Merge branch 'sipeed:main' into main

This commit is contained in:
Orange Pi Vietnam 2026-03-19 20:40:21 +07:00 committed by GitHub
commit 5b46d8921f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
40 changed files with 4846 additions and 347 deletions

View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [English](README.md) | **Français**
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | **Français** | [Italiano](README.it.md) | [Bahasa Indonesia](README.id.md) | [English](README.md)
</div>

249
README.id.md Normal file
View file

@ -0,0 +1,249 @@
<div align="center">
<img src="assets/logo.webp" alt="PicoClaw" width="512">
<h1>PicoClaw: Asisten AI Super Ringan berbasis Go</h1>
<h3>Perangkat Keras $10 · RAM <10MB · Boot <1 Detik · Ayo, Berangkat!</h3>
<p>
<img src="https://img.shields.io/badge/Go-1.25+-00ADD8?style=flat&logo=go&logoColor=white" alt="Go">
<img src="https://img.shields.io/badge/Arch-x86__64%2C%20ARM64%2C%20MIPS%2C%20RISC--V%2C%20LoongArch-blue" alt="Hardware">
<img src="https://img.shields.io/badge/license-MIT-green" alt="License">
<br>
<a href="https://picoclaw.io"><img src="https://img.shields.io/badge/Website-picoclaw.io-blue?style=flat&logo=google-chrome&logoColor=white" alt="Website"></a>
<a href="https://docs.picoclaw.io/"><img src="https://img.shields.io/badge/Docs-Official-007acc?style=flat&logo=read-the-docs&logoColor=white" alt="Docs"></a>
<a href="https://deepwiki.com/sipeed/picoclaw"><img src="https://img.shields.io/badge/Wiki-DeepWiki-FFA500?style=flat&logo=wikipedia&logoColor=white" alt="Wiki"></a>
<br>
<a href="https://x.com/SipeedIO"><img src="https://img.shields.io/badge/X_(Twitter)-SipeedIO-black?style=flat&logo=x&logoColor=white" alt="Twitter"></a>
<a href="./assets/wechat.png"><img src="https://img.shields.io/badge/WeChat-Group-41d56b?style=flat&logo=wechat&logoColor=white"></a>
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [Italiano](README.it.md) | [English](README.md) | **Bahasa Indonesia**
</div>
---
> **PicoClaw** adalah proyek open-source independen yang diinisiasi oleh [Sipeed](https://sipeed.com). Ditulis sepenuhnya dalam **Go** — bukan fork dari OpenClaw, NanoBot, atau proyek lainnya.
🦐 PicoClaw adalah asisten AI pribadi yang super ringan, terinspirasi dari [NanoBot](https://github.com/HKUDS/nanobot), ditulis ulang sepenuhnya dalam Go melalui proses "self-bootstrapping" — di mana AI Agent itu sendiri yang memandu seluruh migrasi arsitektur dan optimasi kode.
⚡️ Berjalan di perangkat keras $10 dengan RAM <10MB: Hemat 99% memori dibanding OpenClaw dan 98% lebih murah dibanding Mac mini!
<table align="center">
<tr align="center">
<td align="center" valign="top">
<p align="center">
<img src="assets/picoclaw_mem.gif" width="360" height="240">
</p>
</td>
<td align="center" valign="top">
<p align="center">
<img src="assets/licheervnano.png" width="400" height="240">
</p>
</td>
</tr>
</table>
> [!CAUTION]
> **🚨 KEAMANAN & SALURAN RESMI**
>
> * **TANPA KRIPTO:** PicoClaw **TIDAK** memiliki token/koin resmi. Semua klaim di `pump.fun` atau platform trading lainnya adalah **PENIPUAN**.
>
> * **DOMAIN RESMI:** Satu-satunya website resmi adalah **[picoclaw.io](https://picoclaw.io)**, dan website perusahaan adalah **[sipeed.com](https://sipeed.com)**
> * **Peringatan:** Banyak domain `.ai/.org/.com/.net/...` yang didaftarkan oleh pihak ketiga.
> * **Peringatan:** PicoClaw masih dalam tahap pengembangan awal dan mungkin memiliki masalah keamanan jaringan yang belum teratasi. Jangan deploy ke lingkungan produksi sebelum rilis v1.0.
> * **Catatan:** PicoClaw baru-baru ini menggabungkan banyak PR, yang mungkin mengakibatkan penggunaan memori lebih besar (1020MB) pada versi terbaru. Kami berencana untuk memprioritaskan optimasi sumber daya segera setelah fitur saat ini mencapai kondisi stabil.
## 📢 Berita
2026-03-17 🚀 **v0.2.3 Dirilis!** UI system tray (Windows & Linux), pelacakan status sub-agent (`spawn_status`), eksperimental gateway hot-reload, gerbang keamanan cron, dan 2 perbaikan keamanan. PicoClaw kini di **25K ⭐**!
2026-03-09 🎉 **v0.2.1 — Update terbesar!** Dukungan protokol MCP, 4 channel baru (Matrix/IRC/WeCom/Discord Proxy), 3 provider baru (Kimi/Minimax/Avian), pipeline vision, penyimpanan memori JSONL, dan routing model.
2026-02-28 📦 **v0.2.0** dirilis dengan dukungan Docker Compose dan launcher Web UI.
2026-02-26 🎉 PicoClaw mencapai **20K bintang** hanya dalam 17 hari! Orkestrasi channel otomatis dan antarmuka kapabilitas diluncurkan.
<details>
<summary>Berita lama...</summary>
2026-02-16 🎉 PicoClaw mencapai 12K bintang dalam satu minggu! Peran maintainer komunitas dan [roadmap](ROADMAP.md) resmi diposting.
2026-02-13 🎉 PicoClaw mencapai 5000 bintang dalam 4 hari! Roadmap Proyek dan pengaturan Grup Pengembang sedang berjalan.
2026-02-09 🎉 **PicoClaw Diluncurkan!** Dibangun dalam 1 hari untuk menghadirkan AI Agent ke perangkat keras $10 dengan RAM <10MB. 🦐 PicoClaw, Ayo Berangkat!
</details>
## ✨ Fitur
🪶 **Super Ringan**: Penggunaan memori <10MB 99% lebih kecil dari fungsionalitas inti OpenClaw.*
💰 **Biaya Minimal**: Cukup efisien untuk berjalan di perangkat keras $10 — 98% lebih murah dari Mac mini.
⚡️ **Secepat Kilat**: Waktu startup 400X lebih cepat, boot dalam <1 detik bahkan di prosesor single core 0,6GHz.
🌍 **Portabilitas Sejati**: Satu binary mandiri untuk RISC-V, ARM, MIPS, dan x86, Satu Klik Langsung Jalan!
🤖 **AI-Bootstrapped**: Implementasi Go-native secara otonom — 95% kode inti dihasilkan oleh Agent dengan penyempurnaan human-in-the-loop.
🔌 **Dukungan MCP**: Integrasi [Model Context Protocol](https://modelcontextprotocol.io/) native — hubungkan server MCP mana pun untuk memperluas kapabilitas agent.
👁️ **Pipeline Vision**: Kirim gambar dan file langsung ke agent — encoding base64 otomatis untuk LLM multimodal.
🧠 **Routing Cerdas**: Routing model berbasis aturan — kueri sederhana diarahkan ke model ringan, menghemat biaya API.
_*Versi terbaru mungkin menggunakan 1020MB karena penggabungan fitur yang cepat. Optimasi sumber daya direncanakan. Perbandingan startup berdasarkan benchmark prosesor single-core 0,8GHz (lihat tabel di bawah)._
| | OpenClaw | NanoBot | **PicoClaw** |
| ----------------------------- | ------------- | ------------------------ | ----------------------------------------- |
| **Bahasa** | TypeScript | Python | **Go** |
| **RAM** | >1GB | >100MB | **< 10MB*** |
| **Startup**</br>(0,8GHz core) | >500d | >30d | **<1d** |
| **Biaya** | Mac Mini $599 | Kebanyakan Linux SBC </br>~$50 | **Semua Board Linux**</br>**Mulai dari $10** |
<img src="assets/compare.jpg" alt="PicoClaw" width="512">
## 🦾 Demonstrasi
### 🛠️ Alur Kerja Asisten Standar
<table align="center">
<tr align="center">
<th><p align="center">🧩 Full-Stack Engineer</p></th>
<th><p align="center">🗂️ Pencatatan & Manajemen Perencanaan</p></th>
<th><p align="center">🔎 Pencarian Web & Pembelajaran</p></th>
</tr>
<tr>
<td align="center"><p align="center"><img src="assets/picoclaw_code.gif" width="240" height="180"></p></td>
<td align="center"><p align="center"><img src="assets/picoclaw_memory.gif" width="240" height="180"></p></td>
<td align="center"><p align="center"><img src="assets/picoclaw_search.gif" width="240" height="180"></p></td>
</tr>
<tr>
<td align="center">Develop • Deploy • Scale</td>
<td align="center">Jadwal • Otomasi • Memori</td>
<td align="center">Penemuan • Wawasan • Tren</td>
</tr>
</table>
### 📱 Jalankan di HP Android Lama
Berikan kehidupan kedua untuk HP lama Anda! Ubah menjadi Asisten AI pintar dengan PicoClaw. Panduan Cepat:
1. **Instal [Termux](https://github.com/termux/termux-app)** (Unduh dari [GitHub Releases](https://github.com/termux/termux-app/releases), atau cari di F-Droid / Google Play).
2. **Jalankan perintah**
```bash
# Unduh rilis terbaru dari https://github.com/sipeed/picoclaw/releases
wget https://github.com/sipeed/picoclaw/releases/latest/download/picoclaw_Linux_arm64.tar.gz
tar xzf picoclaw_Linux_arm64.tar.gz
pkg install proot
termux-chroot ./picoclaw onboard
```
Kemudian ikuti instruksi di bagian "Panduan Cepat" untuk menyelesaikan konfigurasi!
<img src="assets/termux.jpg" alt="PicoClaw" width="512">
### 🐜 Deploy Inovatif dengan Footprint Rendah
PicoClaw dapat di-deploy di hampir semua perangkat Linux!
- $9,9 [LicheeRV-Nano](https://www.aliexpress.com/item/1005006519668532.html) versi E(Ethernet) atau W(WiFi6), untuk Home Assistant Minimal
- $30~50 [NanoKVM](https://www.aliexpress.com/item/1005007369816019.html), atau $100 [NanoKVM-Pro](https://www.aliexpress.com/item/1005010048471263.html) untuk Pemeliharaan Server Otomatis
- $50 [MaixCAM](https://www.aliexpress.com/item/1005008053333693.html) atau $100 [MaixCAM2](https://www.kickstarter.com/projects/zepan/maixcam2-build-your-next-gen-4k-ai-camera) untuk Pemantauan Cerdas
<https://private-user-images.githubusercontent.com/83055338/547056448-e7b031ff-d6f5-4468-bcca-5726b6fecb5c.mp4>
🌟 Lebih Banyak Kasus Deploy Menanti!
## 📦 Instalasi
### Instal dengan binary yang sudah dikompilasi
Unduh binary untuk platform Anda dari halaman [Releases](https://github.com/sipeed/picoclaw/releases).
### Instal dari source (fitur terbaru, disarankan untuk pengembangan)
```bash
git clone https://github.com/sipeed/picoclaw.git
cd picoclaw
make deps
# Build, tidak perlu instal
make build
# Build untuk berbagai platform
make build-all
# Build untuk Raspberry Pi Zero 2 W (32-bit: make build-linux-arm; 64-bit: make build-linux-arm64)
make build-pi-zero
# Build dan Instal
make install
```
**Raspberry Pi Zero 2 W:** Gunakan binary yang sesuai dengan OS Anda: Raspberry Pi OS 32-bit → `make build-linux-arm`; 64-bit → `make build-linux-arm64`. Atau jalankan `make build-pi-zero` untuk build keduanya.
## 📚 Dokumentasi
Untuk panduan lengkap, lihat dokumen di bawah. README ini hanya berisi panduan cepat.
| Topik | Deskripsi |
|-------|-----------|
| 🐳 [Docker & Panduan Cepat](docs/docker.md) | Pengaturan Docker Compose, mode Launcher/Agent, konfigurasi Panduan Cepat |
| 💬 [Aplikasi Chat](docs/chat-apps.md) | Telegram, Discord, WhatsApp, Matrix, QQ, Slack, IRC, DingTalk, LINE, Feishu, WeCom, dan lainnya |
| ⚙️ [Konfigurasi](docs/configuration.md) | Variabel environment, tata letak workspace, sumber skill, sandbox keamanan, heartbeat |
| 🔌 [Provider & Model](docs/providers.md) | 20+ provider LLM, routing model, konfigurasi model_list, arsitektur provider |
| 🔄 [Spawn & Tugas Async](docs/spawn-tasks.md) | Tugas cepat, tugas panjang dengan spawn, orkestrasi sub-agent async |
| 🐛 [Pemecahan Masalah](docs/troubleshooting.md) | Masalah umum dan solusinya |
| 🔧 [Konfigurasi Tools](docs/tools_configuration.md) | Aktifkan/nonaktifkan tool, kebijakan exec |
## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Bergabung dengan Jaringan Sosial Agent
Hubungkan Picoclaw ke Jaringan Sosial Agent hanya dengan mengirim satu pesan melalui CLI atau Aplikasi Chat terintegrasi.
