<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Code-Review on Ashish Jaiswal</title>
    <link>https://ashish1099.me/tags/code-review/</link>
    <description>Recent content in Code-Review on Ashish Jaiswal</description>
    <generator>Hugo -- 0.147.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 08 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://ashish1099.me/tags/code-review/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building a PR Review Bot Under 32K Context: Go AST Diffing, YAML Key Diffing, and Smart Truncation</title>
      <link>https://ashish1099.me/posts/pr-review-bot-go-ast-small-context-window/</link>
      <pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://ashish1099.me/posts/pr-review-bot-go-ast-small-context-window/</guid>
      <description>Artoo, Obmondo&amp;rsquo;s Mattermost bot, got a PR review engine that runs on a self-hosted Qwen3-14B with a ~32K context window. The key problem: a single Kubernetes PR can have 10,000+ lines of diff. The solution: Go pre-processing that compresses diffs to ~2KB before the LLM ever sees them — using go/ast for Go files, YAML key-level diffing for Helm/K8s configs, and priority-based file truncation. This post covers why each decision was made and what the LLM still cannot do.</description>
    </item>
  </channel>
</rss>
