feat: switch from OpenAI API to native Ollama Python client

This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure.

Key changes:
- Replace openai package with ollama package in backend requirements
- Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls
- Update main.py to use non-streaming Ollama responses with thinking extraction
- Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags)
- Fix string截取错误 by using slice() instead of substring()
- Add src/utils/api.js and src/utils/config.js for shared configuration
- Add CORS middleware to FastAPI backend
- Update prompt.py with clearer instructions for continuation generation
- Add comprehensive README.md documentation

BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)

.env.example

@@ -0,0 +1,10 @@
+VITE_API_URL=http://localhost:8000/v1/completions
+
+# Ollama 配置
+OLLAMA_HOST=http://192.168.0.120:11434
+OLLAMA_MODEL=gpt-oss:120b
+
+# 可选：其他配置
+# 如果ollama需要认证，可以使用以下变量
+# OLLAMA_USERNAME=your_username
+# OLLAMA_PASSWORD=your_password

README.md

@@ -1,5 +1,210 @@
-# Vue 3 + Vite
+# LLM in Text - 智能写作助手
 
-This template should help get you started developing with Vue 3 in Vite. The template uses Vue 3 `<script setup>` SFCs, check out the [script setup docs](https://v3.vuejs.org/api/sfc-script-setup.html#sfc-script-setup) to learn more.
+基于 Vue3 和 FastAPI 的智能写作助手，实现类似 GitHub Copilot 的 inline suggestions（行内建议）功能。
 
-Learn more about IDE Support for Vue in the [Vue Docs Scaling up Guide](https://vuejs.org/guide/scaling-up/tooling.html#ide-support).
+## 项目概述
+
+本项目是一个全屏 Markdown 编辑器，集成了大语言模型（LLM）的智能补全功能。当用户输入时，系统会根据上下文实时提供文本补全建议，用户可以通过 Tab 键接受建议或点击建议文本直接插入。
+
+## 技术栈
+
+### 前端
+- **Vue 3** - 渐进式 JavaScript 框架
+- **Vite** - 下一代前端构建工具
+- **Milkdown** - 基于 ProseMirror 的 WYSIWYG Markdown 编辑器
+- **Pinia** - Vue 状态管理
+- **Axios** - HTTP 客户端
+
+### 后端
+- **FastAPI** - 现代化的 Python Web 框架
+- **OpenAI API** - 大语言模型接口
+- **Ollama** - 本地 LLM 服务支持
+
+## 核心功能
+
+### 1. 全屏 Markdown 编辑器
+- 基于 Milkdown Crepe 的所见即所得编辑体验
+- 支持完整的 Markdown 语法
+- 代码块高亮、图片粘贴等功能
+- 导出 Markdown 文件
+
+### 2. 智能行内建议
+- 实时监听用户输入
+- 基于上下文（光标前后文本）生成补全建议
+- 流式响应，实时显示建议内容
+- 支持多种交互方式：
+  - **Tab 键**：接受建议
+  - **Esc 键**：取消建议
+  - **点击建议**：直接插入
+
+### 3. 性能优化
+- 150ms 防抖机制，避免频繁请求
+- 流式传输（SSE），降低延迟
+- 上下文智能截取（光标前30行 + 后5行）
+
+## 项目结构
+
+```
+llm-in-text/
+├── src/
+│   ├── components/
+│   │   ├── MilkdownEditor.vue      # 主编辑器组件
+│   │   ├── GhostTextOverlay.vue    # 建议文本显示组件
+│   │   └── MarkdownEditor.vue      # 备用编辑器
+│   ├── plugins/
+│   │   ├── inlineSuggestionPlugin.ts  # 行内建议插件
+│   │   └── types.ts                # 类型定义
+│   ├── router/
+│   │   └── index.js                # 路由配置
+│   ├── store/
+│   │   └── index.js                # 状态管理
+│   ├── App.vue                     # 根组件
+│   └── main.js                     # 入口文件
+├── backend/
+│   ├── main.py                     # FastAPI 服务器
+│   ├── llm.py                      # LLM API 调用
+│   ├── prompt.py                   # Prompt 构建
+│   ├── requirements.txt            # Python 依赖
+│   └── .env                        # 环境变量配置
+├── plans/
+│   ├── milkdown-editor-plan.md     # 编辑器实施计划
+│   └── inline-suggestions-plan.md  # 建议功能实施计划
+├── index.html
+├── package.json
+├── vite.config.js
+└── README.md
+```
+
+## 快速开始
+
+### 前置要求
+- Node.js 18+
+- Python 3.8+
+- OpenAI API Key 或 Ollama 服务
+
+### 安装依赖
+
+**前端：**
+```bash
+npm install
+```
+
+**后端：**
+```bash
+cd backend
+pip install -r requirements.txt
+```
+
+### 配置环境变量
+
+在 `backend/.env` 文件中配置：
+
+```env
+OPENAI_API_KEY=your_api_key_here
+OLLAMA_BASE_URL=http://localhost:11434/v1/
+OLLAMA_MODEL=gpt-4
+```
+
+### 启动服务
+
+**启动后端：**
+```bash
+cd backend
+python main.py
+```
+
+**启动前端：**
+```bash
+npm run dev
+```
+
+访问 `http://localhost:5173` 开始使用。
+
+## API 接口
+
+### POST /v1/completions
+
+获取文本补全建议（流式响应）
+
+**请求体：**
+```json
+{
+  "prefix": "# Hello\n\nThis is ",
+  "suffix": "",
+  "languageId": "markdown"
+}
+```
+
+**响应（SSE 流）：**
+```
+data: {"content": "a "}
+
+data: {"content": "a te"}
+
+data: {"content": "a test"}
+
+data: {"done": true}
+```
+
+## 已知问题
+
+### 🔴 严重问题（P0）
+
+1. **模板语法错误** - [`MilkdownEditor.vue:7-13`](src/components/MilkdownEditor.vue:7-13)
+   - GhostTextOverlay 组件标签缺少尖括号
+   - 导致建议功能完全失效
+
+2. **字符串截取错误** - [`MilkdownEditor.vue:155`](src/components/MilkdownEditor.vue:155)
+   - `prefix.substring(-50)` 应该改为 `prefix.slice(-50)`
+
+3. **错误处理违反原则** - [`MilkdownEditor.vue:92-94`](src/components/MilkdownEditor.vue:92-94)
+   - 请求失败时返回空字符串而不是抛出错误
+   - 违反了"获取失败直接报错"的原则
+
+### 🟡 中等问题（P1）
+
+4. **内存泄漏风险** - 组件卸载时未清理 debounceTimer
+5. **不可靠的事件绑定** - 使用硬编码的 500ms 延迟
+6. **代码重复** - fetchSuggestion 逻辑在两个文件中重复
+7. **全局状态污染** - 插件使用模块级全局变量
+
+### 🟢 轻微问题（P2）
+
+8. 大量调试日志影响性能
+9. 缺少完整的类型定义
+10. 没有加载状态指示器
+11. 建议文本无长度限制
+12. API URL 硬编码在前端
+13. 后端缺少 CORS 配置
+
+## 开发指南
+
+### 代码规范
+
+- **前端**：遵循 Vue 3 Composition API 最佳实践
+- **后端**：遵循 FastAPI 异步编程模式
+- **错误处理**：获取失败直接报错，不返回默认值
+- **性能优化**：优先考虑降低延迟，避免冗余代码
+
+### 调试
+
+前端使用浏览器开发者工具，后端查看控制台输出。所有关键操作都有日志记录。
+
+## 贡献指南
+
+欢迎提交 Issue 和 Pull Request。在提交代码前，请确保：
+
+1. 代码通过 ESLint 检查
+2. 所有测试通过
+3. 添加必要的注释和文档
+4. 遵循项目的代码规范
+
+## 许可证
+
+MIT License
+
+## 致谢
+
+- [Milkdown](https://milkdown.dev/) - 优秀的 Markdown 编辑器框架
+- [FastAPI](https://fastapi.tiangolo.com/) - 现代化的 Python Web 框架
+- [OpenAI](https://openai.com/) - 大语言模型 API

backend/.env

@@ -1,3 +1,3 @@
 OPENAI_API_KEY=ollama
-OLLAMA_BASE_URL=http://100.124.143.24:11434/v1/
+OLLAMA_HOST=http://192.168.0.120:11434
 OLLAMA_MODEL=gpt-oss:120b

backend/llm.py

@@ -1,69 +1,52 @@
 import os
-from typing import AsyncGenerator
-from openai import AsyncOpenAI
 import json
-import time
+import ollama
+from typing import AsyncGenerator
 
-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')
+OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
+OLLAMA_HOST = os.getenv('OLLAMA_BASE_URL', 'http://192.168.0.120:11434')
 