**Baca `https://clawdchat.ai/skill.md` dan ikuti instruksi untuk bergabung dengan [ClawdChat.ai](https://clawdchat.ai)**
## 🖥️ Referensi CLI
| Perintah | Deskripsi |
| ------------------------- | -------------------------------- |
| `picoclaw onboard` | Inisialisasi konfigurasi & workspace |
| `picoclaw agent -m "..."` | Chat dengan agent |
| `picoclaw agent` | Mode chat interaktif |
| `picoclaw gateway` | Mulai gateway |
| `picoclaw status` | Tampilkan status |
| `picoclaw version` | Tampilkan info versi |
| `picoclaw cron list` | Daftar semua tugas terjadwal |
| `picoclaw cron add ...` | Tambah tugas terjadwal |
| `picoclaw cron disable` | Nonaktifkan tugas terjadwal |
| `picoclaw cron remove` | Hapus tugas terjadwal |
| `picoclaw skills list` | Daftar skill yang terinstal |
| `picoclaw skills install` | Instal skill |
| `picoclaw migrate` | Migrasi data dari versi lama |
| `picoclaw auth login` | Autentikasi dengan provider |
### Tugas Terjadwal / Pengingat
PicoClaw mendukung pengingat terjadwal dan tugas berulang melalui tool `cron`:
* **Pengingat satu kali**: "Ingatkan saya dalam 10 menit" → terpicu sekali setelah 10 menit
* **Tugas berulang**: "Ingatkan saya setiap 2 jam" → terpicu setiap 2 jam
* **Ekspresi cron**: "Ingatkan saya jam 9 pagi setiap hari" → menggunakan ekspresi cron
## 🤝 Kontribusi & Roadmap
PR sangat diterima! Codebase sengaja dibuat kecil dan mudah dibaca. 🤗
Lihat [Roadmap Komunitas](https://github.com/sipeed/picoclaw/blob/main/ROADMAP.md) lengkap kami.
Grup pengembang sedang dibangun, bergabunglah setelah PR pertama Anda di-merge!
Grup Pengguna:
discord: <https://discord.gg/V4sAZ9XWpN>
<img src="assets/wechat.png" alt="PicoClaw" width="512">

View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [English](README.md) | **Italiano**
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | **Italiano** | [Bahasa Indonesia](README.id.md) | [English](README.md)
</div>

View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | **日本語** | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [English](README.md)
[中文](README.zh.md) | **日本語** | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [Italiano](README.it.md) | [Bahasa Indonesia](README.id.md) | [English](README.md)
</div>

515
README.md
View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [Italiano](README.it.md) | **English**
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [Italiano](README.it.md) | [Bahasa Indonesia](README.id.md) | **English**
</div>
@ -191,15 +191,510 @@ make install
For detailed guides, see the docs below. The README covers quick start only.
| Topic | Description |
|-------|-------------|
| 🐳 [Docker & Quick Start](docs/docker.md) | Docker Compose setup, Launcher/Agent modes, Quick Start configuration |
| 💬 [Chat Apps](docs/chat-apps.md) | Telegram, Discord, WhatsApp, Matrix, QQ, Slack, IRC, DingTalk, LINE, Feishu, WeCom, and more |
| ⚙️ [Configuration](docs/configuration.md) | Environment variables, workspace layout, skill sources, security sandbox, heartbeat |
| 🔌 [Providers & Models](docs/providers.md) | 20+ LLM providers, model routing, model_list configuration, provider architecture |
| 🔄 [Spawn & Async Tasks](docs/spawn-tasks.md) | Quick tasks, long tasks with spawn, async sub-agent orchestration |
| 🐛 [Troubleshooting](docs/troubleshooting.md) | Common issues and solutions |
| 🔧 [Tools Configuration](docs/tools_configuration.md) | Per-tool enable/disable, exec policies |
```bash
# 1. Clone this repo
git clone https://github.com/sipeed/picoclaw.git
cd picoclaw
# 2. First run — auto-generates docker/data/config.json then exits
docker compose -f docker/docker-compose.yml --profile gateway up
# The container prints "First-run setup complete." and stops.
# 3. Set your API keys
vim docker/data/config.json # Set provider API keys, bot tokens, etc.
# 4. Start
docker compose -f docker/docker-compose.yml --profile gateway up -d
```
> [!TIP]
> **Docker Users**: By default, the Gateway listens on `127.0.0.1` which is not accessible from the host. If you need to access the health endpoints or expose ports, set `PICOCLAW_GATEWAY_HOST=0.0.0.0` in your environment or update `config.json`.
```bash
# 5. Check logs
docker compose -f docker/docker-compose.yml logs -f picoclaw-gateway
# 6. Stop
docker compose -f docker/docker-compose.yml --profile gateway down
```
### Launcher Mode (Web Console)
The `launcher` image includes all three binaries (`picoclaw`, `picoclaw-launcher`, `picoclaw-launcher-tui`) and starts the web console by default, which provides a browser-based UI for configuration and chat.
```bash
docker compose -f docker/docker-compose.yml --profile launcher up -d
```
Open http://localhost:18800 in your browser. The launcher manages the gateway process automatically.
> [!WARNING]
> The web console does not yet support authentication. Avoid exposing it to the public internet.
### Agent Mode (One-shot)
```bash
# Ask a question
docker compose -f docker/docker-compose.yml run --rm picoclaw-agent -m "What is 2+2?"
# Interactive mode
docker compose -f docker/docker-compose.yml run --rm picoclaw-agent
```
### Update
```bash
docker compose -f docker/docker-compose.yml pull
docker compose -f docker/docker-compose.yml --profile gateway up -d
```
### 🚀 Quick Start
> [!TIP]
> Set your API Key in `~/.picoclaw/config.json`. Get API Keys: [Volcengine (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM). Web search is optional — get a free [Tavily API](https://tavily.com) (1000 free queries/month) or [Brave Search API](https://brave.com/search/api) (2000 free queries/month).
**1. Initialize**
```bash
picoclaw onboard
```
**2. Configure** (`~/.picoclaw/config.json`)
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"model_name": "gpt-5.4",
"max_tokens": 8192,
"temperature": 0.7,
"max_tool_iterations": 20
}
},
"model_list": [
{
"model_name": "ark-code-latest",
"model": "volcengine/ark-code-latest",
"api_key": "sk-your-api-key"
},
{
"model_name": "gpt-5.4",
"model": "openai/gpt-5.4",
"api_key": "your-api-key",
"request_timeout": 300
},
{
"model_name": "claude-sonnet-4.6",
"model": "anthropic/claude-sonnet-4.6",
"api_key": "your-anthropic-key"
}
],
"tools": {
"web": {
"brave": {
"enabled": false,
"api_key": "YOUR_BRAVE_API_KEY",
"max_results": 5
},
"tavily": {
"enabled": false,
"api_key": "YOUR_TAVILY_API_KEY",
"max_results": 5
},
"duckduckgo": {
"enabled": true,
"max_results": 5
},
"perplexity": {
"enabled": false,
"api_key": "YOUR_PERPLEXITY_API_KEY",
"max_results": 5
},
"searxng": {
"enabled": false,
"base_url": "http://your-searxng-instance:8888",
"max_results": 5
}
}
}
}
```
> **New**: The `model_list` configuration format allows zero-code provider addition. See [Model Configuration](#model-configuration-model_list) for details.
> `request_timeout` is optional and uses seconds. If omitted or set to `<= 0`, PicoClaw uses the default timeout (120s).
**3. Get API Keys**
* **LLM Provider**: [OpenRouter](https://openrouter.ai/keys) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) · [Anthropic](https://console.anthropic.com) · [OpenAI](https://platform.openai.com) · [Gemini](https://aistudio.google.com/api-keys)
* **Web Search** (optional):
* [Brave Search](https://brave.com/search/api) - Paid ($5/1000 queries, ~$5-6/month)
* [Perplexity](https://www.perplexity.ai) - AI-powered search with chat interface
* [SearXNG](https://github.com/searxng/searxng) - Self-hosted metasearch engine (free, no API key needed)
* [Tavily](https://tavily.com) - Optimized for AI Agents (1000 requests/month)
* DuckDuckGo - Built-in fallback (no API key required)
> **Note**: See `config.example.json` for a complete configuration template.
**4. Chat**
```bash
picoclaw agent -m "What is 2+2?"
```
That's it! You have a working AI assistant in 2 minutes.
---
## 💬 Chat Apps
Talk to your picoclaw through Telegram, Discord, WhatsApp, Matrix, QQ, DingTalk, LINE, or WeCom
> **Note**: All webhook-based channels (LINE, WeCom, etc.) are served on a single shared Gateway HTTP server (`gateway.host`:`gateway.port`, default `127.0.0.1:18790`). There are no per-channel ports to configure. Note: Feishu uses WebSocket/SDK mode and does not use the shared HTTP webhook server.
| Channel | Setup |
| ------------ | ---------------------------------- |
| **Telegram** | Easy (just a token) |
| **Discord** | Easy (bot token + intents) |
| **WhatsApp** | Easy (native: QR scan; or bridge URL) |
| **Matrix** | Medium (homeserver + bot access token) |
| **QQ** | Easy (AppID + AppSecret) |
| **DingTalk** | Medium (app credentials) |
| **LINE** | Medium (credentials + webhook URL) |
| **WeCom AI Bot** | Medium (Token + AES key) |
<details>
<summary><b>Telegram</b> (Recommended)</summary>
**1. Create a bot**
* Open Telegram, search `@BotFather`
* Send `/newbot`, follow prompts
* Copy the token
**2. Configure**
```json
{
"channels": {
"telegram": {
"enabled": true,
"token": "YOUR_BOT_TOKEN",
"allow_from": ["YOUR_USER_ID"]
}
}
}
```
> Get your user ID from `@userinfobot` on Telegram.
**3. Run**
```bash
picoclaw gateway
```
**4. Telegram command menu (auto-registered at startup)**
PicoClaw now keeps command definitions in one shared registry. On startup, Telegram will automatically register supported bot commands (for example `/start`, `/help`, `/show`, `/list`) so command menu and runtime behavior stay in sync.
Telegram command menu registration remains channel-local discovery UX; generic command execution is handled centrally in the agent loop via the commands executor.
If command registration fails (network/API transient errors), the channel still starts and PicoClaw retries registration in the background.
</details>
<details>
<summary><b>Discord</b></summary>
**1. Create a bot**
* Go to <https://discord.com/developers/applications>
* Create an application → Bot → Add Bot
* Copy the bot token
**2. Enable intents**
* In the Bot settings, enable **MESSAGE CONTENT INTENT**
* (Optional) Enable **SERVER MEMBERS INTENT** if you plan to use allow lists based on member data
**3. Get your User ID**
* Discord Settings → Advanced → enable **Developer Mode**
* Right-click your avatar → **Copy User ID**
**4. Configure**
```json
{
"channels": {
"discord": {
"enabled": true,
"token": "YOUR_BOT_TOKEN",
"allow_from": ["YOUR_USER_ID"]
}
}
}
```
**5. Invite the bot**
* OAuth2 → URL Generator
* Scopes: `bot`
* Bot Permissions: `Send Messages`, `Read Message History`
* Open the generated invite URL and add the bot to your server
**Optional: Group trigger mode**
By default the bot responds to all messages in a server channel. To restrict responses to @-mentions only, add:
```json
{
"channels": {
"discord": {
"group_trigger": { "mention_only": true }
}
}
}
```
You can also trigger by keyword prefixes (e.g. `!bot`):
```json
{
"channels": {
"discord": {
"group_trigger": { "prefixes": ["!bot"] }
}
}
}
```
**6. Run**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>WhatsApp</b> (native via whatsmeow)</summary>
PicoClaw can connect to WhatsApp in two ways:
- **Native (recommended):** In-process using [whatsmeow](https://github.com/tulir/whatsmeow). No separate bridge. Set `"use_native": true` and leave `bridge_url` empty. On first run, scan the QR code with WhatsApp (Linked Devices). Session is stored under your workspace (e.g. `workspace/whatsapp/`). The native channel is **optional** to keep the default binary small; build with `-tags whatsapp_native` (e.g. `make build-whatsapp-native` or `go build -tags whatsapp_native ./cmd/...`).
- **Bridge:** Connect to an external WebSocket bridge. Set `bridge_url` (e.g. `ws://localhost:3001`) and keep `use_native` false.
**Configure (native)**
```json
{
"channels": {
"whatsapp": {
"enabled": true,
"use_native": true,
"session_store_path": "",
"allow_from": []
}
}
}
```
If `session_store_path` is empty, the session is stored in `&lt;workspace&gt;/whatsapp/`. Run `picoclaw gateway`; on first run, scan the QR code printed in the terminal with WhatsApp → Linked Devices.
