-
Nova - chat.nvim 的 Android 客户端
如果你已经在电脑上使用了 chat.nvim 这个 Neovim AI 对话插件，那么你一定会想知道：能否在手机上继续这些对话？
答案是可以的，chat.nvim 支持链接多种 IM 工具，包括微信、飞书、Telegram、Discord 等等。
和 IM 不同的是，Nova 是通过 chat.nvim 的 REST API 来链接各个会话，是一个专门为 chat.nvim 设计的 Android 客户端。
Nova 是什么？
Nova 是一个 Android 原生应用，它通过连接 chat.nvim 的 HTTP Server，让你可以在手机上继续你的 AI 对话。
简单来说：
- chat.nvim 运行在你的电脑上（Neovim 插件）
- HTTP Server 由 chat.nvim 提供（中间层）
- Nova 运行在你的手机上（Android 客户端）
核心特性
📱 移动端访问
在手机上继续你的 Neovim AI 对话，无需重新开始，历史记录完整同步。
💬 会话管理
- 查看所有会话列表
- 切换不同会话
- 创建新会话
- 删除不需要的会话
🎨 美观的界面
- Material Design 设计风格
- 区分用户和 AI 消息
- Markdown 渲染（支持代码高亮、表格、任务列表等）
🔒 本地存储
设置信息和会话列表保存在本地，保护你的隐私。
快速开始
前置条件
在手机上使用 Nova 之前，你需要：
- 安装 chat.nvim - 在你的电脑上安装 chat.nvim Neovim 插件
- 启动 HTTP Server - 在 Neovim 中启动 HTTP Server
安装 Nova
- 访问 Nova Releases 页面
- 下载最新的
ChatApp.apk - 在 Android 设备上安装（需要允许安装未知来源应用）
配置连接
首次使用需要配置服务器信息：
- 打开 Nova 应用
- 点击右上角「Settings」图标
- 填写服务器配置：
- 服务器地址: 运行 chat.nvim HTTP Server 的电脑 IP 地址
- 端口: HTTP Server 端口（默认 8000）
- API Key: 如果 chat.nvim 配置了验证，填写你的 API Key
- 点击保存
开始使用
配置完成后：
- 查看会话列表 - 打开应用显示所有会话
- 进入对话 - 点击会话进入聊天界面
- 新建会话 - 点击右下角按钮创建新会话
- 删除会话 - 长按会话项，选择删除
技术架构
技术栈
Nova 是一个原生 Android 应用，使用以下技术：
技术 说明 语言 Java 最低 SDK Android 7.0 (API 24) 目标 SDK Android 14 (API 34) UI 框架 AppCompat + Material Design 网络请求 OkHttp 4.12.0 Markdown Markwon 4.6.2 JSON 解析 org.json 工作原理
┌────────────────────┐ │ Tools / MCP │ │ (Editor) │ └────────────────────┘ ▲ │ Async Job ▼ ┌──────────────┐ HTTP API ┌──────────────┐ AI API ┌────────────┐ │ Nova │ ◄──────────► │ chat.nvim │ ◄────────► │ AI Model │ │ (Android) │ │ HTTP Server │ │ │ └──────────────┘ └──────────────┘ └────────────┘ ▲ │ │ user input / result ▼ ┌──────────────┐ │ Neovim │ │ Floating UI │ └──────────────┘数据流：
- Neovim 启动 chat.nvim HTTP Server（本地端口 8000）
- Nova（Android）配置服务器地址，连接到 HTTP Server
- 用户在 Nova 发送消息 → HTTP Server → AI Model
- AI 响应 → HTTP Server → Nova 显示
- 同时 Neovim 也能访问相同会话
重要: Nova 不直接连接大模型 API，而是通过 chat.nvim HTTP Server 作为中间层。
在家里、办公室、咖啡馆，无论在哪，只要你的电脑开启了 chat.nvim HTTP Server，就能通过手机随时访问。
与其他方案的对比
相比 Termux + Neovim
- ✅ 更轻量: 不需要在手机上安装完整的 Neovim 环境
- ✅ 更简单: 只需一个 APK，无需复杂配置
- ✅ 性能更好: 原生 Android 应用，启动快
- ❌ 依赖电脑: 需要电脑端运行 HTTP Server
相比直接调用 AI API
- ✅ 工具支持: 继承 chat.nvim 的工具调用能力
- ✅ 历史同步: 会话历史与电脑端同步
- ✅ 配置复用: 使用相同的配置和提示词
- ❌ 网络要求: 需要能访问到电脑端 HTTP Server
应用截图
会话列表 聊天界面 设置界面 后续计划
Nova 还在不断进化中，后续计划支持：
- 支持流式响应（SSE）
- 支持图片发送
- 支持语音输入
开发者信息
如果你是开发者，想要参与贡献：
- 项目地址: https://github.com/wsdjeg/Nova
- 技术栈: Java + Android SDK
- 开发环境: Android Studio Hedgehog 或更高版本
总结
Nova 是 chat.nvim 生态的重要补充，它打破了桌面环境的限制，让你可以在移动设备上继续使用 AI 辅助开发。无论你是在通勤路上、咖啡馆里，还是任何远离电脑的地方，只要有网络连接，就能随时访问你的 AI 助手。
相关项目：picker.nvim - Neovim fuzzy finder
如果你在使用过程中遇到问题，欢迎在 GitHub Issues 提交反馈！
-
curl 请求体长度限制问题及解决方案
起因
在开发 chat.nvim 插件时， 遇到了一个奇怪的错误：当使用 curl 发送较大的 JSON 请求体时， 会报错
ENAMETOOLONG: name too long。这个错误提示虽然明确，但背后的原因和解决方案却值得记录一下。问题背景
chat.nvim 是一个 Neovim 插件，用于在 Neovim 内集成 AI 助手功能。 在调用 AI API 时，需要使用 job.nvim 异步调用 curl 发送 POST 请求， 请求体是一个 JSON 对象，包含了模型名称、对话历史、工具定义等信息。
原始的实现方式是这样的：
local cmd = { 'curl', '-s', url, '-H', 'Content-Type: application/json', '-H', 'Authorization: Bearer ' .. api_key, '-X', 'POST', '-d', vim.json.encode({ model = requestObj.model, messages = requestObj.messages, stream = true, stream_options = { include_usage = true }, tools = require('chat.tools').available_tools(), }), } local jobid = job.start(cmd, { on_stdout = requestObj.on_stdout, on_stderr = requestObj.on_stderr, on_exit = requestObj.on_exit, })这种方式将 JSON 数据直接作为 curl 的
-d参数传递，看似没问题，但当对话历史较长或者工具定义较多时，JSON 数据会变得很大，导致命令行参数过长。问题分析
ENAMETOOLONG错误表明命令行参数超过了系统限制。不同操作系统对命令行参数长度有不同的限制：- Linux: 通常为 128KB 到 2MB（取决于
MAX_ARG_STRLEN） - macOS: 约 256KB
- Windows: 约 8KB 到 32KB（更严格的限制）
当 JSON 数据包含大量对话历史或工具定义时，很容易超过这些限制。比如，一个包含 50 条对话记录的请求，JSON 可能就有几十 KB，再加上 URL、Header 等参数，总长度很容易超标。
解决方案
curl 提供了一个非常实用的特性：使用
-d @-从 stdin 读取数据。这样就可以避免命令行参数长度限制，将请求体通过 stdin 传递给 curl。修改后的代码：
local cmd = { 'curl', '-s', url, '-H', 'Content-Type: application/json', '-H', 'Authorization: Bearer ' .. api_key, '-X', 'POST', '-d', '@-', -- 从 stdin 读取数据 } local body = vim.json.encode({ model = requestObj.model, messages = requestObj.messages, thinking = { type = 'enabled', }, stream = true, stream_options = { include_usage = true }, tools = require('chat.tools').available_tools(), }) local jobid = job.start(cmd, { on_stdout = requestObj.on_stdout, on_stderr = requestObj.on_stderr, on_exit = requestObj.on_exit, }) -- 通过 stdin 发送请求体 job.send(jobid, body) job.send(jobid, nil) -- 关闭 stdin，表示数据发送完毕关键变化：
-d参数从 JSON 字符串改为@-，表示从 stdin 读取- 将 JSON 数据单独编码为
body变量 - 启动 job 后，使用
job.send()通过 stdin 发送数据 - 最后发送
nil关闭 stdin，告诉 curl 数据已发送完毕
相关 commit
这个问题的修复记录在 commit
@3f4277：commit 3f427762779ff9ffe645fd6683195da0b234731d Author: Eric Wong <[email protected]> Date: Sun Feb 8 21:41:47 2026 +0800 fix: use stdin to send body use body as curl command argument cause error: `ENAMETOOLONG: name too long`修复涉及了三个 provider 文件：
deepseek.lua、github.lua、moonshot.lua，统一采用了 stdin 方式发送请求体。其他注意事项
在使用 stdin 发送数据时，有几个细节需要注意：
-
