id) or {}
         completed_state["status"] = "completed"
         _store_task_progress(task_id, completed_state)
+        _cleanup_runtime_memory()
 
         # 清理日志捕获和 stderr 捕获
         stderr_capture.stop()
@@ -531,9 +553,10 @@ async def parse_pdf(
             pass
         failed_state = _get_task_progress(task_id) or {}
         failed_state["status"] = "failed"
-        failed_state["error"] = str(e)
+        failed_state["error"] = _format_parse_error(e)
         _store_task_progress(task_id, failed_state)
-        return JSONResponse(status_code=500, content={"error": f"Internal Error: {str(e)}"})
+        _cleanup_runtime_memory()
+        return JSONResponse(status_code=500, content={"error": _format_parse_error(e)})
 
 
 # --- FastAPI 核心应用 ---

web_ui/src/components/MindMapRenderer.vue

@@ -16,9 +16,12 @@
         </el-button>
         <template #dropdown>
           <el-dropdown-menu>
-            <el-dropdown-item command="svg">SVG 格式</el-dropdown-item>
+            <el-dropdown-item command="full-svg">全部导图 SVG</el-dropdown-item>
-            <el-dropdown-item command="png">PNG 格式</el-dropdown-item>
+            <el-dropdown-item command="full-png">全部导图 PNG</el-dropdown-item>
-            <el-dropdown-item command="jpeg">JPEG 格式</el-dropdown-item>
+            <el-dropdown-item command="full-jpeg">全部导图 JPEG</el-dropdown-item>
+            <el-dropdown-item divided command="viewport-svg">当前窗口 SVG</el-dropdown-item>
+            <el-dropdown-item command="viewport-png">当前窗口 PNG</el-dropdown-item>
+            <el-dropdown-item command="viewport-jpeg">当前窗口 JPEG</el-dropdown-item>
           </el-dropdown-menu>
         </template>
       </el-dropdown>
@@ -176,14 +179,30 @@ function downloadBlob(blob: Blob, fileName: string) {
   URL.revokeObjectURL(url)
 }
 
-function createExportSvg() {
+type ExportFormat = 'svg' | 'png' | 'jpeg'
+type ExportScope = 'full' | 'viewport'
+
+function getViewportSize(svg: SVGElement) {
+  const rect = svg.getBoundingClientRect()
+  return {
+    width: Math.ceil(Math.max(rect.width, 320)),
+    height: Math.ceil(Math.max(rect.height, 240))
+  }
+}
+
+function cleanExportSvg(svg: SVGElement) {
+  if (!svg.getAttribute('xmlns')) {
+    svg.setAttribute('xmlns', 'http://www.w3.org/2000/svg')
+  }
+  svg.querySelectorAll('[style*="cursor"]').forEach((node) => node.removeAttribute('style'))
+}
+
+function createFullExportSvg() {
   const svg = svgRef.value
   if (!svg) return null
 
   const svgCopy = svg.cloneNode(true) as SVGElement
-  if (!svgCopy.getAttribute('xmlns')) {
+  cleanExportSvg(svgCopy)
-    svgCopy.setAttribute('xmlns', 'http://www.w3.org/2000/svg')
-  }
 
   const contentGroup = svg.querySelector('g')
   const bbox = contentGroup
@@ -195,10 +214,30 @@ function createExportSvg() {
   const height = Math.ceil(Math.max(bbox.height + padding * 2, 240))
   const viewBox = `${Math.floor(bbox.x - padding)} ${Math.floor(bbox.y - padding)} ${width} ${height}`
 