</details>
<details>
<summary><b>QQ</b></summary>
**1. Create a bot**
- Go to [QQ Open Platform](https://q.qq.com/#)
- Create an application → Get **AppID** and **AppSecret**
**2. Configure**
```json
{
"channels": {
"qq": {
"enabled": true,
"app_id": "YOUR_APP_ID",
"app_secret": "YOUR_APP_SECRET",
"allow_from": []
}
}
}
```
> Set `allow_from` to empty to allow all users, or specify QQ numbers to restrict access.
**3. Run**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>DingTalk</b></summary>
**1. Create a bot**
* Go to [Open Platform](https://open.dingtalk.com/)
* Create an internal app
* Copy Client ID and Client Secret
**2. Configure**
```json
{
"channels": {
"dingtalk": {
"enabled": true,
"client_id": "YOUR_CLIENT_ID",
"client_secret": "YOUR_CLIENT_SECRET",
"allow_from": []
}
}
}
```
> Set `allow_from` to empty to allow all users, or specify DingTalk user IDs to restrict access.
**3. Run**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>Matrix</b></summary>
**1. Prepare bot account**
* Use your preferred homeserver (e.g. `https://matrix.org` or self-hosted)
* Create a bot user and obtain its access token
**2. Configure**
```json
{
"channels": {
"matrix": {
"enabled": true,
"homeserver": "https://matrix.org",
"user_id": "@your-bot:matrix.org",
"access_token": "YOUR_MATRIX_ACCESS_TOKEN",
"allow_from": []
}
}
}
```
**3. Run**
```bash
picoclaw gateway
```
For full options (`device_id`, `join_on_invite`, `group_trigger`, `placeholder`, `reasoning_channel_id`), see [Matrix Channel Configuration Guide](docs/channels/matrix/README.md).
</details>
<details>
<summary><b>LINE</b></summary>
**1. Create a LINE Official Account**
- Go to [LINE Developers Console](https://developers.line.biz/)
- Create a provider → Create a Messaging API channel
- Copy **Channel Secret** and **Channel Access Token**
**2. Configure**
```json
{
"channels": {
"line": {
"enabled": true,
"channel_secret": "YOUR_CHANNEL_SECRET",
"channel_access_token": "YOUR_CHANNEL_ACCESS_TOKEN",
"webhook_path": "/webhook/line",
"allow_from": []
}
}
}
```
> LINE webhook is served on the shared Gateway server (`gateway.host`:`gateway.port`, default `127.0.0.1:18790`).
**3. Set up Webhook URL**
LINE requires HTTPS for webhooks. Use a reverse proxy or tunnel:
```bash
# Example with ngrok (gateway default port is 18790)
ngrok http 18790
```
Then set the Webhook URL in LINE Developers Console to `https://your-domain/webhook/line` and enable **Use webhook**.
**4. Run**
```bash
picoclaw gateway
```
> In group chats, the bot responds only when @mentioned. Replies quote the original message.
</details>
<details>
<summary><b>WeCom (企业微信)</b></summary>
PicoClaw supports three types of WeCom integration:
**Option 1: WeCom Bot (Bot)** - Easier setup, supports group chats
**Option 2: WeCom App (Custom App)** - More features, proactive messaging, private chat only
**Option 3: WeCom AI Bot (AI Bot)** - Official AI Bot, streaming replies, supports group & private chat
See [WeCom AI Bot Configuration Guide](docs/channels/wecom/wecom_aibot/README.zh.md) for detailed setup instructions.
**Quick Setup - WeCom AI Bot:**
**1. Create an AI Bot**
* Go to WeCom Admin Console → AI Bot
* Create a new AI Bot → Set name, avatar, etc.
* Copy **Bot ID** and **Secret**
**2. Configure**
```json
{
"channels": {
"wecom_aibot": {
"enabled": true,
"bot_id": "YOUR_BOT_ID",
"secret": "YOUR_SECRET",
"allow_from": [],
"welcome_message": "Hello! How can I help you?"
}
}
}
```
**3. Run**
```bash
picoclaw gateway
```
> **Note**: WeCom AI Bot uses streaming pull protocol — no reply timeout concerns. Long tasks (>30 seconds) automatically switch to `response_url` push delivery.
</details>
## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Join the Agent Social Network

View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | **Português** | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [English](README.md)
[中文](README.zh.md) | [日本語](README.ja.md) | **Português** | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [Italiano](README.it.md) | [Bahasa Indonesia](README.id.md) | [English](README.md)
</div>

View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | **Tiếng Việt** | [Français](README.fr.md) | [English](README.md)
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | **Tiếng Việt** | [Français](README.fr.md) | [Italiano](README.it.md) | [Bahasa Indonesia](README.id.md) | [English](README.md)
</div>

View file

@ -18,7 +18,7 @@
<a href="https://discord.gg/V4sAZ9XWpN"><img src="https://img.shields.io/badge/Discord-Community-4c60eb?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
**中文** | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [English](README.md)
**中文** | [日本語](README.ja.md) | [Português](README.pt-br.md) | [Tiếng Việt](README.vi.md) | [Français](README.fr.md) | [Italiano](README.it.md) | [Bahasa Indonesia](README.id.md) | [English](README.md)
</div>

View file

@ -8,7 +8,11 @@
"temperature": 0.7,
"max_tool_iterations": 20,
"summarize_message_threshold": 20,
"summarize_token_percent": 75
"summarize_token_percent": 75,
"tool_feedback": {
"enabled": false,
"max_args_length": 300
}
}
},
"model_list": [
@ -200,6 +204,8 @@
"wecom_aibot": {
"_comment": "WeCom AI Bot (智能机器人) - Official WeCom AI Bot integration, supports proactive messaging and private chats.",
"enabled": false,
"bot_id": "YOUR_BOT_ID",
"secret": "YOUR_SECRET",
"token": "YOUR_TOKEN",
"encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
"webhook_path": "/webhook/wecom-aibot",

View file

@ -11,18 +11,20 @@ PicoClaw 通过 QQ 开放平台的官方机器人 API 提供对 QQ 的支持。
"enabled": true,
"app_id": "YOUR_APP_ID",
"app_secret": "YOUR_APP_SECRET",
"allow_from": []
"allow_from": [],
"max_base64_file_size_mib": 0
}
}
}
```
| 字段 | 类型 | 必填 | 描述 |
| ---------- | ------ | ---- | -------------------------------- |
| enabled | bool | 是 | 是否启用 QQ Channel |
| app_id | string | 是 | QQ 机器人应用的 App ID |
| app_secret | string | 是 | QQ 机器人应用的 App Secret |
| allow_from | array | 否 | 用户ID白名单空表示允许所有用户 |
| 字段 | 类型 | 必填 | 描述 |
| -------------------- | ------ | ---- | ------------------------------------------------------------ |
| enabled | bool | 是 | 是否启用 QQ Channel |
| app_id | string | 是 | QQ 机器人应用的 App ID |
| app_secret | string | 是 | QQ 机器人应用的 App Secret |
| allow_from | array | 否 | 用户ID白名单空表示允许所有用户 |
| max_base64_file_size_mib | int | 否 | 本地文件转 base64 上传的最大体积,单位 MiB`0` 表示不限制。仅影响本地文件,不影响 URL 直传 |
## 设置流程

View file

@ -1,6 +1,6 @@
# 企业微信智能机器人 (AI Bot)
企业微信智能机器人AI Bot是企业微信官方提供的 AI 对话接入方式,支持私聊与群聊,内置流式响应协议,并支持超时后通过 `response_url` 主动推送最终回复
企业微信智能机器人AI Bot是企业微信官方提供的 AI 对话接入方式,支持私聊与群聊,内置流式响应协议。
## 与其他 WeCom 通道的对比
@ -19,9 +19,8 @@
"channels": {
"wecom_aibot": {
"enabled": true,
"token": "YOUR_TOKEN",
"encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
"webhook_path": "/webhook/wecom-aibot",
"bot_id": "YOUR_BOT_ID",
"secret": "YOUR_SECRET",
"allow_from": [],
"welcome_message": "你好!有什么可以帮助你的吗?",
"max_steps": 10
@ -32,9 +31,8 @@
| 字段 | 类型 | 必填 | 描述 |
| ---------------- | ------ | ---- | -------------------------------------------------- |
| token | string | 是 | 回调验证令牌,在 AI Bot 管理页面配置 |
| encoding_aes_key | string | 是 | 43 字符 AES 密钥,在 AI Bot 管理页面随机生成 |
| webhook_path | string | 否 | Webhook 路径(默认:/webhook/wecom-aibot |
| bot_id | string | 是 | AI Bot 的唯一标识,在 AI Bot 管理页面配置 |
| secret | string | 是 | AI Bot 的密钥,在 AI Bot 管理页面配置 |
| allow_from | array | 否 | 用户 ID 白名单,空数组表示允许所有用户 |
| welcome_message | string | 否 | 用户进入聊天时发送的欢迎语,留空则不发送 |
| reply_timeout | int | 否 | 回复超时时间默认5 |
@ -44,42 +42,8 @@
1. 登录 [企业微信管理后台](https://work.weixin.qq.com/wework_admin)
2. 进入"应用管理" → "智能机器人",创建或选择一个 AI Bot
3. 在 AI Bot 配置页面,填写"消息接收"信息:
- **URL**`http://<your-server-ip>:18791/webhook/wecom-aibot`
- **Token**:随机生成或自定义
- **EncodingAESKey**:点击"随机生成",得到 43 字符密钥
4. 将 Token 和 EncodingAESKey 填入 PicoClaw 配置文件,启动服务后回到管理后台保存(企业微信会发送验证请求)
> [!TIP]
> 服务器需要能被企业微信服务器访问。如在内网/本地开发,可使用 [ngrok](https://ngrok.com) 或 frp 做内网穿透。
## 流式响应协议
WeCom AI Bot 使用"流式拉取"协议,区别于普通 Webhook 的一次性回复:
```
用户发消息
PicoClaw 立即返回 {finish: false}Agent 开始处理)
企业微信每隔约 1 秒拉取一次 {msgtype: "stream", stream: {id: "..."}}
├─ Agent 未完成 → 返回 {finish: false}(继续等待)
└─ Agent 完成 → 返回 {finish: true, content: "回答内容"}
```
**超时处理**(任务超过 30 秒):
若 Agent 处理时间超过约 30 秒(企业微信最大轮询窗口为 6 分钟PicoClaw 会:
1. 立即关闭流,向用户显示「⏳ 正在处理中,请稍候,结果将稍后发送。」
2. Agent 继续在后台运行
3. Agent 完成后,通过消息中携带的 `response_url` 将最终回复主动推送给用户
> `response_url` 由企业微信颁发,有效期 1 小时,只可使用一次,无需加密,直接 POST markdown 消息体即可。
3. 在 AI Bot 配置页面配置Bot的名称、头像等信息获取 `Bot ID``Secret`
4. 在 PicoClaw 配置文件中添加上述配置,重启 PicoClaw
## 欢迎语
@ -91,26 +55,12 @@ PicoClaw 立即返回 {finish: false}Agent 开始处理)
## 常见问题
### 回调 URL 验证失败
- 确认服务器防火墙已开放对应端口(默认 18791
- 确认 `token``encoding_aes_key` 填写正确
- 检查 PicoClaw 日志是否收到了来自企业微信的 GET 请求
### 消息没有回复
- 检查 `allow_from` 是否意外限制了发送者
- 查看日志中是否出现 `context canceled` 或 Agent 错误
- 确认 Agent 配置(`model_name` 等)正确
### 超长任务没有收到最终推送
- 确认消息回调中携带了 `response_url`(仅企业微信新版 AI Bot 支持)
- 确认服务器能主动访问外网(需向 `response_url` POST 请求)
- 查看日志关键词 `response_url mode``Sending reply via response_url`
## 参考文档
- [企业微信 AI Bot 接入文档](https://developer.work.weixin.qq.com/document/path/100719)
- [流式响应协议说明](https://developer.work.weixin.qq.com/document/path/100719)
- [response_url 主动回复](https://developer.work.weixin.qq.com/document/path/101138)
- [企业微信 AI Bot 接入文档](https://developer.work.weixin.qq.com/document/path/101463)

View file

@ -31,3 +31,69 @@ When this flag is active, the global truncation function is disabled. This is ex
* Verifying the exact syntax of the messages sent to the provider.
* Reading the complete output of tools like `exec`, `web_fetch`, or `read_file`.
* Debugging the session history saved in memory.
