feat: add image hash-based OCR caching with 100MB size limit

- Implement SHA-256 image hashing to cache OCR results and avoid re-processing identical images
- Add 100MB file size limit for image uploads with user-friendly error messages
- Clear ghost suggestions when uploading new images to prevent interference
- Optimize size limit calculation in copilot plugin to include OCR context
- Remove debug logging from production code
- Add image processing optimization plan document

BREAKING CHANGE: Image upload size limit is now enforced at 100MB (previously unlimited)

backend/prompt.py

@@ -46,7 +46,7 @@ Hard rules:
    Do NOT repeat text that already appears at the start of SUFFIX.
 3. Balanced length:
    Prefer concise but meaningful continuation, not ultra-short fragments.
-   Default target is 20-120 characters and 1-3 lines for plain prose.
+   Default target is 10-500 characters and 1-20 lines for plain prose.
    You may be longer when structure requires it (lists, tables, code blocks, math blocks).
 4. Avoid trivial output:
    Do not output only punctuation or filler such as ".", ",", ";", ":".
@@ -89,6 +89,3 @@ Now produce the insertion.
 Output:"""
 
     return prompt.strip()
-
-
-

plans/image-processing-plan.md

@@ -0,0 +1,79 @@
+# 图片处理优化计划
+
+## 需求概述
+1. 图片上传大小限制为100MB
+2. 为每个图片做哈希，相同哈希不重复调用OCR
+3. 上传图片时打断之前的ghost text
+
+## 需要修改的文件
+
+### 1. `src/utils/ocrCache.js` - 扩展OCR缓存模块
+
+**新增功能：**
+- 图片哈希缓存：`imageHashCache` Map，用于存储 `hash -> ocrText` 的映射
+- 哈希计算函数：使用 `crypto.subtle.digest('SHA-256', imageBytes)` 计算哈希
+- 哈希检查函数：在OCR前检查哈希是否已存在
+- 100MB大小限制常量
+
+```javascript
+// 新增
+export const IMAGE_SIZE_LIMIT = 100 * 1024 * 1024  // 100MB
+
+export async function calculateImageHash(imageBytes) {
+  const hashBuffer = await crypto.subtle.digest('SHA-256', imageBytes)
+  const hashArray = Array.from(new Uint8Array(hashBuffer))
+  return hashArray.map(b => b.toString(16).padStart(2, '0')).join('')
+}
+
+export function getOcrByHash(hash) {
+  return imageHashCache.get(hash) || ''
+}
+
+export function setOcrByHash(hash, text) {
+  imageHashCache.set(hash, text)
+}
+```
+
+### 2. `src/components/MilkdownEditor.vue` - 修改图片上传逻辑
+
+**修改点：**
+
+1. **`handleImageUpload` 函数 (约第392行)**
+   - 添加文件大小检查，超过100MB则提示错误
+   - 计算图片哈希，检查是否已存在OCR结果
+   - 上传图片前调用 `clearGhostSuggestion` 打断现有ghost text
+
+2. **`performOCR` 函数 (约第212行)**
+   - 接收哈希参数，OCR完成后存储到哈希缓存
+
+3. **Milkdown `onUpload` 回调 (约第267行)**
+   - 同样添加大小限制和哈希检查
+
+### 3. `src/plugins/copilotPlugin.ts` - 可能需要导出清除函数
+
+- 确保 `clearGhostSuggestion` 可以被外部调用（目前已导出）
+
+## 实现步骤
+
+```mermaid
+graph TD
+    A[用户上传图片] --> B{文件大小 <= 100MB?}
+    B -->|否| C[提示文件过大错误]
+    B -->|是| D[计算图片哈希]
+    D --> E{哈希已存在OCR结果?}
+    E -->|是| F[直接使用缓存的OCR结果]
+    E -->|否| G[调用OCR API]
+    G --> H[存储OCR结果到哈希缓存]
+    F --> I[打断现有ghost text]
+    H --> I
+    I --> J[插入图片到编辑器]
+```
+
+## 关键代码修改位置
+
+| 文件 | 函数/位置 | 修改内容 |
+|------|-----------|----------|
+| `src/utils/ocrCache.js` | 新增 | 添加哈希相关函数和常量 |
+| `src/components/MilkdownEditor.vue` | `handleImageUpload` | 添加大小检查、哈希检查、打断ghost text |
+| `src/components/MilkdownEditor.vue` | `performOCR` | 接收哈希参数 |
+| `src/components/MilkdownEditor.vue` | `onUpload` | Milkdown上传回调添加同样逻辑 |

