feat: implement inline autocomplete suggestions with FastAPI backend and Milkdown editor integration

backend/.env

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=ollama
+OLLAMA_BASE_URL=http://192.168.0.120:11434/v1/
+OLLAMA_MODEL=gpt-oss:120b

backend/.env.example

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=ollama
+OLLAMA_BASE_URL=http://192.168.0.120:11434/v1/
+OLLAMA_MODEL=gpt-oss:120b

backend/llm.py

@@ -0,0 +1,44 @@
+import os
+from typing import AsyncGenerator
+from openai import AsyncOpenAI
+import json
+
+api_key = os.getenv('OPENAI_API_KEY', 'ollama')
+base_url = os.getenv('OLLAMA_BASE_URL', 'http://192.168.0.120:11434/v1/')
+model = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
+
+print(f"[LLM] API key configured: {'Yes' if api_key else 'No'}")
+print(f"[LLM] Base URL: {base_url}")
+print(f"[LLM] Model: {model}")
+
+client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+
+async def stream_openai(prompt: str) -> AsyncGenerator[str, None]:
+    """
+    调用 OpenAI/Ollama API 并流式返回补全内容。
+    参考 completions-sample-code 的 streaming 逻辑。
+    """
+    print(f"[LLM] Calling API with prompt length: {len(prompt)}")
+    
+    try:
+        stream = await client.chat.completions.create(
+            model=model,
+            messages=[{"role": "user", "content": prompt}],
+            stream=True,
+            max_tokens=128,
+            temperature=0.2,
+        )
+
+        chunk_count = 0
+        async for chunk in stream:
+            if chunk.choices[0].delta.content:
+                content = chunk.choices[0].delta.content
+                chunk_count += 1
+                print(f"[LLM] Chunk {chunk_count}: {content}")
+                yield json.dumps({"content": content})
+        
+        print(f"[LLM] Stream complete, total chunks: {chunk_count}")
+    except Exception as e:
+        error_msg = f"Error: {str(e)}"
+        print(f"[LLM] Error: {error_msg}")
+        yield json.dumps({"error": str(e)})

backend/main.py

@@ -0,0 +1,47 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import StreamingResponse
+from pydantic import BaseModel
+import os
+import json
+
+app = FastAPI()
+
+class CompletionRequest(BaseModel):
+    prefix: str
+    suffix: str
+    languageId: str = 'markdown'
+
+def generate_stream(request: CompletionRequest):
+    from prompt import build_prompt
+    from llm import stream_openai
+    
+    print(f"[Backend] Received request - prefix length: {len(request.prefix)}, suffix length: {len(request.suffix)}")
+    
+    try:
+        prompt = build_prompt(request.prefix, request.suffix)
+        print(f"[Backend] Built prompt (first 100 chars): {prompt[:100]}...")
+        
+        async def gen():
+            chunk_count = 0
+            async for chunk in stream_openai(prompt):
+                chunk_count += 1
+                yield f"data: {chunk}\n\n"
+                if chunk_count % 5 == 0:
+                    print(f"[Backend] Sent chunk {chunk_count}")
+            yield "data: {\"done\": true}\n\n"
+            print(f"[Backend] Stream complete, total chunks: {chunk_count}")
+        return gen()
+    except Exception as e:
+        error_msg = f"{{\"error\": \"{str(e)}\"}}"
+        print(f"[Backend] Error: {e}")
+        yield f"data: {error_msg}\n\n"
+
+@app.post("/v1/completions")
+async def create_completion(request: CompletionRequest):
+    print(f"[Backend] POST /v1/completions called")
+    return StreamingResponse(generate_stream(request), media_type="text/event-stream")
+
+if __name__ == "__main__":
+    import uvicorn
+    print("[Backend] Starting server on http://0.0.0.0:8000")
+    uvicorn.run(app, host="0.0.0.0", port=8000)

backend/prompt.py

@@ -0,0 +1,28 @@
+import os
+from typing import Tuple
+
+def build_prompt(prefix: str, suffix: str) -> str:
+    """
+    构建用于代码补全的 Prompt。
+    参考 completions-sample-code 的 extractPrompt 逻辑简化实现。
+    """
+    MAX_CONTEXT_LINES = 30
+    
+    prefix_lines = prefix.split('\n')
+    suffix_lines = suffix.split('\n') if suffix else []
+    
+    recent_prefix = '\n'.join(prefix_lines[-MAX_CONTEXT_LINES:])
+    recent_suffix = '\n'.join(suffix_lines[:5])
+
+    prompt = f"""
+You are a helpful writing assistant. Continue the text naturally based on the context.
+
+Context (before cursor):
+{recent_prefix}
+
+Complete this:
+{suffix if suffix else '(cursor here)'}
+
+Continue:"""
+    
+    return prompt.strip()