及时关闭 stdin：发送完数据后必须关闭 stdin，否则 curl 会一直等待更多数据，导致请求无法完成。使用
job.send(jobid, nil)或job.chanclose(jobid, 'stdin')都可以实现。 -
数据完整性：确保发送的 JSON 数据是完整的，不要分多次发送部分数据，除非你知道如何处理分块传输。
-
编码问题：确保发送的数据是正确的 UTF-8 编码，curl 默认期望 UTF-8。
总结
当使用 curl 发送大量数据时，不要将数据直接作为命令行参数传递，而应该使用 stdin（
-d @-）方式。这样可以：- 避免命令行参数长度限制
- 支持更大数据量的传输
- 更加稳定可靠
这个坑虽然看似简单，但在实际开发中却容易被忽视。记录下来，希望能帮助到遇到类似问题的开发者。
如果你也在开发类似的 HTTP 客户端功能，建议一开始就采用 stdin 方式，避免后续遇到这个问题。
- Linux: 通常为 128KB 到 2MB（取决于
-
阿里云 Coding Plan Bug：流式输出内容截断
问题背景
本文记录在使用 阿里云百炼平台 Coding Plan（GLM-5 模型） 时遇到的另一个严重 bug：流式输出内容截断。
上一篇博文记录了 Tool Call arguments 输出协议异常的问题，这一次遇到了更基础的问题：普通文本回复的内容被截断，直接丢失了最后的几个字符。
阿里云售后人员的回复是：”这是工具问题”。好吧，那就用这篇博文来证明，这根本不是工具问题。
问题现象
请求场景
在 chat.nvim 中使用 GLM-5 模型，发送最简单的问候消息 “你好”。这次请求完全没有触发 Tool Call，就是一次最普通的聊天对话。
完整原始日志（铁证）
以下是 curl stdout 的完整原始日志，逐行打印，未做任何删减：
data: {"choices":[{"delta":{"content":null,"reasoning_content":"用户","role":"assistant"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"说"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"\"你好"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"\"，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"这是一个简单的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"问候。"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"根据我的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"性格设定"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"，我应该"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"：\n1"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"."},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":" 热"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"情"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"友好\n"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"2."},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":" 简"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"洁直接"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"\n3"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"."},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":" 可能使用"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"一些表情"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"符号\n\n"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"我应该回忆"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"一下是否"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"有什么相关的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"记忆，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"比如用户的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"偏好等"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"。不过"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"这是一个新的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"对话开始"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"，我先"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"友好地"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"回应，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"看看用户"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"需要什么"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"帮助。\n\n"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"我应该：\n"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"-"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":" 友好"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"地问候"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"\n-"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":" 简单"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"介绍自己"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"可以"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"做什么\n"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"- "},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"询问需要"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"什么帮助"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"\n\n"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"不需要调用"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"任何工具"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"，只是"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"简单的对话"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":null,"reasoning_content":"问候。"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"你好！","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"我是 No","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"va，","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"来自 N","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"eovim 的小","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"星星 :","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":")","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"\n\n","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"我可以","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"帮","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"你：\n- 📝","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":" 编","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"写和修","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"改 ","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"Lu","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"a 插","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"件代码","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"\n- 🔍","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":" 搜","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"索、","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"阅读项目文件\n","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"- 📦","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":" Gi","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"t 操","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"作（提","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"交、","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"分支","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"管","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"理等）\n","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"- 💾","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":" 记","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"住你","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"的偏好和习","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"惯","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"\n- 🌐","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":" 搜索网","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"络、获","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"取网页内","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"容\n\n","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"有什么","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"delta":{"content":"我","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[{"finish_reason":"stop","delta":{"content":"","reasoning_content":null},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":16418,"completion_tokens":191,"total_tokens":16609,"completion_tokens_details":{"reasoning_tokens":106},"prompt_tokens_details":{"cached_tokens":16414}},"created":1776597535,"system_fingerprint":null,"model":"glm-5","id":"chatcmpl-f87aa751-9260-9884-8cb6-f33c540cab94"} data: [DONE]问题定位
从完整日志中可以清楚看到：
- 前面的
reasoning_content（思考过程）输出正常，从 “用户” 到 “问候。” 共 55 行 - 后面的
content（正式回复）开始输出，从 “你好！” 到功能介绍 - 关键截断点：最后一个有 content 的 chunk 是
{"content":"我"} - 紧接着就是一个
finish_reason: "stop"的 chunk，content 是空字符串 - 然后是 usage 统计和
[DONE]
按照正常的回复逻辑，AI 应该说 “有什么我可以帮你的吗？”，但实际只输出了 “有什么我”，后面的 7 个字符”可以帮你的吗？”直接丢失了。
这不是工具问题
请求原理
chat.nvim 的请求逻辑非常简单：
function M.request(opt) local cmd = { 'curl', '-s', 'https://coding.dashscope.aliyuncs.com/v1/chat/completions', '-H', 'Content-Type: application/json', '-H', 'Authorization: Bearer ' .. api_key, '-X', 'POST', '-d', '@-', -- 从 stdin 读取请求体 } -- 启动 job，通过 stdin 发送请求体 local jobid = job.start(cmd, { on_stdout = opt.on_stdout, -- 处理 stdout 输出 on_stderr = opt.on_stderr, on_exit = opt.on_exit, }) job.send(jobid, body) end解析逻辑
SSE 解析逻辑也只是简单地：
- 检测
data:前缀 - 解析 JSON
- 提取
content字段
if choice.delta.content and #choice.delta.content > 0 then sessions.on_progress(id, choice.delta.content) end为什么这不是工具问题
论点 证据 curl 只是传输层 curl 不做任何内容处理，只是把 stdout 原样输出 日志是完整原始输出 日志是逐行打印的，不存在截断或遗漏 SSE 格式正常 每个 chunk 都是合法的 data: {...}格式finish_reason 正确返回 服务端明确返回了 finish_reason: "stop"usage 统计显示完成 completion_tokens: 191表明模型认为已完成结论：服务端已经认为回复完成了（
finish_reason: "stop"），但实际输出不完整。这是服务端生成逻辑的 bug，客户端无法检测或修复。
可能的根因分析
推测的原因
根据输出特征，推测可能的原因：
- 提前终止生成：模型在生成过程中被服务端提前终止，但没有返回错误信息
- 缓冲区问题：最后几个 token 在缓冲区中被丢弃，未发送到客户端
- token 计数错误：服务端在某个阈值（如 completion_tokens 达到某个值）时错误地终止生成
- 流式输出同步问题：模型生成结束和服务端发送
finish_reason: stop的时机不同步
为什么 usage 显示 191 tokens
有趣的是，usage 显示
completion_tokens: 191，其中reasoning_tokens: 106。这意味着：- reasoning_content（思考）：约 106 tokens
- content（回复）：约 85 tokens（191 - 106）
但实际输出的 content 远少于 85 tokens（只有几个短句），说明：
- 要么：token 计数有误
- 要么：有大量 content 在服务端被丢弃
与 Tool Call Bug 的关联
上一篇博文记录的 Tool Call bug 是 arguments 输出协议异常。这次遇到的是更基础的 content 截断问题。
两个问题的共同特征：
特征 Tool Call Bug Content 截断 Bug 问题层级 协议层 内容生成层 表现形式 数据格式异常 数据丢失 影响范围 Tool Call 功能 所有回复 客户端可检测 ✅ 可以检测并容错 ❌ 无法检测 Content 截断 bug 更加隐蔽，因为：
- 格式合法：每个 SSE chunk 都是合法的 JSON，不会触发解析错误
- finish_reason 正常：服务端明确返回了
stop，客户端会认为正常完成 - 无错误信息：没有任何错误提示，客户端无法知道内容不完整
对用户的影响
实际影响
影响项 严重程度 回复不完整 高 功能介绍缺失 中 用户体验下降 高 无法自动检测 高 用户感知
用户发送消息后，收到的是不完整的回复。例如：
- 期望：”有什么我可以帮你的吗？”
- 实际：”有什么我”
用户可能会：
- 认为模型回答奇怪
- 再次发送消息询问
- 怀疑客户端有问题
无法修复
客户端无法修复这个问题，因为：
- 没有任何错误信息
finish_reason: "stop"表示正常结束- 客户端无法知道应该还有后续内容
唯一的”修复”方式是：用户自己发现回复不完整，手动再次询问。
给阿里云的建议
问题定性
这是一个 服务端内容生成层 bug，具体表现为：
- 流式输出在模型生成过程中提前终止
- 最后的 token 被丢弃，未发送到客户端
- 服务端错误地认为生成已完成，返回
finish_reason: "stop"
希望的修复
- 确保模型生成的所有 token 都正确发送到客户端
- 在
finish_reason: "stop"之前，确保所有 content 已完整输出 - 检查 token 计数逻辑，确保与实际输出一致
测试建议
建议阿里云增加以下测试：
# 简单测试：检查输出是否完整 curl -N https://coding.dashscope.aliyuncs.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_KEY" \ -d '{"model":"glm-5","messages":[{"role":"user","content":"你好"}],"stream":true}' \ > output.txt # 分析：最后一个 content chunk 后是否直接出现 finish_reason: stop grep "content" output.txt | tail -5 grep "finish_reason" output.txt
结论