+  const viewportGroupCopy = svgCopy.querySelector('g')
+  viewportGroupCopy?.removeAttribute('transform')
   svgCopy.setAttribute('viewBox', viewBox)
   svgCopy.setAttribute('width', String(width))
   svgCopy.setAttribute('height', String(height))
-  svgCopy.querySelectorAll('[style*="cursor"]').forEach((node) => node.removeAttribute('style'))
+
+  return {
+    data: new XMLSerializer().serializeToString(svgCopy),
+    width,
+    height
+  }
+}
+
+function createViewportExportSvg() {
+  const svg = svgRef.value
+  if (!svg) return null
+
+  const svgCopy = svg.cloneNode(true) as SVGElement
+  cleanExportSvg(svgCopy)
+
+  const { width, height } = getViewportSize(svg)
+  svgCopy.setAttribute('width', String(width))
+  svgCopy.setAttribute('height', String(height))
+  svgCopy.setAttribute('viewBox', svg.getAttribute('viewBox') || `0 0 ${width} ${height}`)
 
   return {
     data: new XMLSerializer().serializeToString(svgCopy),
@@ -208,17 +247,18 @@ function createExportSvg() {
 }
 
 // 下载思维导图
-const downloadMindMap = async (format: 'svg' | 'png' | 'jpeg' = 'svg') => {
+const downloadMindMap = async (format: ExportFormat = 'svg', scope: ExportScope = 'full') => {
-  const exportSvg = createExportSvg()
+  const exportSvg = scope === 'viewport' ? createViewportExportSvg() : createFullExportSvg()
   if (!exportSvg) return
 
   const time = new Date().getTime()
+  const scopeName = scope === 'viewport' ? 'viewport' : 'full'
   if (format === 'svg') {
-    downloadBlob(new Blob([exportSvg.data], { type: 'image/svg+xml;charset=utf-8' }), `mindmap_${time}.svg`)
+    downloadBlob(new Blob([exportSvg.data], { type: 'image/svg+xml;charset=utf-8' }), `mindmap_${scopeName}_${time}.svg`)
     return
   }
 
-  const maxCanvasPixels = 16_000_000
+  const maxCanvasPixels = scope === 'viewport' ? 16_000_000 : 64_000_000
   const scaleFactor = Math.min(3, Math.max(1, Math.sqrt(maxCanvasPixels / (exportSvg.width * exportSvg.height))))
   const canvas = document.createElement('canvas')
   const ctx = canvas.getContext('2d')
@@ -236,7 +276,7 @@ const downloadMindMap = async (format: 'svg' | 'png' | 'jpeg' = 'svg') => {
     const mimeType = format === 'jpeg' ? 'image/jpeg' : 'image/png'
     canvas.toBlob((blob) => {
       if (!blob) return
-      downloadBlob(blob, `mindmap_${time}.${format === 'jpeg' ? 'jpg' : 'png'}`)
+      downloadBlob(blob, `mindmap_${scopeName}_${time}.${format === 'jpeg' ? 'jpg' : 'png'}`)
     }, mimeType, 0.96)
   }
   img.onerror = () => ElMessage.error('导出图片失败')
@@ -245,8 +285,9 @@ const downloadMindMap = async (format: 'svg' | 'png' | 'jpeg' = 'svg') => {
 
 // 处理下载命令
 const handleDownload = (command: string) => {
-  if (command === 'svg' || command === 'png' || command === 'jpeg') {
+  const [scope, format] = command.split('-') as [ExportScope, ExportFormat]
-    downloadMindMap(command)
+  if ((scope === 'full' || scope === 'viewport') && (format === 'svg' || format === 'png' || format === 'jpeg')) {
+    downloadMindMap(format, scope)
   }
 }
 

web_ui/src/composables/useDocumentProcessor.ts

@@ -1,4 +1,4 @@
-import { ref, reactive } from 'vue'
+import { ref, reactive, watch } from 'vue'
 import type { Ref } from 'vue'
 import { documentApi, type ParseParams } from '@/api/document'
 import { convertWordToPdf, isWordFile } from '@/utils/wordToPdf'
@@ -26,13 +26,24 @@ export interface ProcessResult {
   downloadUrl?: string
 }
 
+const CONFIG_STORAGE_KEY = 'mineru.documentProcessor.config'
+
+function loadCachedConfig(): Partial<DocumentConfig> {
+  try {
+    const raw = window.localStorage.getItem(CONFIG_STORAGE_KEY)
+    return raw ? JSON.parse(raw) : {}
+  } catch {
+    return {}
+  }
+}
+
 export function useDocumentProcessor() {
   // 文件相关
   const uploadedFiles: Ref<File[]> = ref([])
   const isUploading = ref(false)
   