-print(f"[LLM] API key configured: {'Yes' if api_key else 'No'}")
-print(f"[LLM] Base URL: {base_url}")
-print(f"[LLM] Model: {model}")
+# 移除 /v1/ 后缀（如果有的话），因为 Ollama Python 包使用原生 API
+if OLLAMA_HOST.endswith('/v1/'):
+    OLLAMA_HOST = OLLAMA_HOST[:-4]
+elif OLLAMA_HOST.endswith('/v1'):
+    OLLAMA_HOST = OLLAMA_HOST[:-3]
 
-client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+os.environ['OLLAMA_HOST'] = OLLAMA_HOST
+
+print(f"[LLM] Ollama host: {OLLAMA_HOST}")
+print(f"[LLM] Model: {OLLAMA_MODEL}")
+
+client = ollama.AsyncClient(host=OLLAMA_HOST)
 
 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。
-    """
-    start_time = time.time()
-    print(f"[LLM] ========== API Call Start ==========")
-    print(f"[LLM] Prompt length: {len(prompt)}")
-    print(f"[LLM] Model: {model}")
+    print(f"[LLM] Calling Ollama API with prompt length: {len(prompt)}")
     
     try:
-        print(f"[LLM] Creating streaming chat completion...")
-        stream = await client.chat.completions.create(
-            model=model,
-            messages=[{"role": "user", "content": prompt}],
+        print(f"[LLM] Awaiting client.chat...")
+        stream = await client.chat(
+            model=OLLAMA_MODEL,
+            messages=[{'role': 'user', 'content': prompt}],
             stream=True,
-            max_tokens=128,
-            temperature=0.2,
+            options={
+                'num_predict': 8192,
+                'temperature': 0.2,
+            }
         )
+        print(f"[LLM] Got stream object, starting iteration...")
         
-        print(f"[LLM] Stream created successfully, iterating...")
         chunk_count = 0
-        first_chunk_time = None
-        
         async for chunk in stream:
-            current_time = time.time()
-            if first_chunk_time is None:
-                first_chunk_time = current_time - start_time
-            
+            if chunk['message'] and chunk['message']['content']:
+                content = chunk['message']['content']
                 chunk_count += 1
-            choice = chunk.choices[0] if chunk.choices else None
-            
-            if choice and choice.delta.content:
-                content = choice.delta.content
-                print(f"[LLM] Chunk {chunk_count}: '{content}' (latency: {current_time - start_time:.3f}s)")
+                print(f"[LLM] Chunk {chunk_count}: {content}")
                 yield json.dumps({"content": content})
-            elif chunk.choices and hasattr(chunk.choices[0], 'finish_reason'):
-                finish_reason = chunk.choices[0].finish_reason
-                print(f"[LLM] Chunk {chunk_count}: finish_reason={finish_reason}")
-                if finish_reason:
-                    break
-            else:
-                print(f"[LLM] Chunk {chunk_count}: empty or no content")
         
-        total_time = time.time() - start_time
-        print(f"[LLM] Stream complete - chunks: {chunk_count}, first chunk latency: {first_chunk_time:.3f}s, total time: {total_time:.3f}s")
-        print(f"[LLM] ========== API Call End ==========")
+        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}")
         import traceback
         traceback.print_exc()
-        yield json.dumps({"error": str(e), "type": type(e).__name__})
+        yield json.dumps({"error": str(e)})

backend/main.py

@@ -1,75 +1,142 @@
 from fastapi import FastAPI, HTTPException
-from fastapi.responses import StreamingResponse
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse, JSONResponse
 from pydantic import BaseModel
 import os
 import json
-import time
+import re
 
 app = FastAPI()
 
-print("[Main] Backend service starting...")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
 
 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
+def extract_completion_from_thinking(thinking: str) -> str:
+    """
+    从模型的 thinking 输出中提取实际的续写内容。
+    移除推理过程，保留实际的续写。
+    """
+    if not thinking:
+        return ""
     
-    start_time = time.time()
-    print(f"[Main] ========== New Request ==========")
-    print(f"[Main] prefix length: {len(request.prefix)}, suffix length: {len(request.suffix)}")
-    print(f"[Main] languageId: {request.languageId}")
-    print(f"[Main] Prefix (last 200 chars): '{request.prefix[-200:]}'")
-    print(f"[Main] Suffix (first 200 chars): '{request.suffix[:200]}'")
+    # 尝试找到实际的续写内容
+    # 模型通常会在 thinking 中描述上下文，然后输出实际续写
+    # 常见的模式是：推理过程以描述开始，然后直接输出续写
     
-    try:
-        prompt = build_prompt(request.prefix, request.suffix)
-        print(f"[Main] Built prompt length: {len(prompt)}")
-        print(f"[Main] Prompt (first 300 chars): '{prompt[:300]}'")
-        print(f"[Main] Prompt (last 200 chars): '{prompt[-200:]}'")
+    # 查找 "Continuation:" 或类似标记之后的内容
+    continuation_match = re.search(r'Continuation[:\s]*([\s\S]*)', thinking, re.IGNORECASE)
+    if continuation_match:
+        result = continuation_match.group(1).strip()
+        # 移除可能的后续推理说明
+        result = re.sub(r'\s*It seems like.*$', '', result, flags=re.IGNORECASE)
+        return result.strip()
     
-        async def gen():
-            chunk_count = 0
-            first_chunk_time = None
-            try:
-                async for chunk in stream_openai(prompt):
-                    current_time = time.time()
-                    if first_chunk_time is None:
-                        first_chunk_time = current_time - start_time
-                    chunk_count += 1
-                    chunk_data = json.loads(chunk) if isinstance(chunk, str) else chunk
-                    content_preview = chunk_data.get('content', '')[:50] if chunk_data.get('content') else ''
-                    print(f"[Main] Chunk {chunk_count}: '{content_preview}'...")
-                    yield f"data: {json.dumps(chunk_data)}\n\n"
+    # 如果没有明确标记，尝试移除描述性内容
+    # 查找 "We need to continue" 或类似开头
+    continue_match = re.search(r'(?:We need to|Then we should|So we|I will|The|Thus)[,\s]+([A-Z][^.!?]*(?:[.!?]|$))', thinking)
+    if continue_match:
+        # 取找到的句子及其后续内容
+        start_idx = continue_match.start(1)
+        result = thinking[start_idx:].strip()
+        # 移除 "Probably " 开头及其后续内容
+        result = re.sub(r'^Probably\s+', '', result)
+        # 如果有 "It seems like" 或类似短语，截断
+        result = re.split(r'\s*It seems like\s', result, flags=re.IGNORECASE)[0]
+        return result.strip()
     
-                done_signal = {"done": True}
-                total_time = time.time() - start_time
-                print(f"[Main] Stream complete - total chunks: {chunk_count}, first chunk at: {first_chunk_time:.2f}s, total time: {total_time:.2f}s")
-                yield f"data: {json.dumps(done_signal)}\n\n"
-            except Exception as e:
-                error_msg = {"error": str(e), "type": type(e).__name__}
-                print(f"[Main] Generator error: {e}")
-                yield f"data: {json.dumps(error_msg)}\n\n"
-        return gen()
-    except Exception as e:
-        error_msg = {"error": str(e), "type": type(e).__name__}
-        print(f"[Main] Error building prompt or calling LLM: {e}")
-        yield f"data: {json.dumps(error_msg)}\n\n"
+    # 最后的策略：直接返回 thinking，移除末尾的推理说明
+    result = thinking.strip()
+    # 移除 "Probably" 及其后续内容
+    result = re.split(r'\s+Probably\s', result, flags=re.IGNORECASE, maxsplit=1)[0]
+    # 移除 "The instruction:" 及其后续内容
+    result = re.split(r'\s+The instruction:', result, flags=re.IGNORECASE, maxsplit=1)[0]
+    
+    return result.strip()
 
 @app.post("/v1/completions")
 async def create_completion(request: CompletionRequest):
-    print(f"[Main] POST /v1/completions called at {time.time()}")
-    return StreamingResponse(generate_stream(request), media_type="text/event-stream")
+    from prompt import build_prompt
+    import ollama
     