backend/requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+openai
+pydantic
+python-dotenv

plans/inline-suggestions-plan.md

@@ -0,0 +1,111 @@
+# Inline Autocomplete Suggestions 实现计划
+
+## 技术栈确认
+- **前端**: Vue3 + Milkdown Editor
+- **后端**: Python FastAPI
+- **LLM**: OpenAI API（流式响应）
+- **范围**: 基础流式补全，无需复杂缓存机制
+
+## 系统架构
+
+```mermaid
+flowchart TB
+    subgraph 前端 [Vue3 + Milkdown]
+        E[Milkdown Editor]
+        I[InlineSuggestionPlugin<br/>输入监听+防抖]
+        G[GhostTextOverlay<br/>虚影渲染层]
+    end
+    
+    subgraph 后端 [FastAPI]
+        API[/v1/completions<br/>补全接口]
+        P[PromptBuilder<br/>上下文构建]
+        L[OpenAI Client<br/>LLM调用]
+    end
+    
+    I -- "输入事件" --> G
+    G -- "POST {prefix, suffix}" --> API
+    API -- "流式响应" --> G
+```
+
+## 实现步骤
+
+### 1. 前端：创建 Inline Suggestion Plugin
+**文件**: `src/plugins/inlineSuggestionPlugin.ts`
+- 监听编辑器输入事件
+- 防抖处理（150ms）
+- 调用后端 API 获取补全建议
+- 管理 GhostText 显示状态
+
+### 2. 前端：GhostText 渲染组件
+**文件**: `src/components/GhostTextOverlay.vue` 或内联样式
+- 在光标位置显示灰色虚影文本
+- 处理 Tab 键接受补全
+- ESC 键取消显示
+
+### 3. 修改 MilkdownEditor 集成插件
+**文件**: `src/components/MilkdownEditor.vue`
+- 注册 InlineSuggestionPlugin 到 Crepe 实例
+- 配置 API 地址
+
+### 4. 后端：FastAPI 服务
+**文件**: `backend/main.py`
+- POST `/v1/completions` 流式接口
+- 请求体验证和解析
+
+### 5. 后端：Prompt 构建和 LLM 调用
+**文件**: `backend/prompt.py`, `backend/llm.py`
+- 构建补全 Prompt（参考 completions-sample-code 的 extractPrompt）
+- OpenAI API 流式调用
+- 返回 SSE 格式响应
+
+## 文件结构
+
+```
+llm-in-text/
+├── src/
+│   ├── components/
+│   │   └── MilkdownEditor.vue      [修改]
+│   ├── plugins/
+│   │   └── inlineSuggestionPlugin.ts [新建]
+│   └── ...
+└── backend/
+    ├── main.py                      [新建]
+    ├── prompt.py                    [新建]
+    ├── llm.py                       [新建]
+    └── requirements.txt             [新建]
+```
+
+## API 设计
+
+### 请求
+```json
+POST /v1/completions
+{
+  "prefix": "# Hello\n\nThis is ",
+  "suffix": "",
+  "languageId": "markdown"
+}
+```
+
+### 响应（流式 SSE）
+```
+data: {"content": "a "}
+
+data: {"content": "a te"}
+
+data: {"content": "a test"}
+
+data: [DONE]
+```
+
+## 参考代码映射
+
+| completions-sample-code | 本项目实现 |
+|------------------------|-----------|
+| `ghostText.ts getGhostText()` | 后端 LLM 调用逻辑 |
+| `inlineCompletion.ts GhostText` | 前端 Plugin 核心逻辑 |
+| `networking.ts postRequest()` | 后端 API 接口 |
+| `prompt/extractPrompt()` | 后端 Prompt 构建 |
+
+## 下一步
+确认计划后切换到 Code 模式开始实现。

