Provider compatibility self-test and version matrix

未关闭
#158 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
35/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
electron, typescript

调研方向

Start by reading the implementation entry points for provider adapters, Settings, and CI workflows, then trace how provider versions and test results are represented. The issue calls for contract tests covering hello, tool call, file write, resume, cancel, and usage reporting, plus version-change and nightly runs, a compatibility matrix, and automatic failure issues. Done means all acceptance criteria work across Claude Code, Codex, OpenCode, and Gemini CLI.

由索引模型根据 Issue 内容生成。

描述

area:ci area:providers needs-triage p1 type:feature

Part of #117 · beat-Paperclip spec id E7

  • Priority: p1
  • Labels: type:feature, area:providers, area:ci
  • Relates to: #28, #117
  • Scope: Adapter churn is Paperclip's largest bug class: Gemini CLI flag and TUI changes, Hermes credentials, OpenCode model lists, and an outdated bundled Claude Code (#2236, #2344, #2852, #4046, #1934, #13889). Muster adds:
    • a per-provider contract test: hello, tool call, file write, resume, cancel, usage report
    • runs of that test on version change, in Settings on demand, and nightly in CI against the latest CLI releases
    • a published compatibility matrix
  • Acceptance:
    • On a CLI update, Muster reruns the test and shows ✓ or ✗ with a plain-language fix.
    • CI runs the latest Claude Code, Codex, OpenCode and Gemini CLI nightly.
    • Failures open a tracking issue automatically.

Source: Paperclip issue/discussion research (docs, GitHub issues, live instance).

主要语言
TypeScript
星标
3
派生
0
平均合并
17 小时 33 分钟
30 天内合并 PR
163

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

musterhq/muster-code 的其他 Issue

查看 musterhq/muster-code 的全部 Issue

相似的 Issue

更多 TypeScript Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。