src/components/MilkdownEditor.vue

@@ -108,8 +108,8 @@ import { editorViewCtx, serializerCtx } from '@milkdown/kit/core'
 import { Selection } from '@milkdown/prose/state'
 import { copilotPlugin, copilotConfigCtx, copilotGhostMark, setCopilotEnabled, COPILOT_PLUGIN_KEY, SIZE_LIMIT, checkSizeLimit, clearGhostSuggestion } from '../plugins/copilotPlugin'
 import { fetchSuggestion } from '../utils/api.js'
-import { DEBUG, OCR_URL } from '../utils/config.js'
+import { OCR_URL } from '../utils/config.js'
-import { setOcrCache, clearOcrCache, clearAllOcrCache } from '../utils/ocrCache.js'
+import { setOcrCache, clearOcrCache, clearAllOcrCache, IMAGE_SIZE_LIMIT, calculateImageHash, getOcrByHash, setOcrByHash } from '../utils/ocrCache.js'
 
 const emit = defineEmits(['update:markdown'])
 
@@ -130,7 +130,6 @@ const aiButtonLabel = computed(() => {
 
 let crepe = null
 let markdownSyncTimer = null
-let debugLogTimer = null
 const objectUrls = new Set()
 const IMAGE_NODE_TYPES = new Set(['image', 'image-block', 'imageBlock'])
 
@@ -201,67 +200,24 @@ const scheduleMarkdownSync = () => {
       const markdown = await crepe.getMarkdown()
       emit('update:markdown', markdown)
     } catch (e) {
-      if (DEBUG) console.error('[Markdown] Sync failed:', e)
+      // sync error, ignore
     }
   }, 120)
 }
 
-const logDebugInfo = async () => {
-  if (!crepe) return
-  try {
-    const markdown = await crepe.getMarkdown()
-    crepe.editor.action((ctx) => {
-      const view = ctx.get(editorViewCtx)
-      const schema = view.state.schema
-      const { from, to } = view.state.selection
-      const serializer = ctx.get(serializerCtx)
-      let prefixMarkdown = '', suffixMarkdown = ''
-      
-      try {
-        // Prefix: 使用 slice 创建文档节点
-        const prefixSlice = view.state.doc.slice(0, from)
-        if (prefixSlice.content.size > 0) {
-          const prefixDoc = schema.topNodeType.createAndFill(undefined, prefixSlice.content)
-          if (prefixDoc) {
-            prefixMarkdown = serializer(prefixDoc)
-          }
-        }
-        if (!prefixMarkdown) {
-          prefixMarkdown = view.state.doc.textBetween(0, from, '\n', '\n')
-        }
-        
-        // Suffix
-        const suffixSlice = view.state.doc.slice(to)
-        if (suffixSlice.content.size > 0) {
-          const suffixDoc = schema.topNodeType.createAndFill(undefined, suffixSlice.content)
-          if (suffixDoc) {
-            suffixMarkdown = serializer(suffixDoc)
-          }
-        }
-        if (!suffixMarkdown) {
-          suffixMarkdown = view.state.doc.textBetween(to, view.state.doc.content.size, '\n', '\n')
-        }
-      } catch (e) {
-        console.error('[Debug] Serializer error:', e)
-        prefixMarkdown = view.state.doc.textBetween(0, from, '\n', '\n')
-        suffixMarkdown = view.state.doc.textBetween(to, view.state.doc.content.size, '\n', '\n')
-      }
-      console.log('[Debug] ===== Document State =====')
-      console.log('[Debug] PREFIX:', prefixMarkdown)
-      console.log('[Debug] SUFFIX:', suffixMarkdown)
-      console.log('[Debug] FULL MARKDOWN:', markdown)
-      console.log('[Debug] ==========================')
-    })
-  } catch (e) {
-    console.error('[Debug] Log failed:', e)
-  }
-}
-
 const clearCurrentSuggestion = (view) => {
   clearGhostSuggestion(view)
 }
 