src/components/GhostTextOverlay.vue

@@ -0,0 +1,47 @@
+<template>
+  <div v-if="visible" class="ghost-text-overlay" :style="overlayStyle"
+       @click="acceptSuggestion"
+  >{{ suggestion }}
+  </div>
+</template>
+
+<script setup>
+import { computed } from 'vue'
+
+const props = defineProps({
+    suggestion: { type: String, default: '' },
+    position: { type: Object, required: true },
+})
+
+const emit = defineEmits(['accept', 'dismiss'])
+
+const visible = computed(() => props.suggestion && props.position)
+
+const overlayStyle = computed(() => ({
+    position: 'absolute',
+    left: `${props.position.left}px`,
+    top: `${props.position.top}px`,
+    fontSize: `${props.position.fontSize || 16}px`,
+    fontFamily: props.position.fontFamily || 'monospace',
+    color: '#999',
+    backgroundColor: 'transparent',
+    pointerEvents: 'auto',
+    cursor: 'text',
+    whiteSpace: 'pre-wrap',
+    zIndex: 1000,
+}))
+
+const acceptSuggestion = () => emit('accept')
+</script>
+
+<style scoped>
+.ghost-text-overlay {
+    opacity: 0.6;
+    user-select: none;
+}
+
+.ghost-text-overlay:hover {
+    opacity: 1;
+    color: #666;
+}
+</style>

src/components/MilkdownEditor.vue

@@ -1,28 +1,195 @@
 <template>
-  <div class="editor-container">
+  <div class="editor-container" ref="containerRef">
     <button class="export-btn" @click="exportMarkdown">导出文件</button>
+    
     <div ref="root" class="milkdown-editor"></div>
+    
+    GhostTextOverlay
+      v-if="suggestion && cursorRect"
+      :suggestion="suggestion"
+      :position="cursorRect"
+      @accept="acceptSuggestion"
+      @dismiss="dismissSuggestion"
+    /GhostTextOverlay
   </div>
 </template>
 
 <script setup>
 import { onMounted, ref } from 'vue'
 import { Crepe } from '@milkdown/crepe'
+import GhostTextOverlay from './GhostTextOverlay.vue'
 
 const root = ref(null)
+const containerRef = ref(null)
 let crepe = null
 
-onMounted(async () => {
+const suggestion = ref('')
-  if (!root.value) return
+const cursorRect = ref(null)
+let debounceTimer = null
+let lastPos = -1
 
+const API_URL = 'http://localhost:8000/v1/completions'
+const DEBOUNCE_MS = 150
+
+onMounted(async () => {
+    console.log('[Debug] onMounted called')
+    if (!root.value) {
+        console.log('[Debug] root.value is null')
+        return
+    }
+    
+    console.log('[Debug] Creating Crepe editor...')
     crepe = new Crepe({
         root: root.value,
         defaultValue: '# Welcome to Milkdown\n\nStart writing your markdown content here...',
     })
     
     await crepe.create()
+    console.log('[Debug] Crepe editor created')
 })
 