-@app.get("/health")
-async def health_check():
-    return {"status": "healthy", "timestamp": time.time()}
+    print(f"[Backend] POST /v1/completions called")
+    print(f"[Backend] Received request - prefix length: {len(request.prefix)}, suffix length: {len(request.suffix)}")
+    
+    OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
+    OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
+    
+    print(f"[LLM] Using host: {OLLAMA_HOST}, model: {OLLAMA_MODEL}")
+    
+    try:
+        prompt = build_prompt(request.prefix, request.suffix)
+        print(f"[Backend] Built prompt (first 100 chars): {prompt[:100]}...")
+        print(f"[LLM] Full prompt:\n{prompt}\n")
+        
+        # 使用非流式 API 获取完整响应
+        print(f"[LLM] Calling Ollama API (non-streaming)...")
+        client = ollama.AsyncClient(host=OLLAMA_HOST)
+        response = await client.chat(
+            model=OLLAMA_MODEL,
+            messages=[{'role': 'user', 'content': prompt}],
+            stream=False,
+            options={
+                'num_predict': 8192,
+                'temperature': 0.2,
+            }
+        )
+        
+        print(f"[LLM] Response type: {type(response)}")
+        
+        # 提取 content 和 thinking
+        content = ""
+        thinking = ""
+        
+        if hasattr(response, 'message') and response.message:
+            content = response.message.content or ""
+            thinking = getattr(response.message, 'thinking', '') or ""
+        elif isinstance(response, dict):
+            msg = response.get('message', {})
+            content = msg.get('content', '') or ""
+            thinking = msg.get('thinking', '') or ""
+        
+        print(f"[LLM] Original content: {repr(content[:100] if content else '')}...")
+        print(f"[LLM] Thinking length: {len(thinking)}")
+        print(f"[LLM] Thinking (first 200): {thinking[:200]}...")
+        
+        # 如果 content 为空，尝试从 thinking 中提取
+        if not content and thinking:
+            print(f"[LLM] Content is empty, extracting from thinking...")
+            content = extract_completion_from_thinking(thinking)
+            print(f"[LLM] Extracted completion: {repr(content[:100])}...")
+        
+        print(f"[LLM] Final content length: {len(content)}")
+        
+        # 返回完整内容
+        async def generate():
+            if content:
+                print(f"[LLM] Yielding full content: {repr(content)}")
+                yield f"data: {json.dumps({'content': content})}\n\n"
+            yield f"data: {{'done': true}}\n\n"
+        
+        return StreamingResponse(generate(), media_type="text/event-stream")
+        
+    except Exception as e:
+        error_msg = f"{{\"error\": \"{str(e)}\"}}"
+        print(f"[Backend] Error: {e}")
+        import traceback
+        traceback.print_exc()
+        return JSONResponse(content={"error": str(e)}, status_code=500)
 
 if __name__ == "__main__":
     import uvicorn
-    port = int(os.getenv('PORT', 8000))
-    print(f"[Main] Starting server on http://0.0.0.0:{port}")
-    uvicorn.run(app, host="0.0.0.0", port=port)
+    print("[Backend] Starting server on http://0.0.0.0:8000")
+    uvicorn.run(app, host="0.0.0.0", port=8000)

backend/prompt.py

@@ -3,8 +3,8 @@ 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。
+    改进后的提示词构建函数。
+    使用更明确的指令来引导模型生成高质量的续写内容。
     """
     MAX_CONTEXT_LINES = 30
     
@@ -14,15 +14,21 @@ def build_prompt(prefix: str, suffix: str) -> str:
     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.
+    prompt = f"""You are an expert writing assistant. Continue the text naturally.
 
-Context (before cursor):
-{recent_prefix}
+CONTEXT:
+⟨CURSOR⟩ marks where to continue.
+- Before ⟨CURSOR⟩: existing text
+- After ⟨CURSOR⟩: following context (if any)
 
-Complete this:
-{suffix if suffix else '(cursor here)'}
+RULES:
+- Match existing style, tone, and terminology
+- Maintain logical flow
+- Write only the continuation, nothing else
 
-Continue:"""
+TEXT:
+{recent_prefix}⟨CURSOR⟩{recent_suffix}
+
+CONTINUATION:"""
     
     return prompt.strip()

backend/requirements.txt

@@ -1,5 +1,6 @@
 fastapi
 uvicorn
-openai
+ollama
 pydantic
 python-dotenv
+httpx

package-lock.json

@@ -353,7 +353,6 @@
       "version": "6.12.1",
       "resolved": "https://registry.npmjs.org/@codemirror/language/-/language-6.12.1.tgz",
       "integrity": "sha512-Fa6xkSiuGKc8XC8Cn96T+TQHYj4ZZ7RdFmXA3i9xe/3hLHfwPZdM+dqfX0Cp0zQklBKhVD8Yzc8LS45rkqcwpQ==",
-      "peer": true,
       "dependencies": {
         "@codemirror/state": "^6.0.0",
         "@codemirror/view": "^6.23.0",
@@ -425,7 +424,6 @@
       "version": "6.5.4",
       "resolved": "https://registry.npmjs.org/@codemirror/state/-/state-6.5.4.tgz",
       "integrity": "sha512-8y7xqG/hpB53l25CIoit9/ngxdfoG+fx+V3SHBrinnhOtLvKHRyAJJuHzkWrR4YXXLX8eXBsejgAAxHUOdW1yw==",
-      "peer": true,
       "dependencies": {
         "@marijn/find-cluster-break": "^1.0.0"
       }
@@ -445,7 +443,6 @@
       "version": "6.39.11",
       "resolved": "https://registry.npmjs.org/@codemirror/view/-/view-6.39.11.tgz",
       "integrity": "sha512-bWdeR8gWM87l4DB/kYSF9A+dVackzDb/V56Tq7QVrQ7rn86W0rgZFtlL3g3pem6AeGcb9NQNoy3ao4WpW4h5tQ==",
-      "peer": true,
       "dependencies": {
         "@codemirror/state": "^6.5.0",
         "crelt": "^1.0.6",
@@ -3414,7 +3411,6 @@
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -3567,7 +3563,6 @@
       "version": "1.25.4",
       "resolved": "https://registry.npmjs.org/prosemirror-model/-/prosemirror-model-1.25.4.tgz",
       "integrity": "sha512-PIM7E43PBxKce8OQeezAs9j4TP+5yDpZVbuurd1h5phUxEKIu+G2a+EUZzIC5nS1mJktDJWzbqS23n1tsAf5QA==",
-      "peer": true,
       "dependencies": {
         "orderedmap": "^2.0.0"
       }
@@ -3598,7 +3593,6 @@
       "version": "1.4.4",
       "resolved": "https://registry.npmjs.org/prosemirror-state/-/prosemirror-state-1.4.4.tgz",
       "integrity": "sha512-6jiYHH2CIGbCfnxdHbXZ12gySFY/fz/ulZE333G6bPqIZ4F+TXo9ifiR86nAHpWnfoNjOb3o5ESi7J8Uz1jXHw==",
-      "peer": true,
       "dependencies": {
         "prosemirror-model": "^1.0.0",
         "prosemirror-transform": "^1.0.0",
@@ -3629,7 +3623,6 @@
       "version": "1.41.5",
       "resolved": "https://registry.npmjs.org/prosemirror-view/-/prosemirror-view-1.41.5.tgz",
       "integrity": "sha512-UDQbIPnDrjE8tqUBbPmCOZgtd75htE6W3r0JCmY9bL6W1iemDM37MZEKC49d+tdQ0v/CKx4gjxLoLsfkD2NiZA==",
-      "peer": true,
       "dependencies": {
         "prosemirror-model": "^1.20.0",
         "prosemirror-state": "^1.0.0",
@@ -3966,7 +3959,6 @@
       "integrity": "sha512-w+N7Hifpc3gRjZ63vYBXA56dvvRlNWRczTdmCBBa+CotUzAPf5b7YMdMR/8CQoeYE5LX3W4wj6RYTgonm1b9DA==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "esbuild": "^0.27.0",
         "fdir": "^6.5.0",
@@ -4041,7 +4033,6 @@
       "resolved": "https://registry.npmjs.org/vue/-/vue-3.5.26.tgz",
       "integrity": "sha512-SJ/NTccVyAoNUJmkM9KUqPcYlY+u8OVL1X5EW9RIs3ch5H2uERxyyIUI4MRxVCSOiEcupX9xNGde1tL9ZKpimA==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@vue/compiler-dom": "3.5.26",
         "@vue/compiler-sfc": "3.5.26",