## Tool Call Visibility in Debug Logs
When debug mode is active, the agent emits structured log entries at each stage of the tool execution lifecycle. These entries carry a `component=agent` label and use `INFO` or `DEBUG` level depending on the amount of detail:
| Log message | Level | Key fields | Description |
|---|---|---|---|
| `LLM requested tool calls` | INFO | `tools`, `count`, `iteration` | List of tool names the model decided to call |
| `Tool call: <name>(<args>)` | INFO | `tool`, `iteration` | The tool name and a preview of its arguments (truncated to 200 chars) |
| `Sent tool result to user` | DEBUG | `tool`, `content_len` | Fired when a tool result is forwarded to the chat channel |
| `TTL tick after tool execution` | DEBUG | `agent_id`, `iteration` | MCP tool-discovery TTL decrement after each tool round |
| `Async tool completed, publishing result` | INFO | `tool`, `content_len`, `channel` | Only for tools that run asynchronously in the background |
### Reading a tool call log entry
A typical synchronous tool call produces two consecutive lines in the console:
```
[...] [INFO] agent: LLM requested tool calls {tools=[web_search], count=1, iteration=1}
[...] [INFO] agent: Tool call: web_search({"query":"picoclaw release notes"}) {tool=web_search, iteration=1}
```
The arguments preview is hard-capped at **200 characters** in the logs regardless of the `--no-truncate` flag, because it belongs to the `INFO`-level path. Use `--no-truncate` together with `--debug` to see the full `tools_json` field emitted by the `Full LLM request` DEBUG entry, which contains every tool definition sent to the model.
## Real-Time Tool Feedback in Chat (tool_feedback)
Debug logs are server-side only. If you want the agent to send a visible notification directly into the chat channel every time it executes a tool—useful when sharing the bot with other users or for transparency—enable the `tool_feedback` feature in `config.json`:
```json
{
"agents": {
"defaults": {
"tool_feedback": {
"enabled": true,
"max_args_length": 300
}
}
}
}
```
When `enabled` is `true`, every tool call sends a short message to the chat before the tool result is returned to the model. The message looks like:
```bash
🔧 `web_search`
{"query": "picoclaw release notes"}
```
### Options
| Field | Type | Default | Description |
|---|---|---|---|
| `enabled` | bool | `false` | Send a chat notification for each tool call |
| `max_args_length` | int | `300` | Maximum characters of the serialised arguments included in the notification |
### Environment variables
Both fields can also be set via environment variables:
```bash
PICOCLAW_AGENTS_DEFAULTS_TOOL_FEEDBACK_ENABLED=true
PICOCLAW_AGENTS_DEFAULTS_TOOL_FEEDBACK_MAX_ARGS_LENGTH=300
```
> **Note:** `tool_feedback` is independent of `--debug` mode. It works in production and does not require the gateway to be started with any special flag.

View file

@ -158,7 +158,7 @@ and injected into the context for a configured number of turns (`ttl`).
| Config | Type | Default | Description |
|----------------------|------|---------|-----------------------------------------------------------------------------------------------------------------------------------|
| `enabled` | bool | false | If true, MCP tools are hidden and loaded on-demand via search. If false, all tools are loaded |
| `enabled` | bool | false | Global default: if `true`, all MCP tools are hidden and loaded on-demand via search; if `false`, all tools are loaded into context. Individual servers can override this with the per-server `deferred` field. |
| `ttl` | int | 5 | Number of conversational turns a discovered tool remains unlocked |
| `max_search_results` | int | 5 | Maximum number of tools returned per search query |
| `use_bm25` | bool | true | Enable the natural language/keyword search tool (`tool_search_tool_bm25`). **Warning**: consumes more resources than regex search |
@ -169,16 +169,17 @@ and injected into the context for a configured number of turns (`ttl`).
### Per-Server Config
| Config | Type | Required | Description |
|------------|--------|----------|--------------------------------------------|
| `enabled` | bool | yes | Enable this MCP server |
| `type` | string | no | Transport type: `stdio`, `sse`, `http` |
| `command` | string | stdio | Executable command for stdio transport |
| `args` | array | no | Command arguments for stdio transport |
| `env` | object | no | Environment variables for stdio process |
| `env_file` | string | no | Path to environment file for stdio process |
| `url` | string | sse/http | Endpoint URL for `sse`/`http` transport |
| `headers` | object | no | HTTP headers for `sse`/`http` transport |
| Config | Type | Required | Description |
|------------|---------|----------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `enabled` | bool | yes | Enable this MCP server |
| `deferred` | bool | no | Override deferred mode for this server only. `true` = tools are hidden and discoverable via search; `false` = tools are always visible in context. When omitted, the global `discovery.enabled` value applies. |
| `type` | string | no | Transport type: `stdio`, `sse`, `http` |
| `command` | string | stdio | Executable command for stdio transport |
| `args` | array | no | Command arguments for stdio transport |
| `env` | object | no | Environment variables for stdio process |
| `env_file` | string | no | Path to environment file for stdio process |
| `url` | string | sse/http | Endpoint URL for `sse`/`http` transport |
| `headers` | object | no | HTTP headers for `sse`/`http` transport |
### Transport Behavior
@ -291,6 +292,50 @@ dynamically only when requested by the user.*
}
```
#### 4) Mixed setup: per-server deferred override
*Discovery is enabled globally, but `filesystem` is pinned as always-visible while `context7` follows the global
default (deferred). `aws` explicitly opts in to deferred mode even though it is the same as the global default.*
```json
{
"tools": {
"mcp": {
"enabled": true,
"discovery": {
"enabled": true,
"ttl": 5,
"max_search_results": 5,
"use_bm25": true
},
"servers": {
"filesystem": {
"enabled": true,
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"],
"deferred": false
},
"context7": {
"enabled": true,
"command": "npx",
"args": ["-y", "@upstash/context7-mcp"]
},
"aws": {
"enabled": true,
"command": "npx",
"args": ["-y", "aws-mcp-server"],
"deferred": true
}
}
}
}
}
```
> **Tip:** `deferred` on a per-server basis is independent of `discovery.enabled`. You can keep
> `discovery.enabled: false` globally (all tools visible by default) and still mark individual
> high-volume servers as `"deferred": true` to avoid polluting the context with their tools.
## Skills Tool
The skills tool configures skill discovery and installation via registries like ClawHub.

View file

@ -3,13 +3,13 @@ package agent
import (
"context"
"fmt"
"log"
"os"
"path/filepath"
"regexp"
"strings"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/media"
"github.com/sipeed/picoclaw/pkg/memory"
"github.com/sipeed/picoclaw/pkg/providers"
@ -85,9 +85,11 @@ func NewAgentInstance(
if cfg.Tools.IsToolEnabled("exec") {
execTool, err := tools.NewExecToolWithConfig(workspace, restrict, cfg, allowReadPaths)
if err != nil {
log.Fatalf("Critical error: unable to initialize exec tool: %v", err)
logger.ErrorCF("agent", "Failed to initialize exec tool; continuing without exec",
map[string]any{"error": err.Error()})
} else {
toolsRegistry.Register(execTool)
}
toolsRegistry.Register(execTool)
}
if cfg.Tools.IsToolEnabled("edit_file") {
@ -210,8 +212,8 @@ func NewAgentInstance(
})
lightCandidates = resolved
} else {
log.Printf("routing: light_model %q not found in model_list — routing disabled for agent %q",
rc.LightModel, agentID)
logger.WarnCF("agent", "Routing light model not found; routing disabled",
map[string]any{"light_model": rc.LightModel, "agent_id": agentID})
}
}
@ -320,7 +322,8 @@ func (a *AgentInstance) Close() error {
func initSessionStore(dir string) session.SessionStore {
store, err := memory.NewJSONLStore(dir)
if err != nil {
log.Printf("memory: init store: %v; using json sessions", err)
logger.WarnCF("agent", "Memory JSONL store init failed; falling back to json sessions",
map[string]any{"error": err.Error()})
return session.NewSessionManager(dir)
}
@ -328,11 +331,12 @@ func initSessionStore(dir string) session.SessionStore {
// Migration failure means the store could not write data.
// Fall back to SessionManager to avoid a split state where
// some sessions are in JSONL and others remain in JSON.
log.Printf("memory: migration failed: %v; falling back to json sessions", merr)
logger.WarnCF("agent", "Memory migration failed; falling back to json sessions",
map[string]any{"error": merr.Error()})
store.Close()
return session.NewSessionManager(dir)
} else if n > 0 {
log.Printf("memory: migrated %d session(s) to jsonl", n)
logger.InfoCF("agent", "Memory migrated to JSONL", map[string]any{"sessions_migrated": n})
}
return session.NewJSONLBackend(store)

View file

@ -246,3 +246,37 @@ func TestNewAgentInstance_AllowsMediaTempDirForReadListAndExec(t *testing.T) {
t.Fatalf("exec output missing media content: %s", execResult.ForLLM)
}
}
func TestNewAgentInstance_InvalidExecConfigDoesNotExit(t *testing.T) {
workspace := t.TempDir()
cfg := &config.Config{
Agents: config.AgentsConfig{
Defaults: config.AgentDefaults{
Workspace: workspace,
ModelName: "test-model",
},
},
Tools: config.ToolsConfig{
ReadFile: config.ReadFileToolConfig{Enabled: true},
Exec: config.ExecConfig{
ToolConfig: config.ToolConfig{Enabled: true},
EnableDenyPatterns: true,
CustomDenyPatterns: []string{"[invalid-regex"},
},
},
}
agent := NewAgentInstance(nil, &cfg.Agents.Defaults, cfg, &mockProvider{})
if agent == nil {
t.Fatal("expected agent instance, got nil")
}
if _, ok := agent.Tools.Get("exec"); ok {
t.Fatal("exec tool should not be registered when exec config is invalid")
}
if _, ok := agent.Tools.Get("read_file"); !ok {
t.Fatal("read_file tool should still be registered")
}
}

View file

@ -1322,6 +1322,22 @@ func (al *AgentLoop) runLLMIteration(
"iteration": iteration,
})
// Send tool feedback to chat channel if enabled
if al.cfg.Agents.Defaults.IsToolFeedbackEnabled() && opts.Channel != "" {
feedbackPreview := utils.Truncate(
string(argsJSON),
al.cfg.Agents.Defaults.GetToolFeedbackMaxArgsLength(),
)
feedbackMsg := fmt.Sprintf("\U0001f527 `%s`\n```\n%s\n```", tc.Name, feedbackPreview)
fbCtx, fbCancel := context.WithTimeout(ctx, 3*time.Second)
_ = al.bus.PublishOutbound(fbCtx, bus.OutboundMessage{
Channel: opts.Channel,
ChatID: opts.ChatID,
Content: feedbackMsg,
})
fbCancel()
}
// Create async callback for tools that implement AsyncExecutor.
// When the background work completes, this publishes the result
// as an inbound system message so processSystemMessage routes it

View file

@ -11,6 +11,7 @@ import (
"fmt"
"sync"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/mcp"
"github.com/sipeed/picoclaw/pkg/tools"
@ -111,6 +112,12 @@ func (al *AgentLoop) ensureMCPInitialized(ctx context.Context) error {
for serverName, conn := range servers {
uniqueTools += len(conn.Tools)
// Determine whether this server's tools should be deferred (hidden).
// Per-server "deferred" field takes precedence over the global Discovery.Enabled.
serverCfg := al.cfg.Tools.MCP.Servers[serverName]
registerAsHidden := serverIsDeferred(al.cfg.Tools.MCP.Discovery.Enabled, serverCfg)
for _, tool := range conn.Tools {
for _, agentID := range agentIDs {
agent, ok := al.registry.GetAgent(agentID)
@ -120,7 +127,7 @@ func (al *AgentLoop) ensureMCPInitialized(ctx context.Context) error {
mcpTool := tools.NewMCPTool(mcpManager, serverName, tool)
if al.cfg.Tools.MCP.Discovery.Enabled {
if registerAsHidden {
agent.Tools.RegisterHidden(mcpTool)
} else {
agent.Tools.Register(mcpTool)
@ -133,6 +140,7 @@ func (al *AgentLoop) ensureMCPInitialized(ctx context.Context) error {
"server": serverName,
"tool": tool.Name,
"name": mcpTool.Name(),
"deferred": registerAsHidden,
})
}
}
@ -198,3 +206,18 @@ func (al *AgentLoop) ensureMCPInitialized(ctx context.Context) error {
return al.mcp.getInitErr()
}
// serverIsDeferred reports whether an MCP server's tools should be registered
// as hidden (deferred/discovery mode).