+const getCursorPosition = async () => {
+    if (!crepe) {
+        console.log('[Debug] getCursorPosition: crepe is null')
+        return null
+    }
+    
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        const { from } = view.state.selection
+        console.log('[Debug] Cursor position:', from)
+        
+        const coords = view.coordsAtPos(from)
+        const containerRect = containerRef.value?.getBoundingClientRect()
+        if (!containerRect) {
+            console.log('[Debug] containerRect is null')
+            return null
+        }
+        
+        return {
+            left: coords.left - containerRect.left,
+            top: coords.top - containerRect.top + window.scrollY,
+            fontSize: 16,
+            fontFamily: 'monospace',
+        }
+    } catch (e) {
+        console.error('[Debug] getCursorPosition error:', e)
+        return null
+    }
+}
+
+const fetchSuggestion = async (prefix, suffix) => {
+    console.log('[Debug] fetchSuggestion called with prefix length:', prefix.length, 'suffix length:', suffix.length)
+    try {
+        const res = await fetch(API_URL, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({ prefix, suffix, languageId: 'markdown' }),
+        })
+
+        console.log('[Debug] fetchSuggestion response status:', res.status)
+        if (!res.ok) {
+            console.log('[Debug] Response not ok')
+            return ''
+        }
+
+        const reader = res.body?.getReader()
+        if (!reader) {
+            console.log('[Debug] No reader available')
+            return ''
+        }
+
+        let text = ''
+        while (true) {
+            const { done, value } = await reader.read()
+            if (done) break
+            const chunk = new TextDecoder().decode(value)
+            console.log('[Debug] Received chunk:', chunk.substring(0, 100))
+            
+            const lines = chunk.split('\n').filter(l => l.startsWith('data: '))
+            for (const line of lines) {
+                try {
+                    const data = JSON.parse(line.slice(6))
+                    if (data.content) {
+                        text += data.content
+                        console.log('[Debug] Added content:', data.content)
+                    }
+                    if (data.done || data.error) break
+                } catch (e) {
+                    console.warn('[Debug] JSON parse error:', e)
+                }
+            }
+        }
+        
+        console.log('[Debug] Final suggestion text:', text.substring(0, 100))
+        return text
+    } catch (e) {
+        console.error('[Debug] fetchSuggestion error:', e)
+        return ''
+    }
+}
+
+const onInput = async () => {
+    if (!crepe) {
+        console.log('[Debug] onInput: crepe is null')
+        return
+    }
+    
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        const { from } = view.state.selection
+        
+        if (from === lastPos) {
+            console.log('[Debug] Same position, skipping')
+            return
+        }
+        lastPos = from
+        
+        console.log('[Debug] onInput triggered at position:', from)
+        
+        const prefix = view.state.doc.textBetween(0, from)
+        const suffix = view.state.doc.textBetween(from, view.state.doc.content.size)
+        
+        console.log('[Debug] Prefix preview:', prefix.substring(-50))
+        
+        clearTimeout(debounceTimer)
+        debounceTimer = setTimeout(async () => {
+            cursorRect.value = await getCursorPosition()
+            suggestion.value = await fetchSuggestion(prefix, suffix)
+            console.log('[Debug] Suggestion updated:', suggestion.value ? 'yes' : 'no')
+        }, DEBOUNCE_MS)
+    } catch (e) {
+        console.error('[Debug] onInput error:', e)
+    }
+}
+
+const handleTab = () => {
+    if (suggestion.value) {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        view.dispatch(view.state.tr.insertText(suggestion.value))
+        suggestion.value = ''
+        console.log('[Debug] Tab pressed, accepted suggestion')
+    }
+}
+
+const dismissSuggestion = () => {
+    suggestion.value = ''
+    console.log('[Debug] Suggestion dismissed')
+}
+
+const acceptSuggestion = () => {
+    if (suggestion.value) {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        view.dispatch(view.state.tr.insertText(suggestion.value))
+        suggestion.value = ''
+        console.log('[Debug] Suggestion accepted via click')
+    }
+}
+
 const exportMarkdown = async () => {
     if (!crepe) return
     const markdown = await crepe.getMarkdown()
@@ -34,6 +201,31 @@ const exportMarkdown = async () => {
     a.click()
     URL.revokeObjectURL(url)
 }
+
+// 监听 crepe 创建完成后绑定事件
+const initEditorEvents = () => {
+    if (!crepe) return
+    
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        console.log('[Debug] Binding input event to editor DOM')
+        
+        // 直接在编辑器 DOM 上监听输入事件
+        view.dom.addEventListener('input', onInput)
+        view.dom.addEventListener('keydown', (e) => {
+            console.log('[Debug] Keydown:', e.key, 'code:', e.code)
+            if (e.key === 'Tab') {
+                handleTab()
+            }
+        })
+    } catch (e) {
+        console.error('[Debug] Failed to bind events:', e)
+    }
+}
+
+// 延迟初始化事件绑定
+setTimeout(initEditorEvents, 500)
 </script>
 
 <style scoped>
@@ -41,7 +233,7 @@ const exportMarkdown = async () => {
     position: relative;
 }
 
-.export-btn {
+export-btn {
     position: fixed;
     top: 20px;
     right: 20px;
@@ -54,7 +246,7 @@ const exportMarkdown = async () => {
     z-index: 1000;
 }
 
-.export-btn:hover {
+export-btn:hover {
     background-color: #3a7bc8;
 }
 
@@ -65,7 +257,6 @@ const exportMarkdown = async () => {
     overflow-y: auto;
 }
 
-/* 当内容不超过视口时隐藏滚动条 */
 .milkdown-editor::-webkit-scrollbar {
     width: 8px;
 }
@@ -79,7 +270,6 @@ const exportMarkdown = async () => {
     border-radius: 4px;
 }
 