plans/inline-suggestions-plan.md

@@ -31,32 +31,485 @@ flowchart TB
 
 ### 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
+
+#### 核心实现要点
+
+```typescript
+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;
+
+interface InlineSuggestionOptions {
+    apiUrl?: string;
+    onSuggestion?: (suggestion: string) => void;
+    onError?: (error: Error) => void;
+}
+
+interface SuggestionState {
+    suggestion: string;
+    visible: boolean;
+    loading: boolean;
+}
+
+function createInlineSuggestionPlugin(options: InlineSuggestionOptions = {}) {
+    const apiUrl = options.apiUrl || 'http://localhost:8000/v1/completions';
+    const onSuggestion = options.onSuggestion || (() => {});
+    const onError = options.onError || ((error) => console.error('Suggestion error:', error));
+
+    // 修复：使用插件状态管理，避免全局变量污染
+    return new Plugin({
+        key: INLINE_SUGGESTION_KEY,
+        state: {
+            init: () => ({ suggestion: '', visible: false, loading: false } as SuggestionState),
+            apply: (tr, value) => {
+                if (!tr.docChanged) return value;
+                const { from, to } = tr.selection;
+                // 如果光标位置没有变化，保持当前状态
+                if (from === value.from && to === value.to) {
+                    return value;
+                }
+                // 光标位置变化，重置建议状态
+                return { suggestion: '', visible: false, loading: false, from, to };
+            },
+        },
+        props: {
+            handleKeyDown: (view: EditorView, event: KeyboardEvent) => {
+                const state = INLINE_SUGGESTION_KEY.getState(view.state) as SuggestionState;
+
+                if (event.key === 'Tab' && state.visible) {
+                    event.preventDefault();
+                    if (state.suggestion) {
+                        view.dispatch(view.state.tr.insertText(state.suggestion, view.state.selection.from));
+                        // 重置状态
+                        view.dispatch(view.state.tr.setMeta(INLINE_SUGGESTION_KEY, {
+                            suggestion: '',
+                            visible: false,
+                            loading: false
+                        }));
+                        return true;
+                    }
+                }
+
+                if (event.key === 'Escape' && state.visible) {
+                    event.preventDefault();
+                    view.dispatch(view.state.tr.setMeta(INLINE_SUGGESTION_KEY, {
+                        suggestion: '',
+                        visible: false,
+                        loading: false
+                    }));
+                    return true;
+                }
+
+                return false;
+            },
+        },
+        appendTransaction: (transactions, oldState, newState) => {
+            const lastTr = transactions[transactions.length - 1];
+            if (!lastTr || !lastTr.docChanged) return null;
+
+            const { from, to } = newState.selection;
+            const prefix = newState.doc.textBetween(0, from);
+            const suffix = newState.doc.textBetween(to, newState.doc.content.size);
+
+            // 修复：使用插件级别的 debounce 管理
+            let debounceTimer: NodeJS.Timeout | null = null;
+
+            clearTimeout(debounceTimer);
+            debounceTimer = setTimeout(async () => {
+                try {
+                    // 设置加载状态
+                    newState.apply(newState.tr.setMeta(INLINE_SUGGESTION_KEY, {
+                        suggestion: '',
+                        visible: false,
+                        loading: true
+                    }));
+
+                    const text = await fetchSuggestion(apiUrl, prefix, suffix);
+
+                    // 检查光标位置是否仍然有效
+                    const currentState = INLINE_SUGGESTION_KEY.getState(newState) as SuggestionState;
+                    if (currentState.from === from && currentState.to === to) {
+                        newState.apply(newState.tr.setMeta(INLINE_SUGGESTION_KEY, {
+                            suggestion: text,
+                            visible: true,
+                            loading: false
+                        }));
+                        onSuggestion(text);
+                    }
+                } catch (e) {
+                    onError(e as Error);
+                    newState.apply(newState.tr.setMeta(INLINE_SUGGESTION_KEY, {
+                        suggestion: '',
+                        visible: false,
+                        loading: false
+                    }));
+                }
+            }, DEBOUNCE_MS);
+
+            return null;
+        },
+    });
+}
+
+// 修复：提取共享的 fetchSuggestion 函数，避免代码重复
+async function fetchSuggestion(apiUrl: string, prefix: string, suffix: string): Promise<string> {
+    const res = await fetch(apiUrl, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ prefix, suffix, languageId: 'markdown' }),
+    });
+
+    // 修复：遵循"获取失败直接报错"原则
+    if (!res.ok) {
+        const errorText = await res.text();
+        throw new Error(`API request failed: ${res.status} - ${errorText}`);
+    }
+
+    const reader = res.body?.getReader();
+    if (!reader) {
+        throw new Error('No response body reader available');
+    }
+
+    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 || data.error) break;
+            } catch (e) {
+                // 忽略 JSON 解析错误，继续处理下一行
+            }
+        }
+    }
+
+    return text;
+}
+
+export { createInlineSuggestionPlugin, INLINE_SUGGESTION_KEY, fetchSuggestion };
+```
 
 ### 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
+**文件**: `src/components/GhostTextOverlay.vue`
+
+#### 核心实现要点
+
+```vue
+<template>
+  <div v-if="visible" class="ghost-text-overlay" :style="overlayStyle"
+       @click="acceptSuggestion"
+  >
+    {{ truncatedSuggestion }}
+  </div>
+</template>
+
+<script setup>
+import { computed } from 'vue'
+
+const props = defineProps({
+    suggestion: { type: String, default: '' },
+    position: { type: Object, required: true },
+    maxLength: { type: Number, default: 200 }, // 修复：添加建议文本长度限制
+})
+
+const emit = defineEmits(['accept', 'dismiss'])
+
+const visible = computed(() => props.suggestion && props.position)
+
+// 修复：截断过长的建议文本
+const truncatedSuggestion = computed(() => {
+    if (props.suggestion.length > props.maxLength) {
+        return props.suggestion.slice(0, props.maxLength) + '...'
+    }
+    return props.suggestion
+})
+
+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>
+```
 
 ### 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
+
+#### 集成要点
+
+```vue
+<script setup>
+import { onMounted, onUnmounted, ref } from 'vue'
+import { Crepe } from '@milkdown/crepe'
+import GhostTextOverlay from './GhostTextOverlay.vue'
+import { createInlineSuggestionPlugin } from '../plugins/inlineSuggestionPlugin'
+
+const root = ref(null)
+const containerRef = ref(null)
+let crepe = null
+
+const suggestion = ref('')
+const cursorRect = ref(null)
+const loading = ref(false)
+
+// 修复：使用环境变量配置 API URL
+const API_URL = import.meta.env.VITE_API_URL || 'http://localhost:8000/v1/completions'
+
+onMounted(async () => {
+    if (!root.value) return
+
+    crepe = new Crepe({
+        root: root.value,
+        defaultValue: '# Welcome to LLM in text\n\nStart writing your content here...',
+    })
+
+    await crepe.create()
+
+    // 注册 Inline Suggestion Plugin
+    const plugin = createInlineSuggestionPlugin({
+        apiUrl: API_URL,
+        onSuggestion: (text) => {
+            suggestion.value = text
+            updateCursorPosition()
+        },
+        onError: (error) => {
+            console.error('Suggestion error:', error)
+            suggestion.value = ''
+        }
+    })
+
+    crepe.ctx.get().updateState((state) => {
+        return state.reconfigure({
+            plugins: [...state.plugins, plugin]
+        })
+    })
+})
+
+// 修复：组件卸载时清理资源
+onUnmounted(() => {
+    if (crepe) {
+        crepe.destroy()
+    }
+})
+
+const updateCursorPosition = async () => {
+    if (!crepe) return
+
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        const { from } = view.state.selection
+
+        const coords = view.coordsAtPos(from)
+        const containerRect = containerRef.value?.getBoundingClientRect()
+        if (!containerRect) return
+
+        cursorRect.value = {
+            left: coords.left - containerRect.left,
+            top: coords.top - containerRect.top + window.scrollY,
+            fontSize: 16,
+            fontFamily: 'monospace',
+        }
+    } catch (e) {
+        console.error('updateCursorPosition error:', e)
+    }
+}
+
+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 = ''
+    }
+}
+
+const dismissSuggestion = () => {
+    suggestion.value = ''
+}
+</script>
+
+<template>
+  <div class="editor-container" ref="containerRef">
+    <div ref="root" class="milkdown-editor"></div>
+
+    <!-- 修复：正确的组件标签语法 -->
+    <GhostTextOverlay
+      v-if="suggestion && cursorRect"
+      :suggestion="suggestion"
+      :position="cursorRect"
+      @accept="acceptSuggestion"
+      @dismiss="dismissSuggestion"
+    />
+  </div>
+</template>
+```
 
 ### 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
+
+#### 核心实现要点
+
+```python
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import StreamingResponse
+from fastapi.middleware.cors import CORSMiddleware  # 修复：添加 CORS 支持
+from pydantic import BaseModel
+import os
+import json
+
+app = FastAPI()
+
+# 修复：添加 CORS 中间件
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # 生产环境应该限制具体域名
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+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
+
+    try:
+        prompt = build_prompt(request.prefix, request.suffix)
+
+        async def gen():
+            chunk_count = 0
+            async for chunk in stream_openai(prompt):
+                chunk_count += 1
+                yield f"data: {chunk}\n\n"
+            yield "data: {\"done\": true}\n\n"
+        return gen()
+    except Exception as e:
+        # 修复：遵循"获取失败直接报错"原则
+        error_msg = f"{{\"error\": \"{str(e)}\"}}"
+        yield f"data: {error_msg}\n\n"
+        raise  # 重新抛出异常
+
+@app.post("/v1/completions")
+async def create_completion(request: CompletionRequest):
+    return StreamingResponse(generate_stream(request), media_type="text/event-stream")
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+```
 
 ### 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
+
+#### Prompt 构建
+
+```python
+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()
+```
+
+#### LLM 调用
+
+```python
+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://localhost:11434/v1/')
+model = os.getenv('OLLAMA_MODEL', 'gpt-4')
+
+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。
+    """
+    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
+                yield json.dumps({"content": content})
+
+    except Exception as e:
+        # 修复：遵循"获取失败直接报错"原则
+        yield json.dumps({"error": str(e)})
+        raise  # 重新抛出异常
+```
 