//
// The per-server Deferred field takes precedence over the global discoveryEnabled
// default. When Deferred is nil, discoveryEnabled is used as the fallback.
func serverIsDeferred(discoveryEnabled bool, serverCfg config.MCPServerConfig) bool {
if !discoveryEnabled {
return false
}
if serverCfg.Deferred != nil {
return *serverCfg.Deferred
}
return true
}

View file

@ -0,0 +1,75 @@
// PicoClaw - Ultra-lightweight personal AI agent
// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot
// License: MIT
//
// Copyright (c) 2026 PicoClaw contributors
package agent
import (
"testing"
"github.com/sipeed/picoclaw/pkg/config"
)
func boolPtr(b bool) *bool { return &b }
func TestServerIsDeferred(t *testing.T) {
tests := []struct {
name string
discoveryEnabled bool
serverDeferred *bool
want bool
}{
// --- global false always wins: per-server deferred is ignored ---
{
name: "global false: per-server deferred=true is ignored",
discoveryEnabled: false,
serverDeferred: boolPtr(true),
want: false,
},
{
name: "global false: per-server deferred=false stays false",
discoveryEnabled: false,
serverDeferred: boolPtr(false),
want: false,
},
// --- global true: per-server override applies ---
{
name: "global true: per-server deferred=false opts out",
discoveryEnabled: true,
serverDeferred: boolPtr(false),
want: false,
},
{
name: "global true: per-server deferred=true stays true",
discoveryEnabled: true,
serverDeferred: boolPtr(true),
want: true,
},
// --- no per-server override: fall back to global ---
{
name: "no per-server field, global discovery enabled",
discoveryEnabled: true,
serverDeferred: nil,
want: true,
},
{
name: "no per-server field, global discovery disabled",
discoveryEnabled: false,
serverDeferred: nil,
want: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
serverCfg := config.MCPServerConfig{Deferred: tt.serverDeferred}
got := serverIsDeferred(tt.discoveryEnabled, serverCfg)
if got != tt.want {
t.Errorf("serverIsDeferred(discoveryEnabled=%v, deferred=%v) = %v, want %v",
tt.discoveryEnabled, tt.serverDeferred, got, tt.want)
}
})
}
}

View file

@ -86,9 +86,10 @@ type Manager struct {
mux *http.ServeMux
httpServer *http.Server
mu sync.RWMutex
placeholders sync.Map // "channel:chatID" → placeholderID (string)
typingStops sync.Map // "channel:chatID" → func()
reactionUndos sync.Map // "channel:chatID" → reactionEntry
placeholders sync.Map // "channel:chatID" → placeholderID (string)
typingStops sync.Map // "channel:chatID" → func()
reactionUndos sync.Map // "channel:chatID" → reactionEntry
channelHashes map[string]string // channel name → config hash
}
type asyncTask struct {
@ -178,17 +179,21 @@ func (m *Manager) preSend(ctx context.Context, name string, msg bus.OutboundMess
func NewManager(cfg *config.Config, messageBus *bus.MessageBus, store media.MediaStore) (*Manager, error) {
m := &Manager{
channels: make(map[string]Channel),
workers: make(map[string]*channelWorker),
bus: messageBus,
config: cfg,
mediaStore: store,
channels: make(map[string]Channel),
workers: make(map[string]*channelWorker),
bus: messageBus,
config: cfg,
mediaStore: store,
channelHashes: make(map[string]string),
}
if err := m.initChannels(); err != nil {
if err := m.initChannels(&cfg.Channels); err != nil {
return nil, err
}
// Store initial config hashes for all channels
m.channelHashes = toChannelHashes(cfg)
return m, nil
}
@ -232,15 +237,15 @@ func (m *Manager) initChannel(name, displayName string) {
}
}
func (m *Manager) initChannels() error {
func (m *Manager) initChannels(channels *config.ChannelsConfig) error {
logger.InfoC("channels", "Initializing channel manager")
if m.config.Channels.Telegram.Enabled && m.config.Channels.Telegram.Token != "" {
if channels.Telegram.Enabled && channels.Telegram.Token != "" {
m.initChannel("telegram", "Telegram")
}
if m.config.Channels.WhatsApp.Enabled {
waCfg := m.config.Channels.WhatsApp
if channels.WhatsApp.Enabled {
waCfg := channels.WhatsApp
if waCfg.UseNative {
m.initChannel("whatsapp_native", "WhatsApp Native")
} else if waCfg.BridgeURL != "" {
@ -248,62 +253,64 @@ func (m *Manager) initChannels() error {
}
}
if m.config.Channels.Feishu.Enabled {
if channels.Feishu.Enabled {
m.initChannel("feishu", "Feishu")
}
if m.config.Channels.Discord.Enabled && m.config.Channels.Discord.Token != "" {
if channels.Discord.Enabled && channels.Discord.Token != "" {
m.initChannel("discord", "Discord")
}
if m.config.Channels.MaixCam.Enabled {
if channels.MaixCam.Enabled {
m.initChannel("maixcam", "MaixCam")
}
if m.config.Channels.QQ.Enabled {
if channels.QQ.Enabled {
m.initChannel("qq", "QQ")
}
if m.config.Channels.DingTalk.Enabled && m.config.Channels.DingTalk.ClientID != "" {
if channels.DingTalk.Enabled && channels.DingTalk.ClientID != "" {
m.initChannel("dingtalk", "DingTalk")
}
if m.config.Channels.Slack.Enabled && m.config.Channels.Slack.BotToken != "" {
if channels.Slack.Enabled && channels.Slack.BotToken != "" {
m.initChannel("slack", "Slack")
}
if m.config.Channels.Matrix.Enabled &&
if channels.Matrix.Enabled &&
m.config.Channels.Matrix.Homeserver != "" &&
m.config.Channels.Matrix.UserID != "" &&
m.config.Channels.Matrix.AccessToken != "" {
m.initChannel("matrix", "Matrix")
}
if m.config.Channels.LINE.Enabled && m.config.Channels.LINE.ChannelAccessToken != "" {
if channels.LINE.Enabled && channels.LINE.ChannelAccessToken != "" {
m.initChannel("line", "LINE")
}
if m.config.Channels.OneBot.Enabled && m.config.Channels.OneBot.WSUrl != "" {
if channels.OneBot.Enabled && channels.OneBot.WSUrl != "" {
m.initChannel("onebot", "OneBot")
}
if m.config.Channels.WeCom.Enabled && m.config.Channels.WeCom.Token != "" {
if channels.WeCom.Enabled && channels.WeCom.Token != "" {
m.initChannel("wecom", "WeCom")
}
if m.config.Channels.WeComAIBot.Enabled && m.config.Channels.WeComAIBot.Token != "" {
if m.config.Channels.WeComAIBot.Enabled &&
((m.config.Channels.WeComAIBot.BotID != "" && m.config.Channels.WeComAIBot.Secret != "") ||
m.config.Channels.WeComAIBot.Token != "") {
m.initChannel("wecom_aibot", "WeCom AI Bot")
}
if m.config.Channels.WeComApp.Enabled && m.config.Channels.WeComApp.CorpID != "" {
if channels.WeComApp.Enabled && channels.WeComApp.CorpID != "" {
m.initChannel("wecom_app", "WeCom App")
}
if m.config.Channels.Pico.Enabled && m.config.Channels.Pico.Token != "" {
if channels.Pico.Enabled && channels.Pico.Token != "" {
m.initChannel("pico", "Pico")
}
if m.config.Channels.IRC.Enabled && m.config.Channels.IRC.Server != "" {
if channels.IRC.Enabled && channels.IRC.Server != "" {
m.initChannel("irc", "IRC")
}
@ -825,6 +832,68 @@ func (m *Manager) GetEnabledChannels() []string {
return names
}
// Reload updates the config reference without restarting channels.
// This is used when channel config hasn't changed but other parts of the config have.
func (m *Manager) Reload(ctx context.Context, cfg *config.Config) error {
m.mu.Lock()
defer m.mu.Unlock()
list := toChannelHashes(cfg)
added, removed := compareChannels(m.channelHashes, list)
for _, name := range removed {
// Stop all channels
channel := m.channels[name]
logger.InfoCF("channels", "Stopping channel", map[string]any{
"channel": name,
})
if err := channel.Stop(ctx); err != nil {
logger.ErrorCF("channels", "Error stopping channel", map[string]any{
"channel": name,
"error": err.Error(),
})
}
go func() {
m.UnregisterChannel(name)
}()
}
dispatchCtx, cancel := context.WithCancel(ctx)
m.dispatchTask = &asyncTask{cancel: cancel}
cc, err := toChannelConfig(cfg, added)
if err != nil {
logger.ErrorC("channels", fmt.Sprintf("toChannelConfig error: %v", err))
return err
}
err = m.initChannels(cc)
if err != nil {
logger.ErrorC("channels", fmt.Sprintf("initChannels error: %v", err))
return err
}
for _, name := range added {
channel := m.channels[name]
logger.InfoCF("channels", "Starting channel", map[string]any{
"channel": name,
})
if err := channel.Start(ctx); err != nil {
logger.ErrorCF("channels", "Failed to start channel", map[string]any{
"channel": name,
"error": err.Error(),
})
continue
}
// Lazily create worker only after channel starts successfully
w := newChannelWorker(name, channel)
m.workers[name] = w
go m.runWorker(dispatchCtx, name, w)
go m.runMediaWorker(dispatchCtx, name, w)
go func() {
m.RegisterChannel(name, channel)
}()
}
m.config = cfg
m.channelHashes = toChannelHashes(cfg)
return nil
}
func (m *Manager) RegisterChannel(name string, channel Channel) {
m.mu.Lock()
defer m.mu.Unlock()

View file

@ -0,0 +1,86 @@
package channels
import (
"crypto/md5"
"encoding/hex"
"encoding/json"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
)
func toChannelHashes(cfg *config.Config) map[string]string {
result := make(map[string]string)
ch := cfg.Channels
// should not be error
marshal, _ := json.Marshal(ch)
var channelConfig map[string]map[string]any
_ = json.Unmarshal(marshal, &channelConfig)
for key, value := range channelConfig {
if !value["enabled"].(bool) {
continue
}
valueBytes, _ := json.Marshal(value)
hash := md5.Sum(valueBytes)
result[key] = hex.EncodeToString(hash[:])
}
return result
}
func compareChannels(old, news map[string]string) (added, removed []string) {
for key, newHash := range news {
if oldHash, ok := old[key]; ok {
if newHash != oldHash {
removed = append(removed, key)
added = append(added, key)
}
} else {
added = append(added, key)
}
}
for key := range old {
if _, ok := news[key]; !ok {
removed = append(removed, key)
}
}
return added, removed
}
func toChannelConfig(cfg *config.Config, list []string) (*config.ChannelsConfig, error) {
result := &config.ChannelsConfig{}
ch := cfg.Channels
// should not be error
marshal, _ := json.Marshal(ch)
var channelConfig map[string]map[string]any
_ = json.Unmarshal(marshal, &channelConfig)
temp := make(map[string]map[string]any, 0)
for key, value := range channelConfig {
found := false
for _, s := range list {
if key == s {
found = true
break
}
}
if !found || !value["enabled"].(bool) {
continue
}
temp[key] = value
}
marshal, err := json.Marshal(temp)
if err != nil {
logger.Errorf("marshal error: %v", err)
return nil, err
}
err = json.Unmarshal(marshal, result)
if err != nil {
logger.Errorf("unmarshal error: %v", err)
return nil, err
}
return result, nil
}

View file

@ -0,0 +1,51 @@
package channels
import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
)
func TestToChannelHashes(t *testing.T) {
logger.SetLevel(logger.DEBUG)
cfg := config.DefaultConfig()
results := toChannelHashes(cfg)
assert.Equal(t, 0, len(results))
logger.Debugf("results: %v", results)
cfg2 := config.DefaultConfig()
cfg2.Channels.DingTalk.Enabled = true
results2 := toChannelHashes(cfg2)
assert.Equal(t, 1, len(results2))
logger.Debugf("results2: %v", results2)
added, removed := compareChannels(results, results2)
assert.EqualValues(t, []string{"dingtalk"}, added)
assert.EqualValues(t, []string(nil), removed)
cfg3 := config.DefaultConfig()
cfg3.Channels.Telegram.Enabled = true
results3 := toChannelHashes(cfg3)
assert.Equal(t, 1, len(results3))
logger.Debugf("results3: %v", results3)
added, removed = compareChannels(results2, results3)
assert.EqualValues(t, []string{"dingtalk"}, removed)
assert.EqualValues(t, []string{"telegram"}, added)
cfg3.Channels.Telegram.Token = "114314"
results4 := toChannelHashes(cfg3)
assert.Equal(t, 1, len(results4))
logger.Debugf("results4: %v", results4)
added, removed = compareChannels(results3, results4)
assert.EqualValues(t, []string{"telegram"}, removed)
assert.EqualValues(t, []string{"telegram"}, added)
cc, err := toChannelConfig(cfg3, added)
assert.NoError(t, err)
logger.Debugf("cc: %#v", cc.Telegram)
assert.Equal(t, "114314", cc.Telegram.Token)
assert.Equal(t, true, cc.Telegram.Enabled)
cc, err = toChannelConfig(cfg2, added)
assert.NoError(t, err)
logger.Debugf("cc: %#v", cc.Telegram)
assert.Equal(t, "", cc.Telegram.Token)
assert.Equal(t, false, cc.Telegram.Enabled)
}

View file

@ -0,0 +1,41 @@
package qq
import (
"fmt"
"strings"
"github.com/sipeed/picoclaw/pkg/logger"
)
// botGoLogger preserves useful SDK info logs while demoting noisy heartbeat
// traffic to DEBUG so long-running QQ sessions do not spam the console.
type botGoLogger struct {
*logger.Logger
}
func newBotGoLogger(component string) *botGoLogger {
return &botGoLogger{Logger: logger.NewLogger(component)}
}
func (b *botGoLogger) Info(v ...any) {
message := fmt.Sprint(v...)