-const performOCR = async (file, cacheKey) => {
+const clearCurrentGhost = () => {
+  if (!crepe) return
+  crepe.editor.action((ctx) => {
+    const view = ctx.get(editorViewCtx)
+    clearGhostSuggestion(view)
+  })
+}
+
+const performOCR = async (file, cacheKey, imageHash = '') => {
   if (!aiEnabled.value) return
   
   const reader = new FileReader()
@@ -289,6 +245,9 @@ const performOCR = async (file, cacheKey) => {
       if (data.text) {
         setOcrCache(cacheKey, data.text)
         setOcrCache(file.name, data.text)
+        if (imageHash) {
+          setOcrByHash(imageHash, data.text)
+        }
       }
     } catch (e) {
       console.error('[OCR] Error:', e)
@@ -298,10 +257,8 @@ const performOCR = async (file, cacheKey) => {
 }
 
 onMounted(async () => {
-    if (DEBUG) console.log('[Debug] onMounted called')
     if (!root.value) throw new Error('root.value is null')
     
-    if (DEBUG) console.log('[Debug] Creating Crepe editor...')
     crepe = new Crepe({
         root: root.value,
         defaultValue: '# Welcome to LLM in text\n\nStart writing your content here...',
@@ -318,10 +275,24 @@ onMounted(async () => {
                 inlineEditConfirm: 'Escape'
             },
             [Crepe.Feature.ImageBlock]: {
-                onUpload: (file) => {
+                onUpload: async (file) => {
+                    if (file.size > IMAGE_SIZE_LIMIT) {
+                        alert(`图片大小不能超过 ${Math.floor(IMAGE_SIZE_LIMIT / 1024 / 1024)}MB`)
+                        return null
+                    }
                     const objectUrl = URL.createObjectURL(file)
                     objectUrls.add(objectUrl)
-                    performOCR(file, objectUrl)
+                    const arrayBuffer = await file.arrayBuffer()
+                    const imageBytes = new Uint8Array(arrayBuffer)
+                    const imageHash = await calculateImageHash(imageBytes)
+                    const existingOcr = getOcrByHash(imageHash)
+                    if (!existingOcr) {
+                        performOCR(file, objectUrl, imageHash)
+                    } else {
+                        setOcrCache(objectUrl, existingOcr)
+                        setOcrCache(file.name, existingOcr)
+                    }
+                    clearCurrentGhost()
                     return objectUrl
                 }
             }
@@ -358,9 +329,6 @@ onMounted(async () => {
         refreshSizeAndLimit(ctx)
     })
     scheduleMarkdownSync()
-    debugLogTimer = setInterval(logDebugInfo, 20000)
-    
-    if (DEBUG) console.log('[Debug] Crepe editor created with copilot plugin')
 })
 
 const exportMarkdown = async () => {
@@ -450,9 +418,27 @@ const handleImageUpload = async (event) => {
     const file = event.target.files?.[0]
     if (!file) return
     
+    if (file.size > IMAGE_SIZE_LIMIT) {
+        alert(`图片大小不能超过 ${Math.floor(IMAGE_SIZE_LIMIT / 1024 / 1024)}MB`)
+        event.target.value = ''
+        return
+    }
+    
     const objectUrl = URL.createObjectURL(file)
     objectUrls.add(objectUrl)
-    performOCR(file, objectUrl)
+    
+    const arrayBuffer = await file.arrayBuffer()
+    const imageBytes = new Uint8Array(arrayBuffer)
+    const imageHash = await calculateImageHash(imageBytes)
+    const existingOcr = getOcrByHash(imageHash)
+    if (!existingOcr) {
+        performOCR(file, objectUrl, imageHash)
+    } else {
+        setOcrCache(objectUrl, existingOcr)
+        setOcrCache(file.name, existingOcr)
+    }
+    
+    clearCurrentGhost()
     insertImageAtCursor(objectUrl)
     
     event.target.value = ''
@@ -472,10 +458,6 @@ onUnmounted(() => {
         clearTimeout(markdownSyncTimer)
         markdownSyncTimer = null
     }
-    if (debugLogTimer) {
-        clearInterval(debugLogTimer)
-        debugLogTimer = null
-    }
 
     for (const url of Array.from(objectUrls)) {
         revokeObjectUrl(url)

src/plugins/copilotPlugin.ts

@@ -9,7 +9,6 @@ import { getOcrCache, OCR_SIZE_LIMIT, extractTextFromOCR } from '../utils/ocrCac
 const COPILOT_PLUGIN_KEY = new PluginKey('milkdown-copilot')
 const DEBOUNCE_MS = 1000
 const SIZE_LIMIT = OCR_SIZE_LIMIT
-const DEBUG = true
 const IMAGE_NODE_TYPES = new Set(['image', 'image-block', 'imageBlock'])
 