   // 配置相关
-  const config = reactive<DocumentConfig>({
+  const defaultConfig: DocumentConfig = {
     maxPages: 1000,
     backend: 'hybrid-auto-engine',
     serverUrl: 'http://localhost:30000',
@@ -40,8 +51,24 @@ export function useDocumentProcessor() {
     formulaEnable: true,
     language: 'ch',
     forceOcr: false
+  }
+  const config = reactive<DocumentConfig>({
+    ...defaultConfig,
+    ...loadCachedConfig()
   })
 
+  watch(
+    config,
+    (value) => {
+      try {
+        window.localStorage.setItem(CONFIG_STORAGE_KEY, JSON.stringify(value))
+      } catch {
+        // 浏览器禁用本地存储时不影响当前页面使用。
+      }
+    },
+    { deep: true }
+  )
+  
   // 结果相关
   const results = ref<ProcessResult | null>(null)
   const isProcessing = ref(false)
@@ -82,9 +109,12 @@ export function useDocumentProcessor() {
     if (!files || files.length === 0) return
     
     const validFiles: File[] = []
+    const file = files[0]
+    uploadedFiles.value = []
+    if (files.length > 1) {
+      error.value = '一次只能选择一个文件，已使用第一个文件'
+    }
     
-    for (let i = 0; i < files.length; i++) {
-      const file = files[i]
     const fileType = file.type
     const fileName = file.name.toLowerCase()
     
@@ -100,14 +130,14 @@ export function useDocumentProcessor() {
     if (!isImage && !isPdf && !isWord) {
       error.value = '不支持的文件类型'
       console.log('Unsupported file type:', fileName, fileType)
-        continue
+      return
     }
     
     // 验证文件大小 (100MB)
     if (file.size > 100 * 1024 * 1024) {
       error.value = '文件大小超出限制'
       console.log('File too large:', fileName, file.size)
-        continue
+      return
     }
     
     // 如果是 Word 文档，转换为 PDF
@@ -123,7 +153,7 @@ export function useDocumentProcessor() {
       } catch (err) {
         error.value = 'Word 转换为 PDF 失败: ' + (err as Error).message
         console.error('Conversion failed:', (err as Error).message)
-          continue
+        return
       } finally {
         isUploading.value = false
       }
@@ -131,7 +161,6 @@ export function useDocumentProcessor() {
       validFiles.push(file)
       console.log('Adding file directly:', fileName)
     }
-    }
     
     uploadedFiles.value = validFiles
     console.log('Final uploaded files:', validFiles.map(f => f.name))

web_ui/src/utils/mindmapMarkdown.ts

@@ -1,167 +1,156 @@
-const MAX_NODE_TEXT_LENGTH = 72
+import MarkdownIt from 'markdown-it'
-const MAX_PARAGRAPH_SUMMARY_LENGTH = 90
+import type Token from 'markdown-it/lib/token.mjs'
-const MAX_CHILDREN_PER_HEADING = 18
+
 const ROOT_TITLE = '文档思维导图'
+const MAX_HEADING_LEVEL = 6
 
-type BlockType = 'paragraph' | 'list' | 'table' | 'code' | 'math' | 'image'
+const md = new MarkdownIt({
+  html: true,
+  linkify: true,
+  typographer: true,
+  breaks: true
+})
 
-interface HeadingState {
+function normalizeNodeText(text: string) {
-  level: number
+  return text
-  childCount: number
+    .replace(/\r?\n/g, ' ')
+    .replace(/\s+/g, ' ')
+    .trim()
 }
 
-function normalizeWhitespace(text: string) {
+function clampHeadingLevel(level: number) {
-  return text.replace(/\s+/g, ' ').trim()
+  return Math.min(Math.max(level, 1), MAX_HEADING_LEVEL)
 }
 
