SLOPSHOPPER

test-mod

No description.

newpanebandrowsguard
★ 9v1.2.3MITupdated 2026-10-08robscc/ginno/packages/mod-runner/tests/fixtures/test-mod
A shopper browsing a rack in a slop shop
Preview · a replayed session in a sandbox
claude · ~/work/app · test-mod
│ ┃ test-mod ✕ [ Go ][ Break ] │ ┃ [ Go ][ Break ] │ ● test-mod: hi from test-mod │ ⏺ Read(src/auth.ts) │ ⎿ Read 6 lines │ [ Go ][ Break ] │ ⏺ Bash(bun test) │ ⎿ 3 pass, 1 fail │ │ [ Go ][ Break ] │ │ [ Go ][ Break ] │ │ │ │ [ Go ][ Break ] [ Go ][ Break ] ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── › [ Go ][ Break ] [ Go ][ Break ]

Draws

Band
[ Go ][ Break ]
Pane · test-mod
[ Go ][ Break ]
Spinner
[ Go ][ Break ]
Prompt hint
[ Go ][ Break ]
Turn line
[ Go ][ Break ]
Your message
[ Go ][ Break ]
Claude's reply
[ Go ][ Break ]
Tool row
[ Go ][ Break ]
Command output
[ Go ][ Break ]
README

Ginno

A local-first personal AI agent that runs on your own machine.

The shape of Claude Code, all-file storage (no DB · no account · no cloud), and a visual Workflow Studio.

License: MIT Platform-black.svg) No cloud

English · 简体中文

Ginno chat workspace

What it is

Ginno turns the capabilities an AI agent should have into a complete desktop app, instead of scattering them across a terminal and a dozen browser tabs.

  • 🧠 Multi-agent chat — switch agents mid-conversation, shared history, per-agent memory
  • 🛠️ Tools · permissions · skills · MCP · hooks — Claude Code's shape, all built in
  • 🔀 Visual Workflow Studio — a versioned DSL you compile into a LangGraph state graph, with a live run observer
  • 📚 Local knowledge base — index your Obsidian vault; answers come back with citations
  • 🎯 Long-horizon goals + TODO sync — let the agent keep working toward a standing objective
  • 🌐 Embedded browser + web search — retrieval with source attribution, not vibes

Full feature walkthrough: docs/user-guide.md.

Workflow StudioLocal knowledge base
Workflow StudioKnowledge base

Why "local-first"

One design rule: your data should not leave your machine.

Ginno
Database❌ none — all state is JSON / JSONL / Markdown under ~/.ginno/
Account❌ none — open it and go
Cloud sync❌ none — everything stays local
Portable✅ copy the folder to move it; readable, hand-editable, git-able

You bring your own model key (OpenAI / Anthropic / DeepSeek, or any compatible endpoint). Ginno is just a client — it never takes custody of your key or your data.

Install

Option A — download (macOS, Apple Silicon): grab the latest .dmg from Releases. It is not code-signed yet, so on first launch use right-click → Open to get past Gatekeeper.

Option B — build from source:

git clone https://github.com/robscc/ginno
cd ginno

pnpm install                       # web + desktop shell
cd packages/runtime && uv sync     # Python runtime
cd ../..

pnpm dev                           # web + runtime + desktop shell, all at once

Requires: Node ≥ 20 · pnpm ≥ 9 · Python ≥ 3.11 (via uv) · Rust (Tauri).

Package a .app: make app → apps/desktop/target/release/bundle/dmg/Ginno_*.dmg (see docs/p3-packaging-notes.md).

Stack

LayerChoice
ShellTauri 2 (Rust) — process management + webview only
UINext.js 14 (static export) + React 18 + Tailwind
RuntimePython + FastAPI + LangGraph (sidecar, bundled with PyInstaller)
Storageplain files (no DB); optional LanceDB for semantic-search vectors

Architecture and subsystem designs: docs/architecture.md.

Status

  • A personal project, used daily (dogfooding) and iterated fast — ~2.5 months, 220+ commits.
  • Early and unpolished; APIs and UI still move.
  • Issues, PRs, and ideas are welcome — in English or Chinese.

License

MIT © 2026 ChuanchuanSong

Source 1 files
hooks/test-mod.ts 34 lines
1// The `--test` fixture: one clean hook, one throwing hook, a renderer whose
2// buttons include a failing press callback, an op-invoking hook, and one
3// registration against an event this host never raises.
4
5export function register(on) {
6  // Clean: reads a `$` op and answers an object.
7  on('turn.start', async ($, e) => ({ id: await $.session.id(), turnId: e.turnId }))
8
9  // Throws: the report's failure row.
10  on('tool.call', () => {
11    throw new Error('exploded')
12  })
13
14  // Draws two buttons: one press resolves, one throws.
15  on('ui.render', async $ => {
16    const ui = $.ui.resolve()
17    return ui.Box({
18      children: [
19        ui.Button({ label: 'Go', onPress: () => 'ok' }),
20        ui.Button({ label: 'Break', onPress: () => { throw new Error('press exploded') } }),
21      ],
22    })
23  })
24
25  // Fire-and-forget `$` op for the ops section.
26  on('prompt.submit', async $ => {
27    $.ui.log('hi from test-mod')
28    return { text: 'rewritten' }
29  })
30
31  // Registered but never raised: a warning row, not a failure.
32  on('telemetry.mark', () => ({}))
33}
34