又一次踩坑阿里云 Coding Plan。上一篇是 Tool Call 协议异常，这次是 Content 截断。
阿里云售后说”这是工具问题”，但本文已经清楚证明：
- curl 只是传输层，不做内容处理
- 日志是完整原始输出
- 服务端明确返回了
finish_reason: "stop" - 客户端无法检测或修复
这是服务端 bug，不是工具问题。
建议使用阿里云 Coding Plan 的开发者：
- 注意检查回复内容是否完整
- 发现截断时手动再次询问
- 向阿里云提交工单，附上原始日志
参考资料
- 前面的
-
阿里云 Coding Plan GLM-5 流式 Tool Call 异常输出
- content
问题背景
本文记录在使用 阿里云百炼平台 Coding Plan（GLM-5 模型） 时遇到的一个流式输出协议异常问题。请求客户端为 Neovim 插件 chat.nvim，通过
curl命令异步调用阿里云的流式聊天补全接口。在正常开发过程中，chat.nvim 需要调用大模型完成代码生成、问题解答等任务，并支持 Tool Call 功能以扩展模型能力。然而在实际使用中，发现当模型返回 Tool Call 响应时，SSE（Server-Sent Events）流中会夹杂未经封装的原始文本数据，导致客户端解析失败。
调用架构与实现
客户端请求实现
chat.nvim 底层使用 Neovim 的 job 系统异步执行 curl 命令，通过标准输入输出与服务端通信。核心请求函数如下：
function M.request(opt) local cmd = { 'curl', '-s', 'https://coding.dashscope.aliyuncs.com/v1/chat/completions', '-H', 'Content-Type: application/json', '-H', 'Authorization: Bearer ' .. config.config.api_key.aliyuncs_pc, '-X', 'POST', '-d', '@-', } local body = vim.json.encode({ model = sessions.get_session_model(opt.session), messages = opt.messages, enable_thinking = true, stream = true, stream_options = { include_usage = true }, tools = require('chat.tools').available_tools(), }) local jobid = job.start(cmd, { on_stdout = opt.on_stdout, on_stderr = opt.on_stderr, on_exit = opt.on_exit, }) job.send(jobid, body) job.send(jobid, nil) sessions.set_session_jobid(opt.session, jobid) return jobid end关键请求参数
参数 配置值 说明 服务端点 https://coding.dashscope.aliyuncs.com/v1/chat/completions阿里云百炼平台 API 模型 glm-5GLM-5 模型（Coding Plan） 流式输出 stream = true启用 SSE 流式响应 Tool Call tools = available_tools()注册可用工具函数 思考模式 enable_thinking = true启用模型思考过程 使用量统计 stream_options.include_usage = true返回 token 使用统计 请求体通过
curl -d @-从标准输入读取，job 系统通过job.send()将 JSON 编码的请求体发送给 curl 进程。响应数据通过on_stdout回调逐行接收，客户端需要实时解析 SSE 格式的数据流。
异常现象详述
正常的 SSE 流格式
符合 OpenAI 规范的 SSE 流式响应应当严格遵循以下格式，每一行都以
data:前缀开头，后面跟随完整的 JSON 对象或[DONE]标记：data: {"id":"chat-123","choices":[{"delta":{"content":"Hello"},"index":0}]} data: {"id":"chat-123","choices":[{"delta":{"content":" world"},"index":0}]} data: {"id":"chat-123","choices":[{"delta":{"content":"!"},"index":0}]} data: {"id":"chat-123","choices":[{"finish_reason":"stop","index":0}]} data: [DONE]客户端解析器通过检测
data:前缀识别有效数据行，使用vim.json.decode()解析 JSON 内容，遇到[DONE]标记时结束流式处理。实际收到的异常数据
在实际调用 GLM-5 模型时，收到的响应流中出现了不符合 SSE 规范的裸文本数据：
data: {"id":"chat-456","choices":[{"delta":{"content":"请查看"},"index":0}]} data: {"id":"chat-456","choices":[{"delta":{"tool_calls":[{"id":"call_1","function":{"name":"read_file","arguments":""},"index":0}]}]} ts from you under this License for any purpose whatsoever, with or without data: {"id":"chat-456","choices":[{"delta":{"tool_calls":[{"function":{"arguments":"\"--filepath\""},"index":0}]}]} data: {"id":"chat-456","choices":[{"finish_reason":"tool_calls","index":0}]} data: [DONE]可以看到在第 2 行和第 3 行之间，插入了两行没有
data:前缀的纯文本内容。这些文本实际上是 Tool Call 的arguments参数值的一部分，应该是 GPL 许可证文本的片段。以上是使用 openai 协议进行请求，切换到 anthropic 协议进行请求，比如发送一句
写一篇1200个单词的文章到 hello.txtdata:{"type":"content_block_start","content_block":{"name":"write_file","input":{},"id":"toolu_tool-5f54e710c4364f5b9a5d0cafb65f246d","type":"tool_use"},"index":2} data:{"delta":{"partial_json":"","type":"input_json_delta"},"type":"content_block_delta","index":2} tracking every change. Integrated development environments provide sophisticated features like syntax highlighting, code completion, and debugging tools that enhance productivity. Testing frameworks help ensure code correctness, while continuous integration systems automate the process of building and deploying software.\\n\\nThe methodology of software development has also evolved significantly. The waterfall model, with its sequential phases of requirements, design, implementation, testing, and deployment, gave way to more flexible approaches like Agile and DevOps. These methodologies recognize that software development is inherently iterative, that requirements change, and that the ability to adapt quickly is more valuable than rigid adherence to an initial plan. The rise of microservices architecture, containerization, and cloud computing has further transformed how we build and deploy applications, emphasizing modularity, scalability, and resilience.\\n\\nBut programming is not just about tools and techniques; it is fundamentally about problem-solving. Every program begins with a problem, a gap between what is and what should be. The programmer's task is to bridge this gap, to transform a vague desire into a concrete solution. This transformation requires analytical thinking, the ability to break complex problems into smaller, manageable pieces, and creative synthesis, the skill of assembling these pieces into a coherent whole that addresses the original problem.