-function stripMarkdownInline(text: string) {
+function pushHeading(result: string[], level: number, text: string) {
-  return normalizeWhitespace(text)
+  const normalized = normalizeNodeText(text)
-    .replace(/!\[([^\]]*)\]\([^)]+\)/g, '$1')
+  if (!normalized) return
-    .replace(/\[([^\]]+)\]\([^)]+\)/g, '$1')
+  result.push(`${'#'.repeat(clampHeadingLevel(level))} ${normalized}`)
-    .replace(/[*_`~>#]/g, '')
 }
 
-function truncateText(text: string, maxLength = MAX_NODE_TEXT_LENGTH) {
+function getHeadingLevel(token: Token) {
-  const normalized = normalizeWhitespace(text)
+  const tagLevel = Number(token.tag.replace(/^h/i, ''))
-  if (normalized.length <= maxLength) return normalized
+  return Number.isFinite(tagLevel) && tagLevel > 0 ? tagLevel : 1
-  return `${normalized.slice(0, maxLength - 1)}...`
 }
 
-function summarizeParagraph(text: string) {
+function getNextInlineContent(tokens: Token[], index: number) {
-  const cleaned = stripMarkdownInline(text)
+  const next = tokens[index + 1]
-  const sentence = cleaned.match(/^(.+?[。！？!?；;：:]|\S.{20,}?[,，])/)
+  return next?.type === 'inline' ? next.content : ''
-  return truncateText(sentence?.[1] || cleaned, MAX_PARAGRAPH_SUMMARY_LENGTH)
 }
 
-function isHeading(line: string) {
+function getFenceContent(token: Token) {
-  return /^#{1,6}\s+/.test(line.trim())
+  const info = normalizeNodeText(token.info || '')
+  const content = token.content.trim()
+  if (!content) return info ? `代码块 ${info}` : '代码块'
+  return info ? `代码块 ${info}: ${content}` : `代码块: ${content}`
 }
 
-function getHeadingLevel(line: string) {
+function collectTableRows(tokens: Token[], startIndex: number) {
-  return line.trim().match(/^#{1,6}/)?.[0].length || 0
+  const rows: string[][] = []
-}
+  let currentRow: string[] | null = null
+  let endIndex = startIndex
 
-function getHeadingText(line: string) {
+  for (let i = startIndex + 1; i < tokens.length; i += 1) {
-  return stripMarkdownInline(line.trim().replace(/^#{1,6}\s+/, ''))
+    const token = tokens[i]
-}
+    endIndex = i
 
-function getListText(line: string) {
+    if (token.type === 'table_close') break
-  return stripMarkdownInline(line.trim().replace(/^[-*+]\s+|^\d+[.)、]\s+/, ''))
+    if (token.type === 'tr_open') {
-}
+      currentRow = []
-
+      continue
-function countHeadingChildren(stack: HeadingState[], level: number) {
+    }
-  while (stack.length && stack[stack.length - 1].level >= level) {
+    if (token.type === 'tr_close') {
-    stack.pop()
+      if (currentRow && currentRow.some((cell) => cell.trim())) {
+        rows.push(currentRow)
+      }
+      currentRow = null
+      continue
+    }
+    if ((token.type === 'th_open' || token.type === 'td_open') && currentRow) {
+      currentRow.push(getNextInlineContent(tokens, i))
+    }
   }
 
-  const parent = stack[stack.length - 1]
+  return { rows, endIndex }
-  if (!parent) return true
-  parent.childCount += 1
-  return parent.childCount <= MAX_CHILDREN_PER_HEADING
-}
-
-function pushBlock(result: string[], stack: HeadingState[], blockType: BlockType, text: string) {
-  const cleaned = text.trim()
-  if (!cleaned) return
-
-  const parentLevel = stack.length ? stack[stack.length - 1].level : 1
-  const level = Math.min(parentLevel + 1, 6)
-  if (!countHeadingChildren(stack, level)) return
-
-  const prefixMap: Record<BlockType, string> = {
-    paragraph: '摘要',
-    list: '要点',
-    table: '表格',
-    code: '代码',
-    math: '公式',
-    image: '图片'
-  }
-
-  result.push(`${'#'.repeat(level)} ${prefixMap[blockType]}：${cleaned}`)
 }
 
 export function buildMindmapMarkdown(markdown: string) {
-  const lines = markdown.split(/\r?\n/)
+  if (!markdown.trim()) return ''
+
+  const tokens = md.parse(markdown, {})
   const result: string[] = [`# ${ROOT_TITLE}`]
-  const stack: HeadingState[] = [{ level: 1, childCount: 0 }]
+  let currentHeadingLevel = 1
-  let paragraphBuffer: string[] = []
+  let listDepth = 0
-  let inCodeBlock = false
-  let codeBlockTitle = ''
 