if shouldDemoteBotGoInfo(message) {
b.Logger.Debug(message)
return
}
b.Logger.Info(message)
}
func (b *botGoLogger) Infof(format string, v ...any) {
message := fmt.Sprintf(format, v...)
if shouldDemoteBotGoInfo(message) {
b.Logger.Debug(message)
return
}
b.Logger.Info(message)
}
func shouldDemoteBotGoInfo(message string) bool {
return strings.Contains(message, " write Heartbeat message") ||
strings.Contains(message, " receive HeartbeatAck message")
}

View file

@ -2,7 +2,15 @@ package qq
import (
"context"
"encoding/base64"
"encoding/json"
"errors"
"fmt"
"net/http"
"net/url"
"os"
"path"
"path/filepath"
"regexp"
"strings"
"sync"
@ -10,9 +18,10 @@ import (
"time"
"github.com/tencent-connect/botgo"
"github.com/tencent-connect/botgo/constant"
"github.com/tencent-connect/botgo/dto"
"github.com/tencent-connect/botgo/event"
"github.com/tencent-connect/botgo/openapi"
"github.com/tencent-connect/botgo/openapi/options"
"github.com/tencent-connect/botgo/token"
"golang.org/x/oauth2"
@ -21,6 +30,8 @@ import (
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/identity"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/media"
"github.com/sipeed/picoclaw/pkg/utils"
)
const (
@ -29,16 +40,29 @@ const (
dedupMaxSize = 10000 // hard cap on dedup map entries
typingResend = 8 * time.Second
typingSeconds = 10
bytesPerMiB = 1024 * 1024
)
type qqAPI interface {
WS(ctx context.Context, params map[string]string, body string) (*dto.WebsocketAP, error)
PostGroupMessage(
ctx context.Context, groupID string, msg dto.APIMessage, opt ...options.Option,
) (*dto.Message, error)
PostC2CMessage(
ctx context.Context, userID string, msg dto.APIMessage, opt ...options.Option,
) (*dto.Message, error)
Transport(ctx context.Context, method, url string, body any) ([]byte, error)
}
type QQChannel struct {
*channels.BaseChannel
config config.QQConfig
api openapi.OpenAPI
api qqAPI
tokenSource oauth2.TokenSource
ctx context.Context
cancel context.CancelFunc
sessionManager botgo.SessionManager
downloadFn func(urlStr, filename string) string
// Chat routing: track whether a chatID is group or direct.
chatType sync.Map // chatID → "group" | "direct"
@ -78,7 +102,7 @@ func (c *QQChannel) Start(ctx context.Context) error {
return fmt.Errorf("QQ app_id and app_secret not configured")
}
botgo.SetLogger(logger.NewLogger("botgo"))
botgo.SetLogger(newBotGoLogger("botgo"))
logger.InfoC("qq", "Starting QQ bot (WebSocket mode)")
// Reinitialize shutdown signal for clean restart.
@ -199,20 +223,7 @@ func (c *QQChannel) Send(ctx context.Context, msg bus.OutboundMessage) error {
msgToCreate.Content = ""
}
// Attach passive reply msg_id and msg_seq if available.
if v, ok := c.lastMsgID.Load(msg.ChatID); ok {
if msgID, ok := v.(string); ok && msgID != "" {
msgToCreate.MsgID = msgID
// Increment msg_seq atomically for multi-part replies.
if counterVal, ok := c.msgSeqCounters.Load(msg.ChatID); ok {
if counter, ok := counterVal.(*atomic.Uint64); ok {
seq := counter.Add(1)
msgToCreate.MsgSeq = uint32(seq)
}
}
}
}
c.applyPassiveReplyMetadata(msg.ChatID, msgToCreate)
// Sanitize URLs in group messages to avoid QQ's URL blacklist rejection.
if chatKind == "group" {
@ -305,9 +316,9 @@ func (c *QQChannel) StartTyping(ctx context.Context, chatID string) (func(), err
}
// SendMedia implements the channels.MediaSender interface.
// QQ RichMediaMessage requires an HTTP/HTTPS URL — local file paths are not supported.
// If part.Ref is already an http(s) URL it is used directly; otherwise we try
// the media store, and skip with a warning if the resolved path is not an HTTP URL.
// QQ group/C2C media sending is a two-step flow:
// 1. Upload media to /files using a remote URL or base64-encoded local bytes.
// 2. Send a msg_type=7 message using the returned file_info.
func (c *QQChannel) SendMedia(ctx context.Context, msg bus.OutboundMediaMessage) error {
if !c.IsRunning() {
return channels.ErrNotRunning
@ -316,69 +327,24 @@ func (c *QQChannel) SendMedia(ctx context.Context, msg bus.OutboundMediaMessage)
chatKind := c.getChatKind(msg.ChatID)
for _, part := range msg.Parts {
// If the ref is already an HTTP(S) URL, use it directly.
mediaURL := part.Ref
if !isHTTPURL(mediaURL) {
// Try resolving through media store.
store := c.GetMediaStore()
if store == nil {
logger.WarnCF("qq", "QQ media requires HTTP/HTTPS URL, no media store available", map[string]any{
"ref": part.Ref,
})
continue
fileInfo, err := c.uploadMedia(ctx, chatKind, msg.ChatID, part)
if err != nil {
logger.ErrorCF("qq", "Failed to upload media", map[string]any{
"type": part.Type,
"chat_id": msg.ChatID,
"error": err.Error(),
})
if errors.Is(err, channels.ErrSendFailed) {
return err
}
resolved, err := store.Resolve(part.Ref)
if err != nil {
logger.ErrorCF("qq", "Failed to resolve media ref", map[string]any{
"ref": part.Ref,
"error": err.Error(),
})
continue
}
if !isHTTPURL(resolved) {
logger.WarnCF("qq", "QQ media requires HTTP/HTTPS URL, local files not supported", map[string]any{
"ref": part.Ref,
"resolved": resolved,
})
continue
}
mediaURL = resolved
return fmt.Errorf("qq send media: %w", channels.ErrTemporary)
}
// Map part type to QQ file type: 1=image, 2=video, 3=audio, 4=file.
var fileType uint64
switch part.Type {
case "image":
fileType = 1
case "video":
fileType = 2
case "audio":
fileType = 3
default:
fileType = 4 // file
}
richMedia := &dto.RichMediaMessage{
FileType: fileType,
URL: mediaURL,
SrvSendMsg: true,
}
var sendErr error
if chatKind == "group" {
_, sendErr = c.api.PostGroupMessage(ctx, msg.ChatID, richMedia)
} else {
_, sendErr = c.api.PostC2CMessage(ctx, msg.ChatID, richMedia)
}
if sendErr != nil {
if err := c.sendUploadedMedia(ctx, chatKind, msg.ChatID, part, fileInfo); err != nil {
logger.ErrorCF("qq", "Failed to send media", map[string]any{
"type": part.Type,
"chat_id": msg.ChatID,
"error": sendErr.Error(),
"error": err.Error(),
})
return fmt.Errorf("qq send media: %w", channels.ErrTemporary)
}
@ -387,6 +353,161 @@ func (c *QQChannel) SendMedia(ctx context.Context, msg bus.OutboundMediaMessage)
return nil
}
type qqMediaUpload struct {
FileType uint64 `json:"file_type"`
URL string `json:"url,omitempty"`
FileData string `json:"file_data,omitempty"`
SrvSendMsg bool `json:"srv_send_msg,omitempty"`
}
func (c *QQChannel) uploadMedia(
ctx context.Context,
chatKind, chatID string,
part bus.MediaPart,
) ([]byte, error) {
payload, err := c.buildMediaUpload(part)
if err != nil {
return nil, err
}
body, err := c.api.Transport(ctx, http.MethodPost, c.mediaUploadURL(chatKind, chatID), payload)
if err != nil {
return nil, err
}
var uploaded dto.Message
if err := json.Unmarshal(body, &uploaded); err != nil {
return nil, fmt.Errorf("qq decode media upload response: %w", err)
}
if len(uploaded.FileInfo) == 0 {
return nil, fmt.Errorf("qq upload media: missing file_info")
}
return uploaded.FileInfo, nil
}
func (c *QQChannel) buildMediaUpload(part bus.MediaPart) (*qqMediaUpload, error) {
payload := &qqMediaUpload{
FileType: qqFileType(part.Type),
}
mediaRef := part.Ref
if isHTTPURL(mediaRef) {
payload.URL = mediaRef
return payload, nil
}
store := c.GetMediaStore()
if store == nil {
return nil, fmt.Errorf("no media store available: %w", channels.ErrSendFailed)
}
resolved, err := store.Resolve(part.Ref)
if err != nil {
return nil, fmt.Errorf("qq resolve media ref %q: %v: %w", part.Ref, err, channels.ErrSendFailed)
}
if isHTTPURL(resolved) {
payload.URL = resolved
return payload, nil
}
if limitBytes := c.maxBase64FileSizeBytes(); limitBytes > 0 {
info, statErr := os.Stat(resolved)
if statErr != nil {
return nil, fmt.Errorf("qq stat local media %q: %v: %w", resolved, statErr, channels.ErrSendFailed)
}
if info.Size() > limitBytes {
return nil, fmt.Errorf(
"qq local media %q exceeds max_base64_file_size_mib (%d > %d bytes): %w",
resolved,
info.Size(),
limitBytes,
channels.ErrSendFailed,
)
}
}
data, err := os.ReadFile(resolved)
if err != nil {
return nil, fmt.Errorf("qq read local media %q: %v: %w", resolved, err, channels.ErrSendFailed)
}
payload.FileData = base64.StdEncoding.EncodeToString(data)
return payload, nil
}
func (c *QQChannel) sendUploadedMedia(
ctx context.Context,
chatKind, chatID string,
part bus.MediaPart,
fileInfo []byte,
) error {
msg := &dto.MessageToCreate{
Content: part.Caption,
MsgType: dto.RichMediaMsg,
Media: &dto.MediaInfo{
FileInfo: fileInfo,
},
}
c.applyPassiveReplyMetadata(chatID, msg)
if chatKind == "group" && msg.Content != "" {
msg.Content = sanitizeURLs(msg.Content)
}
if chatKind == "group" {
_, err := c.api.PostGroupMessage(ctx, chatID, msg)
return err
}
_, err := c.api.PostC2CMessage(ctx, chatID, msg)
return err
}
func (c *QQChannel) applyPassiveReplyMetadata(chatID string, msg *dto.MessageToCreate) {
if v, ok := c.lastMsgID.Load(chatID); ok {
if msgID, ok := v.(string); ok && msgID != "" {
msg.MsgID = msgID
// Increment msg_seq atomically for multi-part replies.
if counterVal, ok := c.msgSeqCounters.Load(chatID); ok {
if counter, ok := counterVal.(*atomic.Uint64); ok {
seq := counter.Add(1)
msg.MsgSeq = uint32(seq)
}
}
}
}
}
func (c *QQChannel) mediaUploadURL(chatKind, chatID string) string {
base := constant.APIDomain
if chatKind == "group" {
return fmt.Sprintf("%s/v2/groups/%s/files", base, chatID)
}
return fmt.Sprintf("%s/v2/users/%s/files", base, chatID)
}
func qqFileType(partType string) uint64 {
switch partType {
case "image":
return 1
case "video":
return 2
case "audio":
return 3
default:
return 4
}
}
func (c *QQChannel) maxBase64FileSizeBytes() int64 {
if c.config.MaxBase64FileSizeMiB <= 0 {
return 0
}
return c.config.MaxBase64FileSizeMiB * bytesPerMiB
}
// handleC2CMessage handles QQ private messages.
func (c *QQChannel) handleC2CMessage() event.C2CMessageEventHandler {
return func(event *dto.WSPayload, data *dto.WSC2CMessageData) error {
@ -404,16 +525,30 @@ func (c *QQChannel) handleC2CMessage() event.C2CMessageEventHandler {
return nil
}
// extract message content
content := data.Content
if content == "" {
logger.DebugC("qq", "Received empty message, ignoring")
sender := bus.SenderInfo{
Platform: "qq",
PlatformID: data.Author.ID,
CanonicalID: identity.BuildCanonicalID("qq", data.Author.ID),
}
if !c.IsAllowedSender(sender) {
return nil
}
content := strings.TrimSpace(data.Content)
mediaPaths, attachmentNotes := c.extractInboundAttachments(senderID, data.ID, data.Attachments)
for _, note := range attachmentNotes {
content = appendContent(content, note)
}
if content == "" && len(mediaPaths) == 0 {
logger.DebugC("qq", "Received empty C2C message with no attachments, ignoring")
return nil
}
logger.InfoCF("qq", "Received C2C message", map[string]any{
"sender": senderID,
"length": len(content),
"sender": senderID,
"length": len(content),
"media_count": len(mediaPaths),
})
// Store chat routing context.