\\n\\nThe cognitive processes involved in programming are fascinating and still not fully understood. Studies have shown that expert programmers use mental models to understand code, building representations of program state and simulating execution in their minds. They recognize patterns, draw on past experiences, and employ heuristics to navigate the vast space of possible solutions. This expertise develops over time, through thousands of hours of practice, and involves not just technical knowledge but also domain understanding, communication skills, and the ability to work effectively in teams.\\n\\nDebugging exemplifies the problem-solving nature of programming. When a program does not behave as expected, the programmer must become a detective, gathering evidence, forming hypotheses, and testing them systematically. This process requires both deductive reasoning—working from general principles to specific conclusions—and inductive reasoning—inferring general patterns from specific observations. It demands patience, attention to detail, and the humility to recognize that our initial assumptions are often wrong.\\n\\nThe social dimension of programming has grown increasingly important. Open-source software development demonstrates how communities can collaborate on a global scale, contributing code, documentation, and support to projects that benefit millions. Platforms like GitHub and GitLab have made it easier than ever to share code, review contributions, and coordinate efforts across time zones and languages. The open-source movement has not only produced valuable software but has also established new norms of transparency, collaboration, and shared ownership.\\n\\nProgramming also raises profound philosophical questions about the nature of intelligence, creativity, and agency. As we develop more sophisticated artificial intelligence systems, we must grapple with questions about whether machines can truly think, create, or understand. The code we write increasingly influences critical decisions in healthcare, finance, criminal justice, and other domains, raising ethical questions about bias, accountability, and transparency. The responsibility that comes with this power requires programmers to consider not just what they can do, but what they should do.\\n\\nLearning to program is a journey that never truly ends. The field evolves rapidly, with new languages, frameworks, and tools emerging constantly. Staying current requires continuous learning, a willingness to embrace new paradigms, and the humility to recognize that there is always more to learn. Yet the fundamentals—algorithmic thinking, abstraction, modularity, testing—remain remarkably stable. Mastering these fundamentals provides a foundation that enables adaptation to whatever new technologies emerge.\\n\\nFor those beginning this journey, the path may seem daunting. The syntax alone can be overwhelming, and error messages are often cryptic. But with persistence and practice, the fog begins to lift. Lines of code that once seemed impenetrable become readable, even elegant. Problems that seemed impossible become manageable challenges. The joy of solving a difficult problem, of seeing a program run correctly after hours of debugging, of building something that helps others—these are the rewards that keep programmers engaged.\\n\\nIn conclusion, programming is a multifaceted discipline that combines technical skill with creative thinking, individual effort with collaborative practice, and practical problem-solving with philosophical reflection. It is a craft that rewards patience, curiosity, and persistence. Whether you are writing a simple script to automate a tedious task or building a complex distributed system that serves millions of users, the fundamental challenges and joys of programming remain the same. It is about translating human intentions into machine actions, about building tools that extend our capabilities, and about participating in the ongoing project of shaping the digital world we all inhabit.\"}","type":"input_json_delta"},"type":"content_block_delta","index":2} data:{"type":"content_block_stop","index":2}上述是 anthropic 协议请求时的返回内容，第三行文字是无效数据。
异常数据特征分析
通过对多次请求的原始响应进行比对，总结出以下异常特征：
特征 表现 出现频率 裸文本行 无 data:前缀的纯文本每次 Tool Call 必现 内容来源 Tool Call arguments 字符串片段 100% 出现位置 tool_calls delta 输出过程中 100% content 输出 正常 SSE 格式 不受影响 finish_reason 正确返回 tool_calls 不受影响 JSON 完整性 tool_call JSON 被截断 100% 这些特征表明问题具有高度一致性，并非网络传输错误或偶发异常，而是服务端实现层面的系统性问题。
根因分析
问题本质：协议层混流
该问题的本质是服务端在流式输出过程中，存在两条独立的输出通道被错误地混合写入同一个 HTTP 响应流：
输出类型 预期通道 实际通道 状态 普通内容 (content) SSE JSON 封装 SSE JSON 封装 ✅ 正常 Tool Call 参数 (arguments) SSE JSON 封装 原始 stdout 直写 ❌ 异常 正常情况下，所有输出内容都应当经过 SSE 协议封装层，统一格式化为
data: {...}后写入 HTTP 响应体。但实际实现中，Tool Call 的 arguments 生成逻辑绕过了封装层，直接将 token 写入输出流。推测的错误实现
根据输出特征，推测服务端可能存在类似以下的错误实现：
// ❌ 错误实现示意 func streamToolCallArguments(tokens []string, writer http.ResponseWriter) { for _, token := range tokens { // 错误：直接写入原始 token，未经过 SSE 封装 writer.Write([]byte(token)) writer.(http.Flusher).Flush() } } // ✅ 正确实现应当是 func streamToolCallArguments(tokens []string, writer http.ResponseWriter) { for _, token := range tokens { // 正确：构造完整的 SSE 消息 message := SSEMessage{ Choices: []Choice{ { Delta: Delta{ ToolCalls: []ToolCall{ { Function: Function{ Arguments: token, }, }, }, }, }, }, } fmt.Fprintf(writer, "data: %s\n\n", json.Marshal(message)) writer.(http.Flusher).Flush() } }为什么会出现”半截字符串”