-  const flushParagraph = () => {
+  for (let i = 0; i < tokens.length; i += 1) {
-    if (paragraphBuffer.length === 0) return
+    const token = tokens[i]
-    const text = summarizeParagraph(paragraphBuffer.join(' '))
-    pushBlock(result, stack, 'paragraph', text)
-    paragraphBuffer = []
-  }
 
-  for (const line of lines) {
+    if (token.type === 'heading_open') {
-    const trimmed = line.trim()
+      currentHeadingLevel = clampHeadingLevel(getHeadingLevel(token) + 1)
-
+      pushHeading(result, currentHeadingLevel, getNextInlineContent(tokens, i) || '未命名章节')
-    if (/^```/.test(trimmed)) {
+      i += 2
-      if (inCodeBlock) {
-        pushBlock(result, stack, 'code', codeBlockTitle || '代码块')
-        codeBlockTitle = ''
-      } else {
-        flushParagraph()
-        codeBlockTitle = trimmed.replace(/^```/, '').trim()
-      }
-      inCodeBlock = !inCodeBlock
       continue
     }
 
-    if (inCodeBlock) continue
+    if (token.type === 'bullet_list_open' || token.type === 'ordered_list_open') {
-
+      listDepth += 1
-    if (!trimmed) {
-      flushParagraph()
       continue
     }
 
-    if (isHeading(trimmed)) {
+    if (token.type === 'bullet_list_close' || token.type === 'ordered_list_close') {
-      flushParagraph()
+      listDepth = Math.max(0, listDepth - 1)
-      const rawLevel = getHeadingLevel(trimmed)
-      const level = Math.min(rawLevel + 1, 6)
-      while (stack.length && stack[stack.length - 1].level >= level) {
-        stack.pop()
-      }
-      result.push(`${'#'.repeat(level)} ${truncateText(getHeadingText(trimmed)) || '未命名章节'}`)
-      stack.push({ level, childCount: 0 })
       continue
     }
 
-    if (/^\|.+\|$/.test(trimmed)) {
+    if (token.type === 'paragraph_open') {
-      flushParagraph()
+      const level = currentHeadingLevel + Math.max(listDepth, 1)
-      pushBlock(result, stack, 'table', '表格内容')
+      pushHeading(result, level, getNextInlineContent(tokens, i))
+      i += 2
       continue
     }
 
-    if (/^!\[[^\]]*]\([^)]+\)/.test(trimmed)) {
+    if (token.type === 'fence' || token.type === 'code_block') {
-      flushParagraph()
+      pushHeading(result, currentHeadingLevel + 1, getFenceContent(token))
-      pushBlock(result, stack, 'image', stripMarkdownInline(trimmed) || '图片')
       continue
     }
 
-    if (/^\$\$.*\$\$$/.test(trimmed) || /^\$[^$].*\$$/.test(trimmed)) {
+    if (token.type === 'html_block') {
-      flushParagraph()
+      pushHeading(result, currentHeadingLevel + 1, token.content)
-      pushBlock(result, stack, 'math', truncateText(trimmed, 80))
       continue
     }
 
-    if (/^[-*+]\s+|^\d+[.)、]\s+/.test(trimmed)) {
+    if (token.type === 'blockquote_open') {
-      flushParagraph()
+      pushHeading(result, currentHeadingLevel + 1, '引用')
-      pushBlock(result, stack, 'list', truncateText(getListText(trimmed)))
+      currentHeadingLevel = clampHeadingLevel(currentHeadingLevel + 1)
       continue
     }
 