 ## 文件结构
 
@@ -66,13 +519,14 @@ llm-in-text/
 │   ├── components/
 │   │   └── MilkdownEditor.vue      [修改]
 │   ├── plugins/
-│   │   └── inlineSuggestionPlugin.ts [新建]
+│   │   ├── inlineSuggestionPlugin.ts [修改]
+│   │   └── types.ts                [新建]
 │   └── ...
 └── backend/
-    ├── main.py                      [新建]
-    ├── prompt.py                    [新建]
-    ├── llm.py                       [新建]
-    └── requirements.txt             [新建]
+    ├── main.py                      [修改]
+    ├── prompt.py                    [修改]
+    ├── llm.py                       [修改]
+    └── requirements.txt             [修改]
 ```
 
 ## API 设计
@@ -95,9 +549,51 @@ data: {"content": "a te"}
 
 data: {"content": "a test"}
 
-data: [DONE]
+data: {"done": true}
 ```
 
+## 已知问题及修复方案
+
+### 🔴 严重问题（P0）
+
+#### 1. 全局状态污染
+**位置**: `inlineSuggestionPlugin.ts:6-8`
+**问题**: 使用模块级全局变量，多个编辑器实例会共享状态
+**修复**: 使用 ProseMirror 插件的状态管理机制，每个插件实例维护自己的状态
+
+#### 2. 错误处理违反原则
+**位置**: `llm.py:42-44`, `main.py:34-37`
+**问题**: 错误时只返回错误信息，不抛出异常
+**修复**: 遵循"获取失败直接报错"原则，在 yield 错误信息后重新抛出异常
+
+### 🟡 中等问题（P1）
+
+#### 3. 代码重复
+**问题**: `fetchSuggestion` 逻辑在两个文件中重复
+**修复**: 提取共享的 `fetchSuggestion` 函数，在插件和编辑器组件中复用
+
+#### 4. 缺少 CORS 配置
+**问题**: 后端没有配置 CORS，可能导致跨域请求失败
+**修复**: 在 FastAPI 中添加 CORS 中间件
+
+#### 5. 建议文本无长度限制
+**问题**: 建议文本可能过长，影响显示效果
+**修复**: 在 GhostTextOverlay 组件中添加 `maxLength` prop，截断过长的建议
+
+### 🟢 轻微问题（P2）
+
+#### 6. 缺少加载状态
+**问题**: 用户无法知道是否正在获取建议
+**修复**: 在插件状态中添加 `loading` 字段，在 UI 中显示加载指示器
+
+#### 7. 缺少类型定义
+**问题**: TypeScript 代码中缺少完整的类型定义
+**修复**: 添加 `SuggestionState` 接口和完整的类型定义
+
+#### 8. API URL 硬编码
+**问题**: API URL 硬编码在前端代码中
+**修复**: 使用环境变量 `VITE_API_URL` 配置 API URL
+
 ## 参考代码映射
 
 | completions-sample-code | 本项目实现 |
@@ -107,5 +603,23 @@ data: [DONE]
 | `networking.ts postRequest()` | 后端 API 接口 |
 | `prompt/extractPrompt()` | 后端 Prompt 构建 |
 
+## 最佳实践
+
+### 错误处理
+- 遵循"获取失败直接报错"原则
+- 不返回默认值，不尝试隐藏报错信息
+- 在前端和后端都实现完整的错误处理
+
+### 性能优化
+- 使用 150ms 防抖，避免频繁请求
+- 流式传输（SSE），降低延迟
+- 及时清理定时器和事件监听器
+
+### 代码质量
+- 避免全局变量，使用插件状态管理
+- 提取共享逻辑，避免代码重复
+- 添加完整的类型定义
+- 移除调试日志或条件化输出
+
 ## 下一步
 确认计划后切换到 Code 模式开始实现。

plans/milkdown-editor-plan.md

@@ -24,6 +24,14 @@ graph TB
         G[代码块高亮]
         H[图片粘贴支持]
     end
+
+    subgraph "集成功能"
+        I[GhostTextOverlay<br/>建议文本显示]
+        J[InlineSuggestionPlugin<br/>智能补全]
+    end
+
+    C --> I
+    C --> J
 ```
 
 ## 实施步骤
@@ -38,19 +46,280 @@ npm install @milkdown/crepe @milkdown/vue
 
 **文件**: `src/components/MilkdownEditor.vue`
 
+#### 核心实现要点
+
 ```vue
 <template>
-  <MilkdownProvider>
-    <Milkdown />
-  </MilkdownProvider>
+  <div class="editor-container" ref="containerRef">
+    <button class="export-btn" @click="exportMarkdown">导出文件</button>
+
+    <div ref="root" class="milkdown-editor"></div>
+
+    <!-- 修复：正确的组件标签语法 -->
+    <GhostTextOverlay
+      v-if="suggestion && cursorRect"
+      :suggestion="suggestion"
+      :position="cursorRect"
+      @accept="acceptSuggestion"
+      @dismiss="dismissSuggestion"
+    />
+  </div>
 </template>
 
 <script setup>
-import { Milkdown, MilkdownProvider, useEditor } from '@milkdown/vue'
+import { onMounted, onUnmounted, ref } from 'vue'
 import { Crepe } from '@milkdown/crepe'
+import GhostTextOverlay from './GhostTextOverlay.vue'
 
-const { get } = useEditor((root) => new Crepe({ root }))
+const root = ref(null)
+const containerRef = ref(null)
+let crepe = null
+
+const suggestion = ref('')
+const cursorRect = ref(null)
+let debounceTimer = null
+let lastPos = -1
+
+const API_URL = import.meta.env.VITE_API_URL || 'http://localhost:8000/v1/completions'
+const DEBOUNCE_MS = 150
+
+onMounted(async () => {
+    if (!root.value) return
+
+    crepe = new Crepe({
+        root: root.value,
+        defaultValue: '# Welcome to LLM in text\n\nStart writing your content here...',
+    })
+
+    await crepe.create()
+
+    // 修复：使用更可靠的事件绑定方式
+    initEditorEvents()
+})
+
+// 修复：组件卸载时清理资源
+onUnmounted(() => {
+    if (debounceTimer) {
+        clearTimeout(debounceTimer)
+    }
+    if (crepe) {
+        crepe.destroy()
+    }
+})
+
+const getCursorPosition = async () => {
+    if (!crepe) return null
+
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        const { from } = view.state.selection
+
+        const coords = view.coordsAtPos(from)
+        const containerRect = containerRef.value?.getBoundingClientRect()
+        if (!containerRect) return null
+
+        return {
+            left: coords.left - containerRect.left,
+            top: coords.top - containerRect.top + window.scrollY,
+            fontSize: 16,
+            fontFamily: 'monospace',
+        }
+    } catch (e) {
+        console.error('getCursorPosition error:', e)
+        return null
+    }
+}
+
+const fetchSuggestion = async (prefix, suffix) => {
+    try {
+        const res = await fetch(API_URL, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({ prefix, suffix, languageId: 'markdown' }),
+        })
+
+        // 修复：遵循"获取失败直接报错"原则
+        if (!res.ok) {
+            const errorText = await res.text()
+            throw new Error(`API request failed: ${res.status} - ${errorText}`)
+        }
+
+        const reader = res.body?.getReader()
+        if (!reader) {
+            throw new Error('No response body reader available')
+        }
+
+        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 || data.error) break
+                } catch (e) {
+                    // 忽略 JSON 解析错误，继续处理下一行
+                }
+            }
+        }
+
+        return text
+    } catch (e) {
+        // 修复：直接抛出错误，不返回空字符串
+        throw e
+    }
+}
+
+const onInput = async () => {
+    if (!crepe) return
+
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+        const { from } = view.state.selection
+
+        if (from === lastPos) return
+        lastPos = from
+
+        const prefix = view.state.doc.textBetween(0, from)
+        const suffix = view.state.doc.textBetween(from, view.state.doc.content.size)
+
+        // 修复：使用正确的字符串截取方法
+        console.log('Prefix preview:', prefix.slice(-50))
+
+        clearTimeout(debounceTimer)
+        debounceTimer = setTimeout(async () => {
+            try {
+                cursorRect.value = await getCursorPosition()
+                suggestion.value = await fetchSuggestion(prefix, suffix)
+            } catch (e) {
+                console.error('Failed to fetch suggestion:', e)
+                suggestion.value = ''
+            }
+        }, DEBOUNCE_MS)
+    } catch (e) {
+        console.error('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 = ''
+    }
+}
+
+const dismissSuggestion = () => {
+    suggestion.value = ''
+}
+
+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 = ''
+    }
+}
+
+const exportMarkdown = async () => {
+    if (!crepe) return
+    const markdown = await crepe.getMarkdown()
+    const blob = new Blob([markdown], { type: 'text/markdown' })
+    const url = URL.createObjectURL(blob)
+    const a = document.createElement('a')
+    a.href = url
+    a.download = `document-${Date.now()}.md`
+    a.click()
+    URL.revokeObjectURL(url)
+}
+
+// 修复：使用更可靠的事件绑定方式
+const initEditorEvents = () => {
+    if (!crepe) return
+
+    try {
+        const ctx = crepe.ctx.get()
+        const view = ctx.get('view')
+
+        // 直接在编辑器 DOM 上监听输入事件
+        view.dom.addEventListener('input', onInput)
+        view.dom.addEventListener('keydown', (e) => {
+            if (e.key === 'Tab') {
+                handleTab()
+            }
+        })
+    } catch (e) {
+        console.error('Failed to bind events:', e)
+    }
+}
 </script>
+
+<style scoped>
+.editor-container {
+    position: relative;
+}
+
+.export-btn {
+    position: fixed;
+    top: 20px;
+    right: 20px;
+    padding: 8px 16px;
+    background-color: #4a90d9;
+    color: white;
+    border: none;
+    border-radius: 4px;
+    cursor: pointer;
+    z-index: 1000;
+}
+
+.export-btn:hover {
+    background-color: #3a7bc8;
+}
+
+.milkdown-editor {
+    width: 100vw;
+    height: 100vh;
+    background-color: #ffffff;
+    overflow-y: auto;
+}
+
+.milkdown-editor::-webkit-scrollbar {
+    width: 8px;
+}
+
+.milkdown-editor::-webkit-scrollbar-track {
+    background: transparent;
+}
+
+.milkdown-editor::-webkit-scrollbar-thumb {
+    background-color: #ddd;
+    border-radius: 4px;
+}
+
+.milkdown-editor :deep(.milkdown) {
+    max-width: 900px;
+    margin: 0 auto !important;
+    padding: 20px 40px !important;
+    min-height: calc(100vh - 40px);
+}
+
+.milkdown-editor :deep(*) {
+    margin-top: 0 !important;
+    margin-bottom: 0 !important;
+    padding-top: 0 !important;
+    padding-bottom: 0 !important;
+}
+</style>
 ```
 
 ### Step 3: 更新 App.vue
@@ -67,8 +336,88 @@ import '@milkdown/crepe/theme/common/style.css'
 import '@milkdown/crepe/theme/frame.css'
 ```
 