-/* 编辑器内容容器样式 */
 .milkdown-editor :deep(.milkdown) {
     max-width: 900px;
     margin: 0 auto !important;
@@ -87,7 +277,6 @@ const exportMarkdown = async () => {
     min-height: calc(100vh - 40px);
 }
 
-/* 全局覆盖所有元素的边距 */
 .milkdown-editor :deep(*) {
     margin-top: 0 !important;
     margin-bottom: 0 !important;

src/plugins/inlineSuggestionPlugin.ts

@@ -0,0 +1,104 @@
+import { Plugin, PluginKey } from '@milkdown/prose/state';
+import { EditorView } from '@milkdown/prose/view';
+
+const INLINE_SUGGESTION_KEY = new PluginKey('inline-suggestion');
+const DEBOUNCE_MS = 150;
+let debounceTimer = null;
+let currentSuggestion = '';
+let suggestionPos = { from: 0, to: 0 };
+
+interface InlineSuggestionOptions {
+    apiUrl?: string;
+}
+
+function createInlineSuggestionPlugin(options: InlineSuggestionOptions = {}) {
+    const apiUrl = options.apiUrl || 'http://localhost:8000/v1/completions';
+
+    return new Plugin({
+        key: INLINE_SUGGESTION_KEY,
+        state: {
+            init: () => ({ suggestion: '', visible: false }),
+            apply: (tr, value) => {
+                if (!tr.docChanged) return value;
+                const { from, to } = tr.selection;
+                if (from === suggestionPos.from && to === suggestionPos.to) {
+                    return value;
+                }
+                return { suggestion: '', visible: false };
+            },
+        },
+        props: {
+            handleKeyDown: (view: EditorView, event: KeyboardEvent) => {
+                if (event.key === 'Tab' && INLINE_SUGGESTION_KEY.getState(view.state).visible) {
+                    event.preventDefault();
+                    const { suggestion } = INLINE_SUGGESTION_KEY.getState(view.state);
+                    if (suggestion) {
+                        view.dispatch(view.state.tr.insertText(suggestion, view.state.selection.from));
+                        currentSuggestion = '';
+                        return true;
+                    }
+                }
+                if (event.key === 'Escape') {
+                    const state = INLINE_SUGGESTION_KEY.getState(view.state);
+                    if (state.visible) {
+                        view.dispatch(view.state.tr.setMeta(INLINE_SUGGESTION_KEY, { suggestion: '', visible: false }));
+                        currentSuggestion = '';
+                        return true;
+                    }
+                }
+                return false;
+            },
+        },
+        appendTransaction: (transactions, oldState, newState) => {
+            const lastTr = transactions[transactions.length - 1];
+            if (!lastTr || !lastTr.docChanged) return null;
+
+            clearTimeout(debounceTimer);
+            debounceTimer = setTimeout(async () => {
+                const { from, to } = newState.selection;
+                const prefix = newState.doc.textBetween(0, from);
+                const suffix = newState.doc.textBetween(to, newState.doc.content.size);
+
+                try {
+                    const res = await fetch(apiUrl, {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({ prefix, suffix, languageId: 'markdown' }),
+                    });
+
+                    if (!res.ok) return;
+
+                    const reader = res.body?.getReader();
+                    if (!reader) return;
+
+                    let text = '';
+                    while (true) {
+                        const { done, value } = await reader.read();
+                        if (done) break;
+                        const chunk = new TextDecoder().decode(value);
+                        const lines = chunk.split('\n').filter(l => l.startsWith('data: '));
+                        for (const line of lines) {
+                            try {
+                                const data = JSON.parse(line.slice(6));
+                                if (data.content) text += data.content;
+                                if (data.done) break;
+                            } catch {}
+                        }
+                    }
+
+                    if (text && newState.selection.from === from) {
+                        currentSuggestion = text;
+                        suggestionPos = { from, to: from + text.length };
+                        newState.apply(newState.tr.setMeta(INLINE_SUGGESTION_KEY, { suggestion: text, visible: true }));
+                    }
+                } catch (e) {
+                    console.error('Inline suggestion error:', e);
+                }
+            }, DEBOUNCE_MS);
+
+            return null;
+        },
+    });
+}
+
+export { createInlineSuggestionPlugin, INLINE_SUGGESTION_KEY };