观察到的裸文本如
ts from you under实际上是 arguments 字符串的中间片段。这是因为：- Token 级流式输出：模型生成 arguments 时按 token 逐个输出，而非等待完整字符串生成后一次性输出
- 写入时机错误：每个 token 生成后立即被写入输出流，但未经过 JSON 转义和 SSE 封装
- 边界不匹配：token 切分点与 JSON 字符串边界不一致，导致输出的是字符串中间片段
例如，当 arguments 应该是
"GPL License text from you under this License"时，实际输出可能是：data: {"arguments":"GPL Licen"} // 正常 SSE se text from you under // 裸文本（错误） this License" // 裸文本（错误） data: {"arguments":""} // 正常 SSE通道混用的可能原因
从软件工程角度分析，这种问题通常由以下原因导致：
- 代码路径分支：content 输出和 tool_call 输出走了不同的代码路径，其中一条路径遗漏了封装逻辑
- 历史遗留代码：可能在迭代过程中，tool_call 功能是后期添加的，复用了旧的输出接口
- 测试覆盖不足：缺少对原始 HTTP 响应流的协议一致性测试，仅测试了最终解析结果
- 多团队协作：流式输出模块和 Tool Call 模块可能由不同团队开发，接口约定不清晰
对客户端的影响
chat.nvim 解析器行为
chat.nvim 的 SSE 解析器期望每一行输入都是合法的
data: {...}格式，当遇到裸文本时会出现以下问题：-- 简化的解析逻辑 local function parse_sse_line(line) local data = line:sub(7) -- 去掉 "data: " 前缀 return vim.json.decode(data) -- 裸文本会导致这里报错 end当输入行为
ts from you under时：line:sub(7)返回 ` from you under`（或原样返回，如果行长度不足 7）vim.json.decode()尝试解析非 JSON 字符串，抛出异常- 异常可能导致整个流式处理中断，Tool Call 无法完成
实际影响范围
影响项 严重程度 说明 JSON 解析失败 高 vim.json.decode()抛出异常Tool Call 识别失败 高 arguments 内容不完整，无法调用工具 流式输出中断 中 可能触发错误处理逻辑，提前终止 用户体验下降 中 功能不可用或响应异常 错误日志污染 低 产生大量解析错误日志 临时容错方案
在无法修改服务端的情况下，客户端可以增加容错逻辑，过滤非法数据行：
local function safe_parse_sse(line) -- 严格过滤：只处理以 "data: " 开头的行 if not line:match("^data: ") then vim.log.warn("跳过非法 SSE 行：" .. line) return nil end local ok, result = pcall(function() local content = line:sub(7) if content == "[DONE]" then return "DONE" end return vim.json.decode(content) end) if not ok then vim.log.warn("JSON 解析失败：" .. result) return nil end return result end -- 在 on_stdout 回调中使用 on_stdout = function(_, data) for line in data:gmatch("[^\n]+") do local parsed = safe_parse_sse(line) if parsed then handle_chunk(parsed) end end end该方案的核心思想是严格过滤 + 静默丢弃，遇到非法数据行时记录警告日志但不中断处理流程。这样可以保证在服务端修复问题之前，客户端仍能正常工作。
调试与验证方法
保存原始响应
使用 curl 直接请求并保存完整响应，便于离线分析：
curl -N \ https://coding.dashscope.aliyuncs.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "glm-5", "messages": [ {"role": "user", "content": "请读取当前目录下的 LICENSE 文件"} ], "stream": true, "tools": [ { "type": "function", "function": { "name": "read_file", "parameters": { "type": "object", "properties": { "filepath": {"type": "string"} } } } } ] }' \ > raw_response.txt参数说明：
-N：禁用缓冲，实时输出raw_response.txt：保存完整原始响应
分析响应内容
# 统计总行数 wc -l raw_response.txt # 查看非 data: 开头的行（非法行） grep -v "^data: " raw_response.txt # 统计非法行数量 grep -cv "^data: " raw_response.txt # 查看非法行的上下文（前后各 2 行） grep -v "^data: " -B 2 -A 2 raw_response.txt # 提取所有 data: 行并验证 JSON 格式 grep "^data: " raw_response.txt | \ sed 's/^data: //' | \ while read line; do echo "$line" | jq . 2>/dev/null || echo "INVALID: $line" done验证 Tool Call 完整性
# 提取所有 tool_calls 相关的行 grep "tool_calls" raw_response.txt # 检查 arguments 字段是否完整 grep "arguments" raw_response.txt | \ sed 's/^data: //' | \ jq '.choices[0].delta.tool_calls[0].function.arguments'如果 arguments 字段显示不完整或解析失败，说明存在数据污染。
结论与建议
问题定性
该问题属于服务端协议层实现缺陷，具体表现为：
- 非客户端问题：chat.nvim 的 SSE 解析逻辑符合 OpenAI 规范
- 非网络问题：裸文本稳定出现，非传输错误
- 非偶发问题：每次 Tool Call 必现，具有可复现性
- 协议级错误：违反 SSE 协议规范，混合输出不同格式数据
根本原因
Tool Call 的 arguments 在流式生成过程中未被正确封装进 SSE 消息格式，导致原始 token 直接泄漏到 HTTP 响应流中。这反映了服务端在流式输出模块和 Tool Call 模块的集成测试不足。
解决建议
对服务端（阿里云）：
- 修复 arguments 输出路径，确保所有输出经过 SSE 封装层
- 增加协议一致性测试，验证响应流符合 SSE 规范
- 提供问题追踪和修复时间表
对客户端（chat.nvim）：
- 增加 SSE 行过滤逻辑，容忍非法数据
- 记录详细的解析错误日志，便于问题诊断
- 考虑增加协议一致性检查，主动检测服务端问题
后续跟进
建议将原始响应日志提交给阿里云技术支持，附上：
- 完整的
raw_response.txt文件 - 请求参数和调用时间
- 问题复现步骤
- 期望的正确输出格式
参考资料
-
job.nvim raw 参数导致 JSON 解析失败
起因
最近在使用 job.nvim 执行一些命令时，遇到了一个奇怪的问题。当我执行一个返回 JSON 数据的命令时，发现 JSON 数据无法被正确解析，总是报错
unexpected end of JSON。经过调试后发现，问题出在 job.nvim 的raw参数默认值上。问题复现
假设我们有一个命令，它会输出一个较大的 JSON 数据：
local job = require('job') local result = {} local jobid = job.start({ 'some-command-that-outputs-json' }, { on_stdout = function(id, data) for _, line in ipairs(data) do table.insert(result, line) end end, on_exit = function(id, code, signal) local json_str = table.concat(result, '') local ok, decoded = pcall(vim.json.decode, json_str) if not ok then print('JSON decode failed: ' .. decoded) else print('JSON decoded successfully') vim.print(decoded) end end, })执行上述代码后，可能会看到类似以下的错误：
JSON decode failed: Expected object key string but found null at character 1024或者在解析时直接报错：
JSON decode failed: Expected value but found T_END at character 1问题分析
要理解这个问题，需要先了解 job.nvim 的