+## 已知问题及修复方案
+
+### 🔴 严重问题（P0）
+
+#### 1. 模板语法错误
+**位置**: `MilkdownEditor.vue:7-13`
+**问题**: GhostTextOverlay 组件标签缺少尖括号
+**修复**: 使用正确的 Vue 组件标签语法 `<GhostTextOverlay>` 和 `</GhostTextOverlay>`
+
+#### 2. 字符串截取错误
+**位置**: `MilkdownEditor.vue:155`
+**问题**: `prefix.substring(-50)` 在 JavaScript 中会返回整个字符串
+**修复**: 改为 `prefix.slice(-50)` 或 `prefix.substring(prefix.length - 50)`
+
+#### 3. 错误处理违反原则
+**位置**: `MilkdownEditor.vue:92-94`
+**问题**: 请求失败时返回空字符串而不是抛出错误
+**修复**: 遵循"获取失败直接报错"原则，抛出异常而不是返回默认值
+
+### 🟡 中等问题（P1）
+
+#### 4. 内存泄漏风险
+**问题**: 组件卸载时没有清理 `debounceTimer`
+**修复**: 添加 `onUnmounted` 生命周期钩子，清理定时器和编辑器实例
+
+#### 5. 不可靠的事件绑定
+**问题**: 使用硬编码的 500ms 延迟等待编辑器创建
+**修复**: 在 `await crepe.create()` 后直接调用 `initEditorEvents()`
+
+#### 6. 代码重复
+**问题**: `fetchSuggestion` 逻辑在两个文件中重复
+**修复**: 将共享逻辑提取到独立的工具函数或服务中
+
+#### 7. 全局状态污染
+**问题**: 插件使用模块级全局变量
+**修复**: 使用 ProseMirror 插件的状态管理机制
+
+### 🟢 轻微问题（P2）
+
+#### 8. 大量调试日志
+**问题**: 代码中包含大量 `console.log` 调试语句
+**修复**: 移除或条件化调试日志
+
+#### 9. 缺少类型定义
+**问题**: TypeScript 代码中缺少完整的类型定义
+**修复**: 添加完整的 TypeScript 类型定义
+
+#### 10. 没有加载状态
+**问题**: 用户无法知道是否正在获取建议
+**修复**: 添加加载状态指示器
+
+#### 11. 建议文本无长度限制
+**问题**: 建议文本可能过长
+**修复**: 添加建议文本长度限制
+
+#### 12. API URL 硬编码
+**问题**: API URL 硬编码在前端代码中
+**修复**: 使用环境变量配置 API URL
+
+#### 13. 缺少 CORS 配置
+**问题**: 后端没有配置 CORS
+**修复**: 在 FastAPI 中添加 CORS 中间件
+
 ## 全屏覆盖样式要点
 
 - 编辑器容器: `width: 100vw; height: 100vh`
 - 移除默认 padding/margin
 - 纯编辑器模式，无预览面板
+- 自定义滚动条样式
+
+## 性能优化建议
+
+1. **防抖优化**: 保持 150ms 防抖，避免频繁请求
+2. **流式响应**: 使用 SSE 流式传输，降低延迟
+3. **上下文截取**: 智能截取上下文（光标前30行 + 后5行）
+4. **内存管理**: 及时清理定时器和事件监听器
+5. **代码精简**: 移除冗余代码和注释
+
+## 测试要点
+
+1. 编辑器基本功能测试
+2. 建议功能测试（Tab 接受、Esc 取消、点击接受）
+3. 错误处理测试（网络错误、API 错误）
+4. 性能测试（大量文本输入）
+5. 内存泄漏测试（长时间使用）

src/components/GhostTextOverlay.vue

@@ -1,43 +1,35 @@
 <template>
   <div v-if="visible" class="ghost-text-overlay" :style="overlayStyle"
        @click="acceptSuggestion"
-  >{{ suggestion }}
+  >{{ truncatedSuggestion }}
   </div>
 </template>
 
 <script setup>
 import { computed } from 'vue'
-import { onMounted, onUnmounted, watch } from 'vue'
 
 const props = defineProps({
     suggestion: { type: String, default: '' },
-    position: { type: Object, required: true },
+    position: {
+        type: Object,
+        required: true,
+        validator: (value) => typeof value.left === 'number' && typeof value.top === 'number'
+    }
 })
 
 const emit = defineEmits(['accept', 'dismiss'])
 
-onMounted(() => {
-    console.log('[GhostTextOverlay] Component mounted')
-    if (props.suggestion && props.position) {
-        console.log('[GhostTextOverlay] Suggestion visible:', props.suggestion.substring(0, 50))
-        console.log('[GhostTextOverlay] Position:', JSON.stringify(props.position))
-    }
-})
-
-onUnmounted(() => {
-    console.log('[GhostTextOverlay] Component unmounted')
-})
-
-watch([() => props.suggestion, () => props.position], ([newSuggestion, newPosition]) => {
-    console.log('[GhostTextOverlay] Props changed:', {
-        suggestionLength: newSuggestion?.length || 0,
-        hasPosition: !!newPosition,
-        positionKeys: newPosition ? Object.keys(newPosition) : []
-    })
-}, { immediate: true })
+const MAX_SUGGESTION_LENGTH = 200
 
 const visible = computed(() => props.suggestion && props.position)
 
+const truncatedSuggestion = computed(() => {
+    if (props.suggestion.length > MAX_SUGGESTION_LENGTH) {
+        return props.suggestion.slice(0, MAX_SUGGESTION_LENGTH) + '...'
+    }
+    return props.suggestion
+})
+
 const overlayStyle = computed(() => ({
     position: 'absolute',
     left: `${props.position.left}px`,
@@ -52,10 +44,7 @@ const overlayStyle = computed(() => ({
     zIndex: 1000,
 }))
 
-const acceptSuggestion = () => {
-    console.log('[GhostTextOverlay] acceptSuggestion called')
-    emit('accept')
-}
+const acceptSuggestion = () => emit('accept')
 </script>
 
 <style scoped>

src/components/MilkdownEditor.vue

@@ -4,178 +4,211 @@
     
     <div ref="root" class="milkdown-editor"></div>
 
-    GhostTextOverlay
+    <GhostTextOverlay
       v-if="suggestion && cursorRect"
       :suggestion="suggestion"
       :position="cursorRect"
       @accept="acceptSuggestion"
       @dismiss="dismissSuggestion"
-    /GhostTextOverlay
+    />
+
+    <div v-if="isLoading" class="loading-indicator">正在获取建议...</div>
   </div>
 </template>
 