 interface CopilotState {
@@ -334,12 +333,7 @@ function scheduleFetch(view: EditorView, runtime: CopilotRuntime, pos: number) {
 
   const doc = view.state.doc
   const schema = view.state.schema
-  const overLimit = doc.content.size > SIZE_LIMIT
+  const baseSize = doc.content.size
-
-  if (overLimit) {
-    setCopilotEnabled(view, false)
-    return
-  }
   
   const serializer = runtime.ctx.get(serializerCtx)
   let prefixMarkdown = ''
@@ -362,12 +356,15 @@ function scheduleFetch(view: EditorView, runtime: CopilotRuntime, pos: number) {
   }
 
   const requestPrefix = `${prefixMarkdown}${buildOcrContextForRequest(doc, pos)}`
+  const totalTextLen = (prefixMarkdown + suffixMarkdown).length
+  const ocrContextLen = requestPrefix.length - prefixMarkdown.length
+  const totalWithOcr = totalTextLen + ocrContextLen
   
-  if (DEBUG) {
+  const overLimit = totalWithOcr > SIZE_LIMIT
-    console.log('[Copilot] ===== LLM Request =====')
+
-    console.log('[Copilot] PREFIX:', requestPrefix)
+  if (overLimit) {
-    console.log('[Copilot] SUFFIX:', suffixMarkdown)
+    setCopilotEnabled(view, false)
-    console.log('[Copilot] ======================')
+    return
   }
 
   if (runtime.debounceTimer) {

src/utils/api.js

@@ -1,7 +1,6 @@
-import { DEBUG, API_URL } from './config.js'
+import { API_URL } from './config.js'
 
 export async function fetchSuggestion(prefix, suffix, signal, apiUrl = API_URL) {
-    if (DEBUG) console.log('[Debug] fetchSuggestion called with prefix length:', prefix.length, 'suffix length:', suffix.length)
     try {
         const res = await fetch(apiUrl, {
             method: 'POST',
@@ -10,7 +9,6 @@ export async function fetchSuggestion(prefix, suffix, signal, apiUrl = API_URL)
             signal
         })
 
-        if (DEBUG) console.log('[Debug] fetchSuggestion response status:', res.status)
         if (!res.ok) {
             const errorText = await res.text()
             throw new Error(`HTTP ${res.status}: ${errorText}`)
@@ -18,7 +16,6 @@ export async function fetchSuggestion(prefix, suffix, signal, apiUrl = API_URL)
 
         const reader = res.body?.getReader()
         if (!reader) {
-            if (DEBUG) console.log('[Debug] No reader available')
             throw new Error('No reader available')
         }
 
@@ -40,23 +37,20 @@ export async function fetchSuggestion(prefix, suffix, signal, apiUrl = API_URL)
                     const data = JSON.parse(jsonStr)
                     if (data.content) {
                         text += data.content
-                        if (DEBUG) console.log('[Debug] Added content:', data.content)
                     }
                     if (data.done || data.error) break
                 } catch (e) {
-                    if (DEBUG) console.warn('[Debug] JSON parse error for:', jsonStr.substring(0, 50))
+                    // skip invalid lines
                 }
             }
         }
         
-        if (DEBUG) console.log('[Debug] Final suggestion text:', text.substring(0, 100))
         return text
     } catch (e) {
         if (e.name === 'AbortError') {
-            if (DEBUG) console.log('[Debug] Request aborted')
+            // ignore abort
         } else {
-            if (DEBUG) console.error('[Debug] fetchSuggestion error:', e)
+            throw e
         }
-        throw e
     }
 }

src/utils/ocrCache.js

@@ -1,6 +1,22 @@
-const SIZE_LIMIT = 64 * 1024
+const SIZE_LIMIT = 32 * 1024
+export const IMAGE_SIZE_LIMIT = 100 * 1024 * 1024
 
 const ocrCache = new Map()
+const imageHashCache = new Map()
+
+export async function calculateImageHash(imageBytes) {
+  const hashBuffer = await crypto.subtle.digest('SHA-256', imageBytes)
+  const hashArray = Array.from(new Uint8Array(hashBuffer))
+  return hashArray.map(b => b.toString(16).padStart(2, '0')).join('')
+}
+
+export function getOcrByHash(hash) {
+  return imageHashCache.get(hash) || ''
+}
+
+export function setOcrByHash(hash, text) {
+  imageHashCache.set(hash, text)
+}
 
 export function setOcrCache(filename, text) {
   ocrCache.set(filename, text)