@ -427,23 +562,13 @@ func (c *QQChannel) handleC2CMessage() event.C2CMessageEventHandler {
"account_id": senderID,
}
sender := bus.SenderInfo{
Platform: "qq",
PlatformID: data.Author.ID,
CanonicalID: identity.BuildCanonicalID("qq", data.Author.ID),
}
if !c.IsAllowedSender(sender) {
return nil
}
c.HandleMessage(c.ctx,
bus.Peer{Kind: "direct", ID: senderID},
data.ID,
senderID,
senderID,
content,
[]string{},
mediaPaths,
metadata,
sender,
)
@ -469,24 +594,38 @@ func (c *QQChannel) handleGroupATMessage() event.GroupATMessageEventHandler {
return nil
}
// extract message content (remove @ bot part)
content := data.Content
if content == "" {
logger.DebugC("qq", "Received empty group message, ignoring")
sender := bus.SenderInfo{
Platform: "qq",
PlatformID: data.Author.ID,
CanonicalID: identity.BuildCanonicalID("qq", data.Author.ID),
}
if !c.IsAllowedSender(sender) {
return nil
}
// GroupAT event means bot is always mentioned; apply group trigger filtering
content := strings.TrimSpace(data.Content)
mediaPaths, attachmentNotes := c.extractInboundAttachments(data.GroupID, data.ID, data.Attachments)
for _, note := range attachmentNotes {
content = appendContent(content, note)
}
// GroupAT event means bot is always mentioned; apply group trigger filtering.
respond, cleaned := c.ShouldRespondInGroup(true, content)
if !respond {
return nil
}
content = cleaned
if content == "" && len(mediaPaths) == 0 {
logger.DebugC("qq", "Received empty group message with no attachments, ignoring")
return nil
}
logger.InfoCF("qq", "Received group AT message", map[string]any{
"sender": senderID,
"group": data.GroupID,
"length": len(content),
"sender": senderID,
"group": data.GroupID,
"length": len(content),
"media_count": len(mediaPaths),
})
// Store chat routing context using GroupID as chatID.
@ -501,23 +640,13 @@ func (c *QQChannel) handleGroupATMessage() event.GroupATMessageEventHandler {
"group_id": data.GroupID,
}
sender := bus.SenderInfo{
Platform: "qq",
PlatformID: data.Author.ID,
CanonicalID: identity.BuildCanonicalID("qq", data.Author.ID),
}
if !c.IsAllowedSender(sender) {
return nil
}
c.HandleMessage(c.ctx,
bus.Peer{Kind: "group", ID: data.GroupID},
data.ID,
senderID,
data.GroupID,
content,
[]string{},
mediaPaths,
metadata,
sender,
)
@ -526,6 +655,157 @@ func (c *QQChannel) handleGroupATMessage() event.GroupATMessageEventHandler {
}
}
func (c *QQChannel) extractInboundAttachments(
chatID, messageID string,
attachments []*dto.MessageAttachment,
) ([]string, []string) {
if len(attachments) == 0 {
return nil, nil
}
scope := channels.BuildMediaScope("qq", chatID, messageID)
mediaPaths := make([]string, 0, len(attachments))
notes := make([]string, 0, len(attachments))
storeMedia := func(localPath string, attachment *dto.MessageAttachment) string {
if store := c.GetMediaStore(); store != nil {
ref, err := store.Store(localPath, media.MediaMeta{
Filename: qqAttachmentFilename(attachment),
ContentType: attachment.ContentType,
Source: "qq",
}, scope)
if err == nil {
return ref
}
}
return localPath
}
for _, attachment := range attachments {
if attachment == nil {
continue
}
filename := qqAttachmentFilename(attachment)
if localPath := c.downloadAttachment(attachment.URL, filename); localPath != "" {
mediaPaths = append(mediaPaths, storeMedia(localPath, attachment))
} else if attachment.URL != "" {
mediaPaths = append(mediaPaths, attachment.URL)
}
notes = append(notes, qqAttachmentNote(attachment))
}
return mediaPaths, notes
}
func (c *QQChannel) downloadAttachment(urlStr, filename string) string {
if urlStr == "" {
return ""
}
if c.downloadFn != nil {
return c.downloadFn(urlStr, filename)
}
return utils.DownloadFile(urlStr, filename, utils.DownloadOptions{
LoggerPrefix: "qq",
ExtraHeaders: c.downloadHeaders(),
})
}
func (c *QQChannel) downloadHeaders() map[string]string {
headers := map[string]string{}
if c.config.AppID != "" {
headers["X-Union-Appid"] = c.config.AppID
}
if c.tokenSource != nil {
if tk, err := c.tokenSource.Token(); err == nil && tk.AccessToken != "" {
auth := strings.TrimSpace(tk.TokenType + " " + tk.AccessToken)
if auth != "" {
headers["Authorization"] = auth
}
}
}
if len(headers) == 0 {
return nil
}
return headers
}
func qqAttachmentFilename(attachment *dto.MessageAttachment) string {
if attachment == nil {
return "attachment"
}
if attachment.FileName != "" {
return attachment.FileName
}
if attachment.URL != "" {
if parsed, err := url.Parse(attachment.URL); err == nil {
if base := path.Base(parsed.Path); base != "" && base != "." && base != "/" {
return base
}
}
}
switch qqAttachmentKind(attachment) {
case "image":
return "image"
case "audio":
return "audio"
case "video":
return "video"
default:
return "attachment"
}
}
func qqAttachmentKind(attachment *dto.MessageAttachment) string {
if attachment == nil {
return "file"
}
contentType := strings.ToLower(attachment.ContentType)
filename := strings.ToLower(attachment.FileName)
switch {
case strings.HasPrefix(contentType, "image/"):
return "image"
case strings.HasPrefix(contentType, "video/"):
return "video"
case strings.HasPrefix(contentType, "audio/"), contentType == "application/ogg", contentType == "application/x-ogg":
return "audio"
}
switch filepath.Ext(filename) {
case ".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp", ".svg":
return "image"
case ".mp4", ".avi", ".mov", ".webm", ".mkv":
return "video"
case ".mp3", ".wav", ".ogg", ".m4a", ".flac", ".aac", ".wma", ".opus", ".silk":
return "audio"
default:
return "file"
}
}
func qqAttachmentNote(attachment *dto.MessageAttachment) string {
filename := qqAttachmentFilename(attachment)
switch qqAttachmentKind(attachment) {
case "image":
return fmt.Sprintf("[image: %s]", filename)
case "audio":
return fmt.Sprintf("[audio: %s]", filename)
case "video":
return fmt.Sprintf("[video: %s]", filename)
default:
return fmt.Sprintf("[file: %s]", filename)
}
}
// isDuplicate checks whether a message has been seen within the TTL window.
// It also enforces a hard cap on map size by evicting oldest entries.
func (c *QQChannel) isDuplicate(messageID string) bool {
@ -587,6 +867,16 @@ func isHTTPURL(s string) bool {
return strings.HasPrefix(s, "http://") || strings.HasPrefix(s, "https://")
}
func appendContent(content, suffix string) string {
if suffix == "" {
return content
}
if content == "" {
return suffix
}
return content + "\n" + suffix
}
// urlPattern matches URLs with explicit http(s):// scheme.
// Only scheme-prefixed URLs are matched to avoid false positives on bare text
// like version numbers (e.g., "1.2.3") or domain-like fragments.

View file

@ -2,13 +2,22 @@ package qq
import (
"context"
"encoding/base64"
"encoding/json"
"errors"
"os"
"strings"
"sync/atomic"
"testing"
"time"
"github.com/tencent-connect/botgo/dto"
"github.com/tencent-connect/botgo/openapi/options"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/media"
)
func TestHandleC2CMessage_IncludesAccountIDMetadata(t *testing.T) {
@ -50,3 +59,438 @@ func TestHandleC2CMessage_IncludesAccountIDMetadata(t *testing.T) {
}
}
}
func TestHandleC2CMessage_AttachmentOnlyPublishesMedia(t *testing.T) {
messageBus := bus.NewMessageBus()
store := media.NewFileMediaStore()
localPath := writeTempFile(t, t.TempDir(), "image.png", []byte("fake-image"))
ch := &QQChannel{
BaseChannel: channels.NewBaseChannel("qq", nil, messageBus, nil),
dedup: make(map[string]time.Time),
done: make(chan struct{}),
ctx: context.Background(),
downloadFn: func(urlStr, filename string) string {
if filename != "image.png" {
t.Fatalf("download filename = %q, want image.png", filename)
}
return localPath
},
}
ch.SetMediaStore(store)
err := ch.handleC2CMessage()(nil, &dto.WSC2CMessageData{
ID: "msg-attachment",
Content: "",
Author: &dto.User{
ID: "7750283E123456",
},
Attachments: []*dto.MessageAttachment{{
URL: "https://example.com/image.png",
FileName: "image.png",
ContentType: "image/png",
}},
})
if err != nil {
t.Fatalf("handleC2CMessage() error = %v", err)
}
inbound := waitInboundMessage(t, messageBus)
if inbound.Content != "[image: image.png]" {
t.Fatalf("inbound.Content = %q", inbound.Content)
}
if len(inbound.Media) != 1 {
t.Fatalf("len(inbound.Media) = %d, want 1", len(inbound.Media))
}
if !strings.HasPrefix(inbound.Media[0], "media://") {
t.Fatalf("inbound.Media[0] = %q, want media:// ref", inbound.Media[0])
}
_, meta, err := store.ResolveWithMeta(inbound.Media[0])
if err != nil {
t.Fatalf("ResolveWithMeta() error = %v", err)
}
if meta.Filename != "image.png" {
t.Fatalf("meta.Filename = %q, want image.png", meta.Filename)
}
if meta.ContentType != "image/png" {
t.Fatalf("meta.ContentType = %q, want image/png", meta.ContentType)
}
}
func TestHandleGroupATMessage_AttachmentOnlyPublishesMedia(t *testing.T) {
messageBus := bus.NewMessageBus()
store := media.NewFileMediaStore()
localPath := writeTempFile(t, t.TempDir(), "report.pdf", []byte("fake-pdf"))
ch := &QQChannel{
BaseChannel: channels.NewBaseChannel("qq", nil, messageBus, nil),
dedup: make(map[string]time.Time),
done: make(chan struct{}),
ctx: context.Background(),
downloadFn: func(urlStr, filename string) string {
if filename != "report.pdf" {
t.Fatalf("download filename = %q, want report.pdf", filename)
}
return localPath
},
}
ch.SetMediaStore(store)
err := ch.handleGroupATMessage()(nil, &dto.WSGroupATMessageData{
ID: "group-attachment",
GroupID: "group-1",
Content: "",
Author: &dto.User{
ID: "7750283E123456",
},
Attachments: []*dto.MessageAttachment{{
URL: "https://example.com/report.pdf",
FileName: "report.pdf",
ContentType: "application/pdf",
}},
})
if err != nil {
t.Fatalf("handleGroupATMessage() error = %v", err)
}
inbound := waitInboundMessage(t, messageBus)
if inbound.Content != "[file: report.pdf]" {
t.Fatalf("inbound.Content = %q", inbound.Content)
}
if len(inbound.Media) != 1 {
t.Fatalf("len(inbound.Media) = %d, want 1", len(inbound.Media))
}
if !strings.HasPrefix(inbound.Media[0], "media://") {
t.Fatalf("inbound.Media[0] = %q, want media:// ref", inbound.Media[0])
}
if inbound.Peer.Kind != "group" || inbound.Peer.ID != "group-1" {
t.Fatalf("inbound.Peer = %+v, want group/group-1", inbound.Peer)
}
}
func TestSendMedia_UploadsLocalFileAsBase64(t *testing.T) {
messageBus := bus.NewMessageBus()
store := media.NewFileMediaStore()
tmpFile, err := os.CreateTemp(t.TempDir(), "qq-media-*.png")
if err != nil {
t.Fatalf("CreateTemp() error = %v", err)
}
defer tmpFile.Close()
content := []byte("local-image-data")
if _, writeErr := tmpFile.Write(content); writeErr != nil {
t.Fatalf("Write() error = %v", writeErr)
}
ref, err := store.Store(tmpFile.Name(), media.MediaMeta{
Filename: "reply.png",
ContentType: "image/png",
}, "qq:test")
if err != nil {
t.Fatalf("Store() error = %v", err)
}
api := &fakeQQAPI{
transportResp: mustJSON(t, dto.Message{FileInfo: []byte("uploaded-file-info")}),
}
ch := &QQChannel{
BaseChannel: channels.NewBaseChannel("qq", nil, messageBus, nil),
api: api,
dedup: make(map[string]time.Time),
done: make(chan struct{}),
ctx: context.Background(),
}
ch.SetRunning(true)
ch.SetMediaStore(store)