 <script setup>
-import { onMounted, ref } from 'vue'
-import { Crepe, rootCtx, defaultValueCtx } from '@milkdown/crepe'
+import { onMounted, onUnmounted, ref } from 'vue'
+import { Crepe } from '@milkdown/crepe'
 import GhostTextOverlay from './GhostTextOverlay.vue'
-import { createInlineSuggestionPlugin } from '../plugins/inlineSuggestionPlugin'
+import { fetchSuggestion } from '../utils/api.js'
+import { DEBUG } from '../utils/config.js'
 
 const root = ref(null)
 const containerRef = ref(null)
 let crepe = null
+let editorElement = null
 
 const suggestion = ref('')
 const cursorRect = ref(null)
+const isLoading = ref(false)
+const lastFetchedContent = ref('')
+let debounceTimer = null
 
-const API_URL = 'http://localhost:8000/v1/completions'
+const DEBOUNCE_MS = 500
 
 onMounted(async () => {
-    console.log('[Debug] onMounted called')
-    if (!root.value) {
-        console.log('[Debug] root.value is null')
-        return
-    }
+    if (DEBUG) console.log('[Debug] onMounted called')
+    if (!root.value) throw new Error('root.value is null')
     
-    console.log('[Debug] Creating Crepe editor...')
-    const inlineSuggestionPlugin = createInlineSuggestionPlugin({ apiUrl: API_URL })
+    if (DEBUG) console.log('[Debug] Creating Crepe editor...')
     crepe = new Crepe({
         root: root.value,
-        defaultValue: '# Welcome to Milkdown\n\nStart writing your markdown content here...',
-        plugins: [inlineSuggestionPlugin],
+        defaultValue: '# Welcome to LLM in text\n\nStart writing your content here...',
     })
     
     await crepe.create()
-    console.log('[Debug] Crepe editor created')
+    if (DEBUG) console.log('[Debug] Crepe editor created')
+    
+    observeEditor()
 })
 
-const getCursorPosition = async () => {
-    if (!crepe) {
-        console.log('[Debug] getCursorPosition: crepe is null')
-        return null
+const observeEditor = () => {
+    if (!containerRef.value) throw new Error('containerRef.value is null')
+    
+    const observer = new MutationObserver(() => {
+        const editorEl = containerRef.value?.querySelector('.milkdown .editor') ||
+                        containerRef.value?.querySelector('.milkdown')
+        if (editorEl) {
+            editorElement = editorEl
+            bindEditorEvents(editorEl)
+            observer.disconnect()
+            if (DEBUG) console.log('[Debug] Editor element found and events bound')
+        }
+    })
+    
+    observer.observe(containerRef.value, {
+        childList: true,
+        subtree: true
+    })
+    
+    setTimeout(() => {
+        const existingEl = containerRef.value?.querySelector('.milkdown .editor') ||
+                          containerRef.value?.querySelector('.milkdown')
+        if (existingEl) {
+            editorElement = existingEl
+            bindEditorEvents(existingEl)
+            observer.disconnect()
+            if (DEBUG) console.log('[Debug] Editor element found immediately')
+        }
+    }, 100)
 }
 
-    try {
-        const ctx = crepe.ctx.get()
-        const view = ctx.get('view')
-        const { from } = view.state.selection
-        console.log('[Debug] Cursor position:', from)
+const bindEditorEvents = (editorEl) => {
+    editorEl.addEventListener('input', onInput)
+    editorEl.addEventListener('keydown', (e) => {
+        if (e.key === 'Tab') {
+            e.preventDefault()
+            handleTab()
+        }
+    })
+}
 
-        const coords = view.coordsAtPos(from)
+const getEditorContent = () => {
+    if (!editorElement) throw new Error('editorElement is null')
+    return editorElement.innerText || ''
+}
+
+const getCursorPositionFromDOM = () => {
+    if (!editorElement) throw new Error('editorElement is null')
+    const selection = window.getSelection()
+    if (!selection.rangeCount) throw new Error('No selection')
+    
+    const range = selection.getRangeAt(0)
+    const rect = range.getBoundingClientRect()
     const containerRect = containerRef.value?.getBoundingClientRect()
-        if (!containerRect) {
-            console.log('[Debug] containerRect is null')
-            return null
-        }
+    if (!containerRect) throw new Error('containerRect is null')
     
     return {
-            left: coords.left - containerRect.left,
-            top: coords.top - containerRect.top + window.scrollY,
+        left: rect.left - containerRect.left,
+        top: rect.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 getCursorPosition = async () => {
+    return getCursorPositionFromDOM()
 }
 
 const onInput = async () => {
-    if (!crepe) {
-        console.log('[Debug] onInput: crepe is null')
+    if (!editorElement) throw new Error('editorElement is null')
+    
+    const selection = window.getSelection()
+    if (!selection.rangeCount) return
+    
+    const range = selection.getRangeAt(0)
+    const from = range.startOffset
+    
+    const content = getEditorContent()
+    const prefix = content.slice(0, from)
+    const suffix = content.slice(from)
+    
+    if (DEBUG) console.log('[Debug] onInput triggered at position:', from)
+    
+    // 清除之前的定时器
+    if (debounceTimer) {
+        clearTimeout(debounceTimer)
+    }
+    
+    // 设置新的定时器 - 只有停止输入后才触发
+    debounceTimer = setTimeout(async () => {
+        if (DEBUG) console.log('[Debug] Debounce timeout reached, fetching suggestion...')
+        
+        // 检查是否已经有建议在显示，如果内容没变则跳过
+        if (suggestion.value && content === lastFetchedContent.value) {
+            if (DEBUG) console.log('[Debug] Content unchanged, skipping fetch')
             return
         }
         
+        isLoading.value = true
         try {
-        const ctx = crepe.ctx.get()
-        const view = ctx.get('view')
-        const { from } = view.state.selection
-        
-        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)
-        
             cursorRect.value = await getCursorPosition()
             suggestion.value = await fetchSuggestion(prefix, suffix)
-        console.log('[Debug] Suggestion updated:', suggestion.value ? 'yes' : 'no')
+            lastFetchedContent.value = content
+            if (DEBUG) console.log('[Debug] Suggestion updated:', suggestion.value ? 'yes' : 'no')
         } catch (e) {
-        console.error('[Debug] onInput error:', e)
+            if (DEBUG) console.error('[Debug] Fetch error:', e)
+        } finally {
+            isLoading.value = false
+            debounceTimer = null
         }
+    }, DEBOUNCE_MS)
 }
 
 const handleTab = () => {
     if (suggestion.value) {
-        const ctx = crepe.ctx.get()
-        const view = ctx.get('view')
-        view.dispatch(view.state.tr.insertText(suggestion.value))
+        const selection = window.getSelection()
+        if (!selection.rangeCount) return
+        
+        const range = selection.getRangeAt(0)
+        range.deleteContents()
+        
+        const textNode = document.createTextNode(suggestion.value)
+        range.insertNode(textNode)
+        
+        range.setStartAfter(textNode)
+        range.setEndAfter(textNode)
+        selection.removeAllRanges()
+        selection.addRange(range)
+        
         suggestion.value = ''
-        console.log('[Debug] Tab pressed, accepted suggestion')
+        if (DEBUG) console.log('[Debug] Tab pressed, accepted suggestion')
     }
 }
 
 const dismissSuggestion = () => {
     suggestion.value = ''
-    console.log('[Debug] Suggestion dismissed')
+    if (DEBUG) 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))
+        const selection = window.getSelection()
+        if (!selection.rangeCount) return
+        
+        const range = selection.getRangeAt(0)
+        range.deleteContents()
+        
+        const textNode = document.createTextNode(suggestion.value)
+        range.insertNode(textNode)
+        
+        range.setStartAfter(textNode)
+        range.setEndAfter(textNode)
+        selection.removeAllRanges()
+        selection.addRange(range)
+        
         suggestion.value = ''
-        console.log('[Debug] Suggestion accepted via click')
+        if (DEBUG) console.log('[Debug] Suggestion accepted via click')
     }
 }
 
@@ -190,6 +223,13 @@ const exportMarkdown = async () => {
     a.click()
     URL.revokeObjectURL(url)
 }
+
+onUnmounted(() => {
+    if (debounceTimer) {
+        clearTimeout(debounceTimer)
+        debounceTimer = null
+    }
+})
 </script>
 
 <style scoped>
@@ -197,7 +237,7 @@ const exportMarkdown = async () => {
     position: relative;
 }
 
-export-btn {
+.export-btn {
     position: fixed;
     top: 20px;
     right: 20px;
@@ -210,7 +250,7 @@ export-btn {
     z-index: 1000;
 }
 
