ce-code-review: allow user-configured cross-model peer routes (e.g. GLM via an Anthropic-compatible endpoint)
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
- 5/5
- 見積もり時間
- 1週間以上
- 初心者へのやさしさ
- 35/100
- issue の種類
- 機能追加
- 明瞭さ
- おおむね明確
- 活発さ
- 静か
- 技術スタック
- shell, typescript, yaml
調査の方向性
Start with scripts/cross-model-adversarial-review.sh and references/cross-model-review.md, then trace how cross_model_peer: is read from .compound-engineering/config.local.yaml and how route validation, host exclusion, announcements, and receipts work. The issue sketches desired custom-peer settings but leaves security and design choices open. Done means deciding whether custom routes are supported or curated routes remain the policy, then implementing that decision and documenting it.
索引モデルが issue の本文から書いたものです。
説明
What I ran into
I wanted to use GLM-5.3 (served over z.ai's Anthropic-compatible endpoint) as the independent cross-model adversarial peer in ce-code-review. There is no supported way to do that today, even though the mechanism it would need already exists.
Two hard stops in scripts/cross-model-adversarial-review.sh:
CROSS_MODEL_FIXED_ROUTEonly acceptscodex | claude | grok-cli | grok-cursor | cursor | composer. Anything else fail-closes, which is correct behaviour — but it means the route set is not extensible.validate_model_overrideacceptsclaude:opus|sonnet|haiku|claude-*only, so binding a non-Anthropic model id to theclauderoute is rejected as a cross-family substitution — also correct, and also a dead end for this case.
The only mechanically working workaround is to export ANTHROPIC_BASE_URL (or shim a claude binary) so the sanctioned claude route silently reaches a different provider. That defeats the entire point of the disclosure and receipt machinery: the pre-egress announcement would name Anthropic while the diff goes somewhere else. I am not doing that, and I don't think anyone should.
Why this seems worth supporting
The design already separates "which provider" from "which model/effort", already has a user-facing preference key (cross_model_peer: in .compound-engineering/config.local.yaml), and already distinguishes receipt-verified from receipt-less routes in the announce wording. A user-defined route would slot into that structure rather than fight it.
Concretely, several strong coding models now ship an Anthropic-compatible endpoint and are driven by the same claude -p adapter you already have. The delta is a base URL, an auth source, and a model id — not a new adapter.
Rough shape of a proposal
Something like a cross_model_custom_peers: block in config.local.yaml:
cross_model_custom_peers:
- name: glm
adapter: claude # reuse the existing claude -p adapter
base_url: https://api.z.ai/api/anthropic
model: glm-5.3
family: glm # participates in same-family host exclusion
receipt: false # announce as 'serving model unverified on this route'
with, I would suggest:
- a custom peer never being reachable by default — it must be named in
cross_model_peer:orCROSS_MODEL_PEERS, so nothing changes for existing users; - the announce naming the endpoint host alongside the model, since the recipient is no longer implied by the route name;
receipt: falsebeing the default for custom peers, so the existing "requested X at Y; serving model/effort unverified on this route" wording carries the honesty burden;- the declared
familyfeeding the same host-exclusion check, withunknownskipping the pass exactly as it does today.
Happy to be told this is out of scope — the curated-route model is a defensible position, and a self-declared family field is weaker evidence than an attested host. But if the answer is "curated only", it would help to say so in references/cross-model-review.md, because the presence of cross_model_peer: reads like an extension point.
Context: I got here from a project that already treats external review egress as an explicitly authorized, provider-named decision in its own conventions file. The thing I most want to avoid is people reaching for the base-URL workaround because the honest path does not exist.
- 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
- 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。
- 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。
- リポジトリをフォークし、ブランチを切って変更します。
- 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
-
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
EveryInc/compound-engineering-plugin#2085 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 66/100
EveryInc/compound-engineering-plugin#795 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
難易度 3/5 1〜2日 初心者へのやさしさ 80/100
EveryInc/compound-engineering-plugin#2084 ·
メンテナーはふだん 1 日以内に返信
-
難易度 4/5 3〜5日 初心者へのやさしさ 48/100
EveryInc/compound-engineering-plugin#2083 ·
メンテナーはふだん 1 日以内に返信
-
Host support: DeepSeek Harness (dsh)対応中かも このイシューにリンクされたプルリクエストがオープン中、またはマージ済みです。 オープン
難易度 3/5 1〜2日 初心者へのやさしさ 48/100
EveryInc/compound-engineering-plugin#2072 ·
メンテナーはふだん 1 日以内に返信
EveryInc/compound-engineering-plugin の issue をすべて見る
似ている issue
-
bug impact:low Team: SecuritySolution Team:Defend Workflows v9.6.0
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
elastic/kibana#306401 · コメント 3 件 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
agentes-chat/agentes-chat#927 ·
メンテナーはふだん 1 日以内に返信
-
comp/desktop P2 type/bug
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
NousResearch/hermes-agent#157702 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 76/100
メンテナーはふだん 1 日以内に返信
-
e2e-failure ready-to-code
難易度 1/5 1時間未満 初心者へのやさしさ 72/100
redhat-developer/rhdh-plugin-export-overlays#4794 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信