-    paragraphBuffer.push(trimmed)
+    if (token.type === 'blockquote_close') {
+      currentHeadingLevel = Math.max(1, currentHeadingLevel - 1)
+      continue
+    }
+
+    if (token.type === 'hr') {
+      pushHeading(result, currentHeadingLevel + 1, '---')
+      continue
+    }
+
+    if (token.type === 'table_open') {
+      const tableLevel = currentHeadingLevel + 1
+      const { rows, endIndex } = collectTableRows(tokens, i)
+      pushHeading(result, tableLevel, '表格')
+      rows.forEach((row) => {
+        pushHeading(result, tableLevel + 1, row.map(normalizeNodeText).join(' | '))
+      })
+      i = endIndex
+    }
   }
 
-  flushParagraph()
   return result.join('\n')
 }
 
 export function replaceFirstMindmapText(markdown: string, oldText: string, newText: string) {
-  const normalizedOld = oldText.replace(/^(摘要|要点|表格|代码|公式|图片)：/, '').trim()
+  const normalizedOld = oldText.replace(/^(引用|表格|代码块)(\s|:|：)?/, '').trim()
   if (!normalizedOld || !newText.trim()) return markdown
 
   const escaped = normalizedOld.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')
@@ -171,7 +160,7 @@ export function replaceFirstMindmapText(markdown: string, oldText: string, newTe
   }
 
   const lines = markdown.split(/\r?\n/)
-  const targetLineIndex = lines.findIndex((line) => stripMarkdownInline(line).includes(normalizedOld))
+  const targetLineIndex = lines.findIndex((line) => normalizeNodeText(line).includes(normalizedOld))
   if (targetLineIndex >= 0) {
     lines[targetLineIndex] = lines[targetLineIndex].replace(normalizedOld, newText.trim())
     return lines.join('\n')

web_ui/src/utils/request.ts

@@ -28,6 +28,12 @@ request.interceptors.response.use(
   (error) => {
     // 统一错误处理
     if (error.response) {
+      const serverMessage = error.response.data?.error || error.response.data?.detail
+      if (serverMessage) {
+        error.message = serverMessage
+        return Promise.reject(error)
+      }
+
       switch (error.response.status) {
         case 400:
           error.message = '请求参数错误'

web_ui/src/views/DocumentProcessor.vue

@@ -20,7 +20,7 @@
           <div class="upload-content" v-show="!isUploadAreaCollapsed">
             <el-icon class="upload-icon"><Folder /></el-icon>
             <div class="upload-text">文件导入</div>
-            <div class="upload-hint">支持 PDF、Word、PNG 格式文件，可转换为 Markdown 和思维导图，也可手动粘贴 Markdown 源码</div>
+            <div class="upload-hint">支持 PDF、Word、PNG 格式单个文件，可转换为 Markdown 和思维导图，也可手动粘贴 Markdown 源码</div>
           </div>
 
           <div class="uploaded-files">
@@ -174,7 +174,6 @@
     <input
       ref="fileInput"
       type="file"
-      multiple
       accept=".pdf,.doc,.docx,.png"
       style="position: absolute; width: 0; height: 0; overflow: hidden;"
       @change="handleFileInputChange"
@@ -219,7 +218,7 @@
 </template>
 
 <script setup lang="ts">
-import { computed, onMounted, onUnmounted, ref } from 'vue'
+import { computed, onMounted, onUnmounted, ref, watch } from 'vue'
 import { Delete, Document, Folder, Close, Loading, ArrowDown } from '@element-plus/icons-vue'
 import { ElMessage } from 'element-plus'
 import ConfigPanel from '@/components/ConfigPanel.vue'
@@ -230,6 +229,36 @@ import { markdownToAstString } from '@/utils/markdownAst'
 import { buildMindmapMarkdown, replaceFirstMindmapText } from '@/utils/mindmapMarkdown'
 import { createEmptyReplacementRule, renderMarkdownTemplate, type ReplacementRule } from '@/utils/markdownTemplate'
 