raw参数的作用。查看 job.nvim 的源码，可以看到：--- @class JobOpts --- @field on_stderr? function --- @field on_exit? fun(id: integer, code: integer, signin: integer) --- @field on_stdout? function --- @field cwd? string --- @field detached? boolean --- @field clear_env? boolean --- @field env? table<string, string|number> --- @field encoding? string --- @field raw? booleanraw参数默认是nil（即false），这意味着使用行缓冲模式。在这种模式下，数据会通过buffered_data函数处理：---@param eof string ---@param data string local function buffered_data(eof, data) data = data:gsub('\r\n', '\n') local std_data = vim.split(data, '\n') if #std_data > 1 then std_data[1] = eof .. std_data[1] eof = std_data[#std_data] == '' and '' or std_data[#std_data] table.remove(std_data, #std_data) elseif #std_data == 1 then if std_data[1] == '' and eof ~= '' then std_data = { eof } eof = '' elseif std_data[1] == '' and eof == '' then std_data = {} elseif std_data[#std_data] ~= '' then eof = std_data[#std_data] std_data = {} end end return eof, std_data end这个函数的逻辑是：
- 将
\r\n替换为\n - 按换行符
\n分割数据 - 处理不完整的行，保存到
eof变量中等待下一次数据
问题在于：大多数 JSON 输出是不包含换行符的单行数据，或者是一个格式化的多行 JSON。当 JSON 数据较大时，可能会被系统分成多个数据块（chunk），但每个数据块内部可能没有换行符。
在这种情况下，
buffered_data函数会：- 如果数据块中没有换行符，会将整个数据块视为一个”不完整的行”，保存到
eof中 - 此时
std_data是空的，不会触发on_stdout回调 - 只有当下一个数据块到来或者 EOF 时，才会将之前保存的数据输出
这样就导致了数据在缓冲区中累积，但
on_stdout回调可能不会及时接收到数据。更糟糕的是，如果 JSON 数据本身就包含换行符（格式化的 JSON），会被错误地分割成多行。对比两种模式
默认模式（raw = false）
-- Default: line-buffered mode uv.read_start(stdout, function(_, data) if data then local stdout_data _jobs['jobid_' .. current_id].state.stdout_eof, stdout_data = buffered_data( _jobs['jobid_' .. current_id].state.stdout_eof, data ) if #stdout_data > 0 then vim.schedule(function() if opts.encoding then stdout_data = vim.tbl_map(function(t) return vim.fn.iconv(t, opts.encoding, 'utf-8') end, stdout_data) end opts.on_stdout(current_id, stdout_data) end) end return end -- ... EOF handling end)Raw 模式（raw = true）
-- Raw mode: no buffering, pass raw data chunks directly if opts.raw then uv.read_start(stdout, function(_, data) if data then vim.schedule(function() if opts.encoding then data = vim.fn.iconv(data, opts.encoding, 'utf-8') end if nparams == 2 then opts.on_stdout(current_id, { data }) else opts.on_stdout(current_id, { data }, 'stdout') end end) else -- EOF if stdout and not stdout:is_closing() then stdout:close() end end end) end可以看到，
raw = true模式下：- 不进行行缓冲处理
- 直接将原始数据块传递给回调函数
- 数据可能会被分成多个块，每个块都是不完整的
解决方案
针对 JSON 数据解析的场景，有以下几种解决方案：
方案一：使用 raw 模式并手动拼接数据
local job = require('job') local result = {} local jobid = job.start({ 'some-command-that-outputs-json' }, { raw = true, -- 使用原始模式 on_stdout = function(id, data) -- data 是一个包含原始数据块的列表 for _, chunk in ipairs(data) do table.insert(result, chunk) end end, on_exit = function(id, code, signal) local json_str = table.concat(result, '') local ok, decoded = pcall(vim.json.decode, json_str) if not ok then print('JSON decode failed: ' .. decoded) else print('JSON decoded successfully') vim.print(decoded) end end, })方案二：在默认模式下正确处理数据
如果 JSON 数据是单行输出（minified JSON），需要在
on_exit回调中处理缓冲区中剩余的数据：local job = require('job') local result = {} local jobid = job.start({ 'some-command-that-outputs-json' }, { on_stdout = function(id, data) for _, line in ipairs(data) do -- 如果 JSON 是格式化的多行，需要保留换行符 table.insert(result, line) end end, on_exit = function(id, code, signal) -- 拼接所有行，如果是 minified JSON，不需要换行符 -- 如果是格式化 JSON，需要添加换行符 local json_str = table.concat(result, '\n') local ok, decoded = pcall(vim.json.decode, json_str) if not ok then print('JSON decode failed: ' .. decoded) else print('JSON decoded successfully') vim.print(decoded) end end, })方案三：使用 luv 的 stream API
如果需要更精细的控制，可以直接使用
vim.loop(或vim.uv) 的 stream API：local uv = vim.uv or vim.loop local stdout = uv.new_pipe() local result = {} local handle, pid = uv.spawn('some-command', { stdio = { nil, stdout, nil }, }, function(code, signal) stdout:close() handle:close() local json_str = table.concat(result, '') local ok, decoded = pcall(vim.json.decode, json_str) if not ok then print('JSON decode failed: ' .. decoded) else print('JSON decoded successfully') vim.print(decoded) end end) uv.read_start(stdout, function(err, data) if data then table.insert(result, data) end end)实际案例
在我开发的 chat.nvim 插件中，调用 AI API 时返回的就是 JSON 数据。最初使用默认模式时，遇到了数据解析失败的问题。
查看调试日志：
[ 14:23:42:123 ] [ Info ] Received chunk 1: {"id":"chatcmpl-123","object":"chat.completion","created":1234567890 [ 14:23:42:125 ] [ Info ] Received chunk 2: ,"model":"gpt-4","choices":[{"index":0,"message":{"role":"assistant" [ 14:23:42:127 ] [ Info ] Received chunk 3: ,"content":"Hello"},"finish_reason":"stop"}]}可以看到，JSON 数据被分成了 3 个数据块，每个块都不完整。在默认模式下，这些数据会被缓冲，等待换行符，但 JSON 数据中没有换行符，导致数据一直在缓冲区中。
使用
raw = true后，可以正确地接收并拼接这些数据块：local job = require('job') local chunks = {} job.start(cmd, { raw = true, on_stdout = function(id, data) for _, chunk in ipairs(data) do table.insert(chunks, chunk) end end, on_exit = function(id, code, signal) local json_str = table.concat(chunks, '') -- 现在可以正确解析 JSON local response = vim.json.decode(json_str) -- 处理响应数据 end, })总结
job.nvim 的
raw参数默认为false，使用行缓冲模式，适合处理以行为单位的文本输出（如日志、命令输出等）。但如果要处理二进制数据或单行的大型 JSON 数据，应该设置raw = true，然后在回调函数中手动拼接数据块。理解
raw参数的作用对于正确处理外部命令的输出非常重要：- raw = false（默认）：行缓冲模式，按换行符分割数据，确保每次回调传递完整的行
- raw = true：原始模式，直接传递数据块，适合处理二进制数据或需要手动拼接的场景
在使用 job.nvim 处理 JSON 数据时，建议使用
raw = true并在on_exit回调中拼接所有数据块后再进行解析。
- 将
-
为什么仍然在使用 job.nvim
