I Built a Self-Hosted AI Engineering Team That Won't Push Code Without My Approval

说明与用途

构建了一个自托管的 AI 工程团队，使用沙箱隔离、分阶段审核，并在推送前需要人工批准，确保代码安全与质量。

问题

AI coding agents often ship incorrect or insecure changes without human oversight, leading to broken code, accidental leaks, and unsafe dependencies.

结果

Implemented a secure, model-agnostic AI coding pipeline that prevents accidental pushes, catches secrets and unstable dependencies, and requires human approval before integration.

工作流

• Define task and handoff notes
• Planner reads code and notes, writes plan with files, acceptance criteria, and risks
• Coder writes code in its own Git worktree
• Quick checks validate secrets, syntax, debug leftovers, and dependency stability
• If checks fail, coder revises code
• Reviewer reviews requirements, crashes, tests, and agreement up to 3 rounds
• UI and security critics run app, capture screenshots, and evaluate UI/security changes
• Git agent creates commit and PR
• Human approves via dashboard
• Branch is pushed to GitHub

证据

Agents run inside the coding harness's sandbox (Landlock/bwrap on Linux).

来源

The Planner reads the code, the project's handoff notes, and team memory, then writes a plan with files, acceptance criteria, and risks before any code is touched.

来源

Quick checks catch secrets, broken JSON/YAML/JS, debug leftovers, and risky new dependencies with plain code, no model call.

来源