+const MARKDOWN_RENDER_MODE_KEY = 'mineru.documentProcessor.markdownRenderMode'
+const SOURCE_VIEW_MODE_KEY = 'mineru.documentProcessor.sourceViewMode'
+
+function loadStoredValue<T>(key: string, fallback: T, validate?: (value: unknown) => value is T): T {
+  try {
+    const raw = window.localStorage.getItem(key)
+    if (!raw) return fallback
+    const value = JSON.parse(raw)
+    return validate ? (validate(value) ? value : fallback) : value
+  } catch {
+    return fallback
+  }
+}
+
+function storeValue(key: string, value: unknown) {
+  try {
+    window.localStorage.setItem(key, JSON.stringify(value))
+  } catch {
+    // 浏览器禁用本地存储时不影响当前页面使用。
+  }
+}
+
+function isMarkdownRenderMode(value: unknown): value is 'markdown' | 'html' | 'pdf' | 'richtext' {
+  return value === 'markdown' || value === 'html' || value === 'pdf' || value === 'richtext'
+}
+
+function isSourceViewMode(value: unknown): value is 'markdown' | 'ast' {
+  return value === 'markdown' || value === 'ast'
+}
+
 const {
   uploadedFiles,
   config,
@@ -253,14 +282,21 @@ const fileInput = ref<HTMLInputElement | null>(null)
 const isDragging = ref(false)
 const activeTab = ref('markdown')
 const isUploadAreaCollapsed = ref(false)
-const markdownRenderMode = ref<'markdown' | 'html' | 'pdf' | 'richtext'>('markdown')
+const markdownRenderMode = ref<'markdown' | 'html' | 'pdf' | 'richtext'>(
+  loadStoredValue(MARKDOWN_RENDER_MODE_KEY, 'markdown', isMarkdownRenderMode)
+)
 const markdownCompatibilityFlavor = ref<'commonmark' | 'gfm'>('gfm')
-const sourceViewMode = ref<'markdown' | 'ast'>('markdown')
+const sourceViewMode = ref<'markdown' | 'ast'>(
+  loadStoredValue(SOURCE_VIEW_MODE_KEY, 'markdown', isSourceViewMode)
+)
 const showReplacementDialog = ref(false)
 const isMobileDialog = ref(false)
 const replacementRules = ref<ReplacementRule[]>([])
 const draftReplacementRules = ref<ReplacementRule[]>([])
 
+watch(markdownRenderMode, (value) => storeValue(MARKDOWN_RENDER_MODE_KEY, value))
+watch(sourceViewMode, (value) => storeValue(SOURCE_VIEW_MODE_KEY, value))
+
 const manualMarkdownContent = computed(() => results.value?.source || '')
 const templateRenderResult = computed(() => renderMarkdownTemplate(manualMarkdownContent.value, replacementRules.value))
 const renderedMarkdownContent = computed(() => templateRenderResult.value.markdown)
@@ -417,11 +453,6 @@ const triggerUpload = () => {
   fileInput.value?.click()
 }
 
-const resetReplacementConfig = () => {
-  replacementRules.value = []
-  draftReplacementRules.value = []
-}
-
 const handleFileInputChange = async (event: Event) => {
   const input = event.target as HTMLInputElement
   if (input.files) {
@@ -430,7 +461,6 @@ const handleFileInputChange = async (event: Event) => {
     if (uploadedFiles.value.length > 0) {
       isUploadAreaCollapsed.value = true
       initializeManualResult()
-      resetReplacementConfig()
       markdownRenderMode.value = 'markdown'
       sourceViewMode.value = 'markdown'
       activeTab.value = 'source'
@@ -447,7 +477,6 @@ const handleDrop = async (event: DragEvent) => {
     if (uploadedFiles.value.length > 0) {
       isUploadAreaCollapsed.value = true
       initializeManualResult()
-      resetReplacementConfig()
       markdownRenderMode.value = 'markdown'
       sourceViewMode.value = 'markdown'
       activeTab.value = 'source'
@@ -464,7 +493,6 @@ const removeFile = (index: number) => {
 
 const clearAllFiles = () => {
   clearAll()
-  resetReplacementConfig()
   isUploadAreaCollapsed.value = false
 }