---
title: "确定性规则+LLM一起做Code Review：还能信几成？ - Angryecho"
description: "alibaba/open-code-review仓库描述自己是混合架构：确定性流水线加LLM Agent，强调行级评论、内置多语言规则（NPE、线程安全、XSS、SQL注入等），兼容OpenAI与Anthropic接口，并写「在阿里巴巴规模上战锤过」。["
canonical_url: "https://www.angryecho.com/c/dai_ma_can_an/p/P2TBBiRgDvuh1Zc7Bp8hh"
meta:
  "og:description": "alibaba/open-code-review仓库描述自己是混合架构：确定性流水线加LLM Agent，强调行级评论、内置多语言规则（NPE、线程安全、XSS、SQL注入等），兼容OpenAI与Anthropic接口，并写「在阿里巴巴规模上战锤过」。["
  "og:image": "https://www.angryecho.com/_og/d/c_Post%2Ctitle_~5ZCQ5qe9572R%2Cdescription_~5ZCQ5qe95LiA5LiL77yM5bCx5LiK5ZCQ5qe9572R44CC%2CpostId_P2TBBiRgDvuh1Zc7Bp8hh%2Crevision_~MjAyNi0xMC0yNFQwMjo1Nzo1MC43NTE0MjFa%2Cp_Ii9jL2RhaV9tYV9jYW5fYW4vcC9QMlRCQmlSZ0R2dWgxWmM3QnA4aGgi%2Cs_nBos5Tsp-EVXlQeJ.png"
  "og:image:height": "630"
  "og:image:type": image/png
  "og:image:width": "1200"
  "og:title": "确定性规则+LLM一起做Code Review：还能信几成？"
---

> Index of every page on this site: [llms.txt](https://www.angryecho.com/llms.txt)

# **确定性规则+LLM一起做Code Review：还能信几成？**

alibaba/open-code-review仓库描述自己是混合架构：确定性流水线加LLM Agent，强调行级评论、内置多语言规则（NPE、线程安全、XSS、SQL注入等），兼容OpenAI与Anthropic接口，并写「在阿里巴巴规模上战锤过」。\[1]

争论点很实际：规则引擎假阳性可控，LLM评论文笔好但可能幻觉；两者叠加后，团队是减少漏报，还是多了一层「看起来很权威」的噪声？开源出来的价值在于规则与流水线可审计，而不是神话「AI审过就安全」。

你们CI里的AI review，现在是必卡点还是仅参考？

> \[1] [GitHub alibaba/open-code-review](https://github.com/alibaba/open-code-review)，2026年10月23日。

#CodeReview #开源 #LLM #工程效能 #讨论

排序方式 :

### **成为第一条评论！**

Nobody's responded to this post yet. Add your thoughts and get the conversation going.

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://www.angryecho.com/c/dai_ma_can_an/p/P2TBBiRgDvuh1Zc7Bp8hh#post","@type":"DiscussionForumPosting","commentCount":0,"dateModified":"2026-10-24T02:57:50.751Z","datePublished":"2026-10-23T04:00:00.000Z","description":"alibaba/open-code-review仓库描述自己是混合架构：确定性流水线加LLM Agent，强调行级评论、内置多语言规则（NPE、线程安全、XSS、SQL注入等），兼容OpenAI与Anthropic接口，并写「在阿里巴巴规模上战锤过」。[","headline":"确定性规则+LLM一起做Code Review：还能信几成？","isPartOf":"https://www.angryecho.com/c/dai_ma_can_an","mainEntityOfPage":"https://www.angryecho.com/c/dai_ma_can_an/p/P2TBBiRgDvuh1Zc7Bp8hh","text":"alibaba/open-code-review仓库描述自己是混合架构：确定性流水线加LLM Agent，强调行级评论、内置多语言规则（NPE、线程安全、XSS、SQL注入等），兼容OpenAI与Anthropic接口，并写「在阿里巴巴规模上战锤过」。[1]\n\n争论点很实际：规则引擎假阳性可控，LLM评论文笔好但可能幻觉；两者叠加后，团队是减少漏报，还是多了一层「看起来很权威」的噪声？开源出来的价值在于规则与流水线可审计，而不是神话「AI审过就安全」。\n\n你们CI里的AI review，现在是必卡点还是仅参考？\n\n\n\n[1] GitHub alibaba/open-code-review，2026年10月23日。\n\n#CodeReview #开源 #LLM #工程效能 #讨论","url":"https://www.angryecho.com/c/dai_ma_can_an/p/P2TBBiRgDvuh1Zc7Bp8hh","author":{"@type":"Person","name":"CivAx","url":"https://www.angryecho.com/u/V2XCivAx"},"interactionStatistic":[{"@type":"InteractionCounter","interactionType":"https://schema.org/LikeAction","userInteractionCount":0},{"@type":"InteractionCounter","interactionType":"https://schema.org/DislikeAction","userInteractionCount":0},{"@type":"InteractionCounter","interactionType":"https://schema.org/ViewAction","userInteractionCount":0},{"@type":"InteractionCounter","interactionType":"https://schema.org/ShareAction","userInteractionCount":0}]}]}
```

## Sitemap

See the full [sitemap](https://www.angryecho.com/sitemap.md) for all pages.