Yaowei Zheng
d4faee3a1e
Branch-length batch covering tooling, the model layer, the Web App and the public surfaces. Highlights: - Changelog: a per-release `changelog/<version>/` tree, grouped by the surface each change touches, with a root CHANGELOG.md holding one line per release. - Dev startup: `scripts/dev-prebuild.mjs` serializes the skills+core prebuild behind a lock and keeps `pnpm install` current; `pnpm dev` runs server+web together. - AgentHub 0.3.3 -> 0.4.0: OmniMessage complete payloads carry one opaque `fidelity` object in place of item-level `signature`/`phase`, threaded verbatim through Trace, replay and resume; malformed classification adapted to the new error types. - Model layer: a model is always referenced by an explicit `(provider, model_id)` pair. The provider is never inferred, guessed or defaulted -- both the catalog inference and the unique-match config resolution are gone, and CLI, SDK, server routes and run_subagent all require the complete pair. Catalog gains the Qwen Token Plan, Qwen Pay-As-You-Go and Fireworks AI gateways, plus an expanded OpenRouter group. - Web App: catalog preset sync and per-group speed test on the Models page, positional slash commands, a markdown renderer, skill-library update reminders, and a vertically centred draft page whose upward menus size themselves to the room available. - Public surfaces: restructured READMEs, the penguin.ooo landing site and blog, refreshed benchmark results for both suites, and the demo videos playing on the landing page. Includes the fixes from a full review of the branch: 23 confirmed findings, among them a provider-inference bug that could send one vendor's API key to another vendor's endpoint, and an Escape handler that destroyed the composer's contents unrecoverably. Verified on the branch head: pnpm test (1127 passing, 7 packages), pnpm typecheck and pnpm format:check clean, Playwright e2e 14/14.
2.5 KiB
2.5 KiB
title, description
| title | description |
|---|---|
| 快速开始 | 安装 PenguinHarness、配置模型并运行第一个 Task。 |
安装
Linux / macOS 一键安装：
curl -fsSL https://penguin.ooo/install.sh | sh
其他方式（npm、源码）见安装。
配置模型
PenguinHarness 不内置任何模型凭据，使用前需要先配置一个模型。可以在 Web UI 的 Models 页面完成，也可以用 CLI：
penguin config model add --provider deepseek --model-id deepseek-v4-pro --api-key sk-... --set-default
- 模型引用始终是
(provider, model_id)二元组，因此--provider与--model-id均为必填——Provider 绝不由模型 id 推断。内置分组见模型与 Provider。 - API Key 也可以来自环境变量：当模型条目没有内联 api_key 时，LLM 网关库 AgentHub 会读取
DEEPSEEK_API_KEY、ANTHROPIC_API_KEY、OPENAI_API_KEY、GEMINI_API_KEY等变量；工作目录下的.env会被自动加载。
启动 Web App
penguin web
服务运行在 http://127.0.0.1:7364 并自动打开浏览器（--no-open 跳过）。首次登录使用 admin / penguin-2026，请立即修改密码。penguin server 启动同一进程的 headless 版本。
单次运行
penguin run -m "创建 hello.txt，内容为 Hello, Penguin"
Workspace 默认为当前目录，可用 --workspace /path 指定；目标目录必须已存在。
交互式对话
penguin chat
- 每输入一行即发起一个 Task。
/compact压缩上下文；/exit或/quit退出；Ctrl-C 中断正在运行的 Task。- 退出时会打印
penguin chat --resume <sessionId>提示，用于恢复本次 Session；--resume不带 id 时恢复该 Agent 最近的 Session。
SDK 示例
安装 @prismshadow/penguin-core 后：
import { createAgent, isCompleteModelMessage, userText } from "@prismshadow/penguin-core";
const agent = await createAgent({ agentId: "default_agent" });
const session = await agent.createSession({ workspaceDir: process.cwd() });
for await (const output of session.run([userText("Create hello.txt containing hi")], {
approve: async () => "allow",
})) {
if (isCompleteModelMessage(output) && output.payload.type === "text") {
console.log(output.payload.text);
}
}
下一步
- Web App 指南：在浏览器中使用 PenguinHarness。
- CLI 参考：完整命令与选项。
- 架构总览：了解整体设计。