-export-btn:hover {
+.export-btn:hover {
     background-color: #3a7bc8;
 }
 
@@ -247,4 +287,16 @@ export-btn:hover {
     padding-top: 0 !important;
     padding-bottom: 0 !important;
 }
+
+.loading-indicator {
+    position: fixed;
+    bottom: 20px;
+    right: 20px;
+    padding: 8px 16px;
+    background-color: #4a90d9;
+    color: white;
+    border-radius: 4px;
+    font-size: 14px;
+    z-index: 1000;
+}
 </style>

src/plugins/inlineSuggestionPlugin.ts

@@ -1,64 +1,58 @@
 import { Plugin, PluginKey } from '@milkdown/prose/state';
 import { EditorView } from '@milkdown/prose/view';
+import { fetchSuggestion } from '../utils/api.js';
+import { DEBUG, API_URL } from '../utils/config.js';
 
 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';
-    console.log('[InlineSuggestion] Plugin initialized with API URL:', apiUrl);
+interface InlineSuggestionState {
+    suggestion: string;
+    visible: boolean;
+    debounceTimer: ReturnType<typeof setTimeout> | null;
+    currentSuggestion: string;
+    suggestionPos: { from: number; to: number };
+}
 
-    return new Plugin({
+function createInlineSuggestionPlugin(options: InlineSuggestionOptions = {}) {
+    const apiUrl = options.apiUrl || API_URL;
+
+    return new Plugin<InlineSuggestionState>({
         key: INLINE_SUGGESTION_KEY,
         state: {
-            init: () => {
-                console.log('[InlineSuggestion] State initialized');
-                return { suggestion: '', visible: false };
-            },
+            init: () => ({
+                suggestion: '',
+                visible: false,
+                debounceTimer: null,
+                currentSuggestion: '',
+                suggestionPos: { from: 0, to: 0 }
+            }),
             apply: (tr, value) => {
-                if (!tr.docChanged) {
-                    console.log('[InlineSuggestion] No doc change in apply, returning same state');
-                    return value;
-                }
+                if (!tr.docChanged) return value;
                 const { from, to } = tr.selection;
-                console.log('[InlineSuggestion] Apply called - selection changed:', { from, to }, 'current suggestionPos:', suggestionPos);
-                if (from === suggestionPos.from && to === suggestionPos.to) {
-                    console.log('[InlineSuggestion] Selection matches suggestion position, keeping state');
+                if (from === value.suggestionPos.from && to === value.suggestionPos.to) {
                     return value;
                 }
-                const newState = { suggestion: '', visible: false };
-                console.log('[InlineSuggestion] Resetting suggestion state');
-                return newState;
+                return { ...value, suggestion: '', visible: false };
             },
         },
         props: {
             handleKeyDown: (view: EditorView, event: KeyboardEvent) => {
-                const currentState = INLINE_SUGGESTION_KEY.getState(view.state);
-                console.log('[InlineSuggestion] Key pressed:', event.key, 'suggestion visible:', currentState.visible);
-
-                if (event.key === 'Tab' && currentState.visible) {
+                const state = INLINE_SUGGESTION_KEY.getState(view.state);
+                if (event.key === 'Tab' && state.visible) {
                     event.preventDefault();
-                    const { suggestion } = currentState;
-                    console.log('[InlineSuggestion] Tab pressed - accepting suggestion:', suggestion.substring(0, 50));
-                    if (suggestion) {
-                        view.dispatch(view.state.tr.insertText(suggestion, view.state.selection.from));
-                        currentSuggestion = '';
+                    if (state.suggestion) {
+                        view.dispatch(view.state.tr.insertText(state.suggestion, view.state.selection.from));
                         return true;
                     }
                 }
                 if (event.key === 'Escape') {
-                    const state = INLINE_SUGGESTION_KEY.getState(view.state);
                     if (state.visible) {
-                        console.log('[InlineSuggestion] Escape pressed - dismissing suggestion');
-                        view.dispatch(view.state.tr.setMeta(INLINE_SUGGESTION_KEY, { suggestion: '', visible: false }));
-                        currentSuggestion = '';
+                        view.dispatch(view.state.tr.setMeta(INLINE_SUGGESTION_KEY, { ...state, suggestion: '', visible: false }));
                         return true;
                     }
                 }
@@ -67,85 +61,30 @@ function createInlineSuggestionPlugin(options: InlineSuggestionOptions = {}) {
         },
         appendTransaction: (transactions, oldState, newState) => {
             const lastTr = transactions[transactions.length - 1];
-            if (!lastTr || !lastTr.docChanged) {
-                console.log('[InlineSuggestion] No document change in transaction');
-                return null;
-            }
+            if (!lastTr || !lastTr.docChanged) return null;
 
-            console.log('[InlineSuggestion] Document changed, setting up debounce for', DEBOUNCE_MS, 'ms');
+            const currentState = INLINE_SUGGESTION_KEY.getState(newState);
             
-            clearTimeout(debounceTimer);
-            debounceTimer = setTimeout(async () => {
+            clearTimeout(currentState.debounceTimer);
+            currentState.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);
 
-                console.log('[InlineSuggestion] Debounce fired - position:', { from, to });
-                console.log('[InlineSuggestion] Prefix length:', prefix.length, 'Suffix length:', suffix.length);
-                console.log('[InlineSuggestion] Prefix (last 100):', prefix.slice(-100));
-                console.log('[InlineSuggestion] Suffix (first 100):', suffix.slice(0, 100));
-
                 try {
-                    console.log('[InlineSuggestion] Fetching from:', apiUrl);
-                    const res = await fetch(apiUrl, {
-                        method: 'POST',
-                        headers: { 'Content-Type': 'application/json' },
-                        body: JSON.stringify({ prefix, suffix, languageId: 'markdown' }),
-                    });
-
-                    console.log('[InlineSuggestion] Response status:', res.status);
-                    if (!res.ok) {
-                        const errorText = await res.text();
-                        console.error('[InlineSuggestion] API error:', errorText);
-                        return;
-                    }
-
-                    const reader = res.body?.getReader();
-                    if (!reader) {
-                        console.error('[InlineSuggestion] No response body reader');
-                        return;
-                    }
-
-                    let text = '';
-                    let chunkCount = 0;
-                    while (true) {
-                        const { done, value } = await reader.read();
-                        if (done) break;
-                        chunkCount++;
-                        const chunk = new TextDecoder().decode(value);
-                        console.log('[InlineSuggestion] Raw chunk', chunkCount, ':', chunk.substring(0, 200));
-
-                        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('[InlineSuggestion] Accumulated suggestion:', text.substring(0, 100));
-                                }
-                                if (data.done) {
-                                    console.log('[InlineSuggestion] Stream done signal received');
-                                    break;
-                                }
-                            } catch (e) {
-                                console.error('[InlineSuggestion] JSON parse error:', e);
-                            }
-                        }
-                    }
-
-                    console.log('[InlineSuggestion] Total chunks received:', chunkCount, 'Total text length:', text.length);
+                    const text = await fetchSuggestion(prefix, suffix, apiUrl);
 
                     if (text && newState.selection.from === from) {
-                        currentSuggestion = text;
-                        suggestionPos = { from, to: from + text.length };
-                        const metaUpdate = { suggestion: text, visible: true };
-                        console.log('[InlineSuggestion] Setting suggestion:', text.substring(0, 50), '...');
-                        newState.apply(newState.tr.setMeta(INLINE_SUGGESTION_KEY, metaUpdate));
-                    } else {
-                        console.log('[InlineSuggestion] Suggestion not applied - empty text or cursor moved');
+                        newState.apply(newState.tr.setMeta(INLINE_SUGGESTION_KEY, {
+                            ...currentState,
+                            currentSuggestion: text,
+                            suggestionPos: { from, to: from + text.length },
+                            suggestion: text,
+                            visible: true
+                        }));
                     }
                 } catch (e) {
-                    console.error('[InlineSuggestion] Error:', e);
+                    if (DEBUG) console.error('Inline suggestion error:', e);
                 }
             }, DEBOUNCE_MS);
 

src/utils/api.js

@@ -0,0 +1,52 @@
+import { DEBUG, API_URL } from './config.js'
+
+export async function fetchSuggestion(prefix, suffix, 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',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({ prefix, suffix, languageId: 'markdown' }),
+        })
+
+        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}`)
+        }
+
+        const reader = res.body?.getReader()
+        if (!reader) {
+            if (DEBUG) console.log('[Debug] No reader available')
+            throw new Error('No reader available')
+        }
+
+        let text = ''
+        while (true) {
+            const { done, value } = await reader.read()
+            if (done) break
+            const chunk = new TextDecoder().decode(value)
+            if (DEBUG) 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
+                        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:', e)
+                }
+            }
+        }
+        
+        if (DEBUG) console.log('[Debug] Final suggestion text:', text.substring(0, 100))
+        return text
+    } catch (e) {
+        if (DEBUG) console.error('[Debug] fetchSuggestion error:', e)
+        throw e
+    }
+}

src/utils/config.js

@@ -0,0 +1,2 @@
+export const DEBUG = import.meta.env.DEV
+export const API_URL = import.meta.env.VITE_API_URL || 'http://localhost:8000/v1/completions'