Code review skill produces wildly different results between Claude and Codex

オープン
#835 コメント 3 件 リアクション 0 件 担当者 0 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

まだ誰も着手していません。

評価

難易度
4/5
見積もり時間
1〜2日
初心者へのやさしさ
47/100
issue の種類
バグ
明瞭さ
おおむね明確
活発さ
静か
技術スタック
typescript

調査の方向性

The report describes inconsistent findings from /ce-code-review in Codex and Claude and mentions a possible connection to issue #799, but names no implementation files or tests. Start by reading the skill implementation and issue #799, then compare how reviewer outputs are collected and synthesized across the two integrations. Done means the same diff produces a consistent, adequately reconciled report, with a regression check covering the reported behavior.

索引モデルが issue の本文から書いたものです。

説明

Hi there,

First of all, thank you for creating such a great plugin. I've been using it for some time now and it's been great.

I've primarily been a Claude user, but lately I've been testing Codex and I've noticed a big difference in how the /ce-code-review skill behaves between the two.

When used against the same task/commit diff, Codex tends to return single-digit findings, while Claude usually produces double-digit findings. The difference between the two is pretty significant.

When I asked Codex why there was such a difference between the results, it said:

I did not spawn the full applicable reviewer set for the final diff.
I did not create/read a fresh run artifact and then synthesize from every reviewer output.
I over-applied the “validate and drop weak findings” mindset before showing you the raw-to-final mapping.
Claude Code has a more direct implementation path for this CE skill; in Codex I had to manually emulate it with spawn_agent, and I under-emulated it.

This isn't a one-off, it consistently happens every time I run the skill. Is this a bug or a limitation of Codex? I'm also not sure if it's related to this https://github.com/EveryInc/compound-engineering-plugin/issues/799 ?


Edit: here's some more comments from Codex:

Why results diverged:

Claude artifacts include raw reviewer output, not just final merged findings. Many items are testing_gaps or residual_risks, not primary findings. My final report only surfaced the main actionable findings and summarized coverage too tightly.

A lot of Claude’s raw findings violate the skill’s strict merge schema: severity values like high/medium/low, confidence values like 90/95/80. Under the skill’s Stage 5 validation, those are supposed to be dropped or normalized before final synthesis. I dropped some instead of salvaging/normalizing useful content.

I demoted or omitted several “coverage-only” items that Claude preserved, ....

Reviewer nondeterminism is real here. Different harness, model tiering, and agent implementations produced different issue discovery. But that does not fully excuse it: several Claude findings are valid and I should have caught or at least surfaced them as testing gaps/residual risks.

I also compressed the final report too much after applying the one safe fix. The skill asks for richer Coverage, Deployment Notes, and residual/actionable tables. My final answer was materially thinner than the Claude artifact set.

So the honest answer: I did spawn the required agents, but my synthesis pass was stricter and less complete than it should have been. The biggest actual miss is not agent coverage; it is that I failed to reconcile valid raw signals into the final report.
主要言語
TypeScript
スター
25.6k
フォーク
2.1k
平均マージ
3時間 57分
マージ済み PR(30日)
170

環境構築

このプロジェクトには開発コンテナ、Dockerfile、コントリビューションガイドがありません。まず README を読み、一般的な手順ははじめてのコントリビューションガイドを参照してください。

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

EveryInc/compound-engineering-plugin のほかの issue

EveryInc/compound-engineering-plugin の issue をすべて見る

似ている issue

TypeScript の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。