惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
WordPress大学
WordPress大学
月光博客
月光博客
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
大猫的无限游戏
大猫的无限游戏
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
博客园 - 聂微东
Apple Machine Learning Research
Apple Machine Learning Research
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
雷峰网
雷峰网
小众软件
小众软件
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - 叶小钗
美团技术团队
宝玉的分享
宝玉的分享
Hugging Face - Blog
Hugging Face - Blog
阮一峰的网络日志
阮一峰的网络日志
A
About on SuperTechFans
Jina AI
Jina AI
D
Docker
Last Week in AI
Last Week in AI
MongoDB | Blog
MongoDB | Blog
Stack Overflow Blog
Stack Overflow Blog
Microsoft Azure Blog
Microsoft Azure Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
我用 DeepSeek V4 搭了个多 Agent 流水线,写代码 沙箱执行 ...
YOXI-Design · 2026-06-14 · via DEV Community

YOXI-Design

为什么要做 AI 流水线?

日常开发中,写代码只是第一步。审查、测试、修复往往花费更长时间。

所以我用 DeepSeek V4 搭了一个多 Agent 流水线:

Writer → 沙箱执行 → Reviewer → Fixer → 再审

架构设计

三个 Agent 上下文完全隔离:

  • Writer 只看需求
  • Reviewer 看代码 + 执行结果
  • Fixer 看代码 + 审查报告
需求 → Writer 生成代码 → 沙箱运行 → Reviewer 审查
       → 未通过 → Fixer 修复 → 沙箱再运行 → 再审
       → 通过 → 交付 ✅

为什么选择 DeepSeek V4?

DeepSeek V4 Flash 的价格太低了:输入 ¥1/百万 token,输出 ¥2/百万 token。跑一次流水线(写+审+修+再审)成本不到 ¥0.02。

沙箱执行

# 核心只有 30 行
import subprocess
import tempfile

def run_code(code, language='python', timeout=30):
    temp_dir = Path(tempfile.mkdtemp())
    file_path = temp_dir / f'script.{language}'
    file_path.write_text(code)
    result = subprocess.run(
        ['python', str(file_path)],
        capture_output=True, text=True, timeout=timeout,
    )
    return result.stdout, result.stderr

代码量

整个流水线只有 7 个文件、约 800 行 Python,测试覆盖率 140 项。

👉 线上体验地址:https://zhijian-helper.up.railway.app


这篇文章由 AI 辅助生成。如果你觉得有用,欢迎访问 AI 代码审查工具 免费试用。

项目开源在 GitHub,欢迎 Star。