起因
job.nvim 发布了 1.5 版本，和往常一样，我在 Reddit 上发布了版本更新文章，也很感谢有不少正面的反馈。
但让我无法理解的是，有些人似乎很难沟通，他们一再强调 Neovim 有内置的
jobstart()和vim.system()，为什么还要创建一个新的插件？即使解释了原因，他们仍然无法理解。我想这可能是我说得不够清楚，因此在这里整理一下前因后果。说起 Job 函数，要从最早期的 Neovim 版本说起。Neovim 增加了一个
jobstart()Vim Script 函数，那时候 Vim 还没有 Job 功能，后来 Vim 才增加了job_start()函数，但其调用方式与 Neovim 并不一致。早期的 Neovim 主要还是以使用 VimL 为主。于是我给 SpaceVim 添加了一个 Job API，以兼容早期 Neovim 的
jobstart()和 Vim 的job_start()函数。commit 44ad1cb4fe6a8d9ccae49b71994e6182bbcaa968 Author: wsdjeg <[email protected]> Date: Fri Mar 31 21:09:38 2017 +0800 Add job api for vim and neovim这样，就可以使用相同的函数同时兼容 Vim 和 Neovim。
let s:JOB = SpaceVim#api#import('job') let s:command = ['echo', 'hello world'] function! s:stdout(id, data, event) " data 是一个字符串列表 for line in a:data echo line endfor endfunction call s:JOB.start(s:command, { \ 'on_stdout' : function('s:stdout'), \ } \ )在这个过程中，前后还遇到过很多兼容性问题。Neovim 的
jobstart()函数的 stdout callback 在数据过大时会被截断，具体的 buffer size 我记不清了，有个 issue 讨论过这个问题。于是，我在这个 API 中增加了data_eol检测，以确保 callback 函数被调用时传入的是完整的数据。当然，后来的 Neovim 官方文档里也写了如何处理这种数据被截断的情况，详见:h channel_buffered。使用 Lua 重写 job API
随着 Neovim 对 Lua 的支持越来越多，我后来使用 Lua 重写了 Job API，但仍然将其内置在 SpaceVim 里。重写之后，调用就可以直接使用 Lua 了。
commit 879129388ab22b64c5a5cf0df83799084cab96fc Author: Eric Wong <[email protected]> Date: Wed Jul 5 22:58:01 2023 +0800 feat(api): add lua job api close https://github.com/neovim/neovim/issues/20856调用方式变成了 Lua：
local job = require('spacevim.api.job') local jobid = job.start(vim.g.test_ctags_cmd, { on_stdout = function(id, data, event) vim.print(id) vim.print(data) vim.print(event) end, on_stderr = function(id, data, event) vim.print(id) vim.print(data) vim.print(event) end, on_exit = function(id, code, signal) vim.print(id) vim.print('exit code', code) vim.print('exit signal', signal) end, })独立成 job.nvim
随着 SpaceVim 项目停止维护，我把我常用的功能插件独立成了各个单独的 Neovim 插件，其中就包括了 job.nvim。
我自己写的很多需要异步执行命令的 Neovim 插件都依赖这个 job.nvim，这样就不需要在每个插件仓库里单独维护执行外部命令的模块了。使用起来也比原来的 SpaceVim 内置 Lua Job API 更简洁一些：
local job = require('job') local function on_exit(id, code, signal) print('job ' .. id .. ' exit code:' .. code .. ' signal:' .. signal) end local cmd = { 'echo', 'hello world' } local jobid1 = job.start(cmd, { on_stdout = function(id, data) vim.print(data) end, on_exit = on_exit, }) vim.print(string.format('jobid is %s', jobid1)) local jobid = job.start({ 'cat' }, { on_stdout = function(id, data) vim.print(data) end, on_exit = function(id, code, signal) print('job ' .. id .. ' exit code:' .. code .. ' signal:' .. signal) end, }) job.send(jobid, { 'hello' }) job.chanclose(jobid, 'stdin')为什么不切换到 vim.system
我不太记得
vim.system是什么时候加入到 Neovim 的了，其前后应该也功能迭代过几个版本。为什么我还在继续维护 job.nvim 而不切换到vim.system呢？-
没有对 stdout 数据进行拼接处理，容易有截断数据，而且传给 callback 函数的数据是 string 而非像
jobstart那样是 string 列表。当然，数据类型都是次要的事情，使用split函数很容易得到列表，但是未做数据拼接这点，在写 callback 函数时会增加很多额外的代码量。 -
callback 函数内无法确认到底是哪个 job 调用触发的这个 callback 函数，应该像
jobstart()的 stdout callback 函数那样，传入一个 jobid 参数。
我创建 job.nvim 的主要原因是：
在旧的 Neovim 版本中，没有
vim.system。第一个版本是 job.vim，它使用 VimL，并以与 Neovim 的jobstart相同的 API 支持 Neovim 和 Vim。我需要为不同的 job 的 stdout 使用相同的 callback 函数。例如，在我的插件管理器 https://github.com/wsdjeg/nvim-plug 中，当同时克隆 8 个插件时，我需要在 job 退出前显示每个 job 的进度。因此在 stdout callback 函数中，我需要知道是哪个 job 触发了这个 callback 函数。据我所知，即使现在的
vim.system的 stdout callback 也不支持这个功能。两种写法，哪种更简单方便，一目了然：
使用
vim.system:local function on_stdout(err, data) --- 首先，这里需要对 data 判断数据的完整性，然后参考以下鬼方法来拼接： -- There are two ways to deal with this: -- - 1. To wait for the entire output, use |channel-buffered| mode. -- - 2. To read line-by-line, use the following code: >vim -- let s:lines = [''] -- func! s:on_event(job_id, data, event) dict -- let eof = (a:data == ['']) -- " Complete the previous line. -- let s:lines[-1] .= a:data[0] -- " Append (last item may be a partial line, until EOF). -- call extend(s:lines, a:data[1:]) -- endf -- 然后，拼接完成后，再执行逐行提取 for _, line in ipairs(data) do local progress = string.match(line, '%d*%%') -- 然后在这个地方，你就会发现，无法判断这到底是哪个 Job 触发的 callback 函数了。 end end -- clone plugin A vim.system({ 'git', 'clone', url_a }, { stdout = on_stdout }) -- clone plugin B vim.system({ 'git', 'clone', url_b }, { stdout = on_stdout })使用
job.nvim:local job = require('job') local jobs = {} local function on_stdout(id, data) for _, line in ipairs(data) do print( string.format( 'repo %s clone progress %s', jobs[id], string.match(line, '%d*%%') ) ) end end -- clone plugin A local id1 = job.start({ 'git', 'clone', url_a }, { on_stdout = on_stdout, }) jobs[id1] = 'A' -- clone plugin B local id2 = job.start({ 'git', 'clone', url_b }, { on_stdout = on_stdout, }) jobs[id2] = 'B'写在最后
也许，job.nvim 在许多年后会停止维护，那一定是我找到了更合适的内置替代方案。至少目前，
vim.system的实现还没有完全满足我的使用需求。最后，我终于理解 avante.nvim 的作者为什么删掉 Reddit 账号了。吵架真的很烦。 https://www.reddit.com/r/neovim/comments/1rdgfxg/comment/o7bzfzc/
vim.system的设计本身就有问题。我自己写了将近二三十个异步调用命令的插件，难道我遇到的问题还不够多吗？有些人一再给我强调可以在 exit_cb 里面区分 job，难道调用常驻命令时，要等它们执行完毕才能看到结果吗？那就让我们看看以后的版本
vim.system会不会增加这样的参数传入，或者会不会有类似的新的内置函数出现吧。
-
最新发布
标签云