ch.chatType.Store("group-1", "group")
ch.lastMsgID.Store("group-1", "msg-1")
ch.msgSeqCounters.Store("group-1", new(atomic.Uint64))
err = ch.SendMedia(context.Background(), bus.OutboundMediaMessage{
ChatID: "group-1",
Parts: []bus.MediaPart{{
Type: "image",
Ref: ref,
Caption: "see https://example.com/image",
}},
})
if err != nil {
t.Fatalf("SendMedia() error = %v", err)
}
if len(api.transportCalls) != 1 {
t.Fatalf("transportCalls = %d, want 1", len(api.transportCalls))
}
upload := api.transportCalls[0]
if upload.method != "POST" {
t.Fatalf("upload method = %q, want POST", upload.method)
}
if upload.url != "https://api.sgroup.qq.com/v2/groups/group-1/files" {
t.Fatalf("upload url = %q", upload.url)
}
if upload.body.URL != "" {
t.Fatalf("upload URL = %q, want empty", upload.body.URL)
}
wantBase64 := base64.StdEncoding.EncodeToString(content)
if upload.body.FileData != wantBase64 {
t.Fatalf("upload file_data = %q, want %q", upload.body.FileData, wantBase64)
}
if upload.body.FileType != 1 {
t.Fatalf("upload file_type = %d, want 1", upload.body.FileType)
}
if len(api.groupMessages) != 1 {
t.Fatalf("groupMessages = %d, want 1", len(api.groupMessages))
}
msg, ok := api.groupMessages[0].(*dto.MessageToCreate)
if !ok {
t.Fatalf("groupMessages[0] type = %T, want *dto.MessageToCreate", api.groupMessages[0])
}
if msg.MsgType != dto.RichMediaMsg {
t.Fatalf("msg.MsgType = %d, want %d", msg.MsgType, dto.RichMediaMsg)
}
if msg.MsgID != "msg-1" {
t.Fatalf("msg.MsgID = %q, want msg-1", msg.MsgID)
}
if msg.MsgSeq != 1 {
t.Fatalf("msg.MsgSeq = %d, want 1", msg.MsgSeq)
}
if msg.Content != "see https://example。com/image" {
t.Fatalf("msg.Content = %q", msg.Content)
}
if msg.Media == nil || string(msg.Media.FileInfo) != "uploaded-file-info" {
t.Fatalf("msg.Media.FileInfo = %q, want uploaded-file-info", string(msg.Media.FileInfo))
}
}
func TestSendMedia_UsesRemoteURLUploadForC2C(t *testing.T) {
messageBus := bus.NewMessageBus()
api := &fakeQQAPI{
transportResp: mustJSON(t, dto.Message{FileInfo: []byte("remote-file-info")}),
}
ch := &QQChannel{
BaseChannel: channels.NewBaseChannel("qq", nil, messageBus, nil),
api: api,
dedup: make(map[string]time.Time),
done: make(chan struct{}),
ctx: context.Background(),
}
ch.SetRunning(true)
ch.chatType.Store("user-1", "direct")
err := ch.SendMedia(context.Background(), bus.OutboundMediaMessage{
ChatID: "user-1",
Parts: []bus.MediaPart{{
Type: "file",
Ref: "https://cdn.example.com/report.pdf",
}},
})
if err != nil {
t.Fatalf("SendMedia() error = %v", err)
}
if len(api.transportCalls) != 1 {
t.Fatalf("transportCalls = %d, want 1", len(api.transportCalls))
}
upload := api.transportCalls[0]
if upload.url != "https://api.sgroup.qq.com/v2/users/user-1/files" {
t.Fatalf("upload url = %q", upload.url)
}
if upload.body.URL != "https://cdn.example.com/report.pdf" {
t.Fatalf("upload URL = %q", upload.body.URL)
}
if upload.body.FileData != "" {
t.Fatalf("upload file_data = %q, want empty", upload.body.FileData)
}
if upload.body.FileType != 4 {
t.Fatalf("upload file_type = %d, want 4", upload.body.FileType)
}
if len(api.c2cMessages) != 1 {
t.Fatalf("c2cMessages = %d, want 1", len(api.c2cMessages))
}
msg, ok := api.c2cMessages[0].(*dto.MessageToCreate)
if !ok {
t.Fatalf("c2cMessages[0] type = %T, want *dto.MessageToCreate", api.c2cMessages[0])
}
if msg.MsgType != dto.RichMediaMsg {
t.Fatalf("msg.MsgType = %d, want %d", msg.MsgType, dto.RichMediaMsg)
}
if msg.Media == nil || string(msg.Media.FileInfo) != "remote-file-info" {
t.Fatalf("msg.Media.FileInfo = %q, want remote-file-info", string(msg.Media.FileInfo))
}
}
func TestSendMedia_ReturnsSendFailedWithoutMediaStore(t *testing.T) {
messageBus := bus.NewMessageBus()
ch := &QQChannel{
BaseChannel: channels.NewBaseChannel("qq", nil, messageBus, nil),
api: &fakeQQAPI{},
dedup: make(map[string]time.Time),
done: make(chan struct{}),
ctx: context.Background(),
}
ch.SetRunning(true)
ch.chatType.Store("group-1", "group")
err := ch.SendMedia(context.Background(), bus.OutboundMediaMessage{
ChatID: "group-1",
Parts: []bus.MediaPart{{
Type: "image",
Ref: "media://missing",
}},
})
if !errors.Is(err, channels.ErrSendFailed) {
t.Fatalf("SendMedia() error = %v, want ErrSendFailed", err)
}
}
func TestSendMedia_ReturnsSendFailedWhenLocalFileExceedsBase64MiBLimit(t *testing.T) {
messageBus := bus.NewMessageBus()
store := media.NewFileMediaStore()
tmpFile, err := os.CreateTemp(t.TempDir(), "qq-media-too-large-*.bin")
if err != nil {
t.Fatalf("CreateTemp() error = %v", err)
}
defer tmpFile.Close()
content := make([]byte, bytesPerMiB+1)
if _, writeErr := tmpFile.Write(content); writeErr != nil {
t.Fatalf("Write() error = %v", writeErr)
}
ref, err := store.Store(tmpFile.Name(), media.MediaMeta{
Filename: "large.bin",
ContentType: "application/octet-stream",
}, "qq:test")
if err != nil {
t.Fatalf("Store() error = %v", err)
}
api := &fakeQQAPI{}
ch := &QQChannel{
BaseChannel: channels.NewBaseChannel("qq", nil, messageBus, nil),
config: config.QQConfig{
MaxBase64FileSizeMiB: 1,
},
api: api,
dedup: make(map[string]time.Time),
done: make(chan struct{}),
ctx: context.Background(),
}
ch.SetRunning(true)
ch.SetMediaStore(store)
ch.chatType.Store("group-1", "group")
err = ch.SendMedia(context.Background(), bus.OutboundMediaMessage{
ChatID: "group-1",
Parts: []bus.MediaPart{{
Type: "file",
Ref: ref,
}},
})
if !errors.Is(err, channels.ErrSendFailed) {
t.Fatalf("SendMedia() error = %v, want ErrSendFailed", err)
}
if len(api.transportCalls) != 0 {
t.Fatalf("transportCalls = %d, want 0", len(api.transportCalls))
}
}
type fakeQQAPI struct {
transportResp []byte
transportErr error
groupErr error
c2cErr error
transportCalls []fakeTransportCall
groupMessages []dto.APIMessage
c2cMessages []dto.APIMessage
}
type fakeTransportCall struct {
method string
url string
body qqMediaUpload
}
func (f *fakeQQAPI) WS(
context.Context,
map[string]string,
string,
) (*dto.WebsocketAP, error) {
return nil, nil
}
func (f *fakeQQAPI) PostGroupMessage(
_ context.Context,
_ string,
msg dto.APIMessage,
_ ...options.Option,
) (*dto.Message, error) {
f.groupMessages = append(f.groupMessages, msg)
return &dto.Message{}, f.groupErr
}
func (f *fakeQQAPI) PostC2CMessage(
_ context.Context,
_ string,
msg dto.APIMessage,
_ ...options.Option,
) (*dto.Message, error) {
f.c2cMessages = append(f.c2cMessages, msg)
return &dto.Message{}, f.c2cErr
}
func (f *fakeQQAPI) Transport(_ context.Context, method, url string, body any) ([]byte, error) {
upload, ok := body.(*qqMediaUpload)
if !ok {
return nil, errors.New("unexpected transport body type")
}
f.transportCalls = append(f.transportCalls, fakeTransportCall{
method: method,
url: url,
body: *upload,
})
return f.transportResp, f.transportErr
}
func mustJSON(t *testing.T, v any) []byte {
t.Helper()
b, err := json.Marshal(v)
if err != nil {
t.Fatalf("json.Marshal() error = %v", err)
}
return b
}
func waitInboundMessage(t *testing.T, messageBus *bus.MessageBus) bus.InboundMessage {
t.Helper()
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
defer cancel()
for {
select {
case <-ctx.Done():
t.Fatal("timeout waiting for inbound message")
case inbound, ok := <-messageBus.InboundChan():
if !ok {
t.Fatal("expected inbound message")
}
return inbound
}
}
}
func writeTempFile(t *testing.T, dir, name string, content []byte) string {
t.Helper()
path := dir + "/" + name
if err := os.WriteFile(path, content, 0o600); err != nil {
t.Fatalf("WriteFile() error = %v", err)
}
return path
}

View file

@ -22,6 +22,10 @@ import (
"github.com/sipeed/picoclaw/pkg/utils"
)
// responseURLHTTPClient is a shared HTTP client for posting to WeCom response_url.
// Reusing it enables connection pooling across replies.
var responseURLHTTPClient = &http.Client{Timeout: 15 * time.Second}
// WeComAIBotChannel implements the Channel interface for WeCom AI Bot (企业微信智能机器人)
type WeComAIBotChannel struct {
*channels.BaseChannel
@ -134,13 +138,25 @@ type WeComAIBotEncryptedResponse struct {
Nonce string `json:"nonce"`
}
// NewWeComAIBotChannel creates a new WeCom AI Bot channel instance
// NewWeComAIBotChannel creates a WeCom AI Bot channel instance.
// If cfg.BotID and cfg.Secret are both set, it returns a WeComAIBotWSChannel
// using the WebSocket long-connection API.
// Otherwise it returns the webhook-mode WeComAIBotChannel (requires Token +
// EncodingAESKey).
func NewWeComAIBotChannel(
cfg config.WeComAIBotConfig,
messageBus *bus.MessageBus,
) (*WeComAIBotChannel, error) {
) (channels.Channel, error) {
// WebSocket long-connection mode takes priority when BotID + Secret are set.
if cfg.BotID != "" && cfg.Secret != "" {
logger.InfoC("wecom_aibot", "BotID and Secret provided, using WebSocket mode")
return newWeComAIBotWSChannel(cfg, messageBus)
}
// Webhook (short-connection) mode.
if cfg.Token == "" || cfg.EncodingAESKey == "" {
return nil, fmt.Errorf("token and encoding_aes_key are required for WeCom AI Bot")
return nil, fmt.Errorf(
"WeCom AI Bot requires either (bot_id + secret) for WebSocket mode " +
"or (token + encoding_aes_key) for webhook mode")
}
base := channels.NewBaseChannel("wecom_aibot", cfg, messageBus, cfg.AllowFrom,
@ -782,8 +798,7 @@ func (c *WeComAIBotChannel) sendViaResponseURL(responseURL, content string) erro
}
req.Header.Set("Content-Type", "application/json; charset=utf-8")
client := &http.Client{Timeout: 15 * time.Second}
resp, err := client.Do(req)
resp, err := responseURLHTTPClient.Do(req)
if err != nil {
return fmt.Errorf("post to response_url failed: %w: %w", channels.ErrTemporary, err)
}
@ -793,7 +808,8 @@ func (c *WeComAIBotChannel) sendViaResponseURL(responseURL, content string) erro
return nil
}
respBody, err := io.ReadAll(resp.Body)
const maxErrBody = 64 << 10 // 64 KB is more than enough for any error response
respBody, err := io.ReadAll(io.LimitReader(resp.Body, maxErrBody))
if err != nil {
return fmt.Errorf("reading response_url body: %w: %w", channels.ErrTemporary, err)
}
@ -895,17 +911,80 @@ func (c *WeComAIBotChannel) encryptMessage(plaintext, receiveid string) (string,
return base64.StdEncoding.EncodeToString(ciphertext), nil
}
// generateStreamID generates a random stream ID
func (c *WeComAIBotChannel) generateStreamID() string {
// func (c *WeComAIBotChannel) downloadAndDecryptImage(
// ctx context.Context,
// imageURL string,
// ) ([]byte, error) {
// // Download image
// req, err := http.NewRequestWithContext(ctx, http.MethodGet, imageURL, nil)
// if err != nil {
// return nil, fmt.Errorf("failed to create request: %w", err)
// }
// client := &http.Client{
// Timeout: 15 * time.Second,
// }
// resp, err := client.Do(req)
// if err != nil {
// return nil, fmt.Errorf("failed to download image: %w", err)
// }
// defer resp.Body.Close()
// if resp.StatusCode != http.StatusOK {
// return nil, fmt.Errorf("download failed with status: %d", resp.StatusCode)
// }
// // Limit image download to 20 MB to prevent memory exhaustion
// const maxImageSize = 20 << 20 // 20 MB
// encryptedData, err := io.ReadAll(io.LimitReader(resp.Body, maxImageSize+1))
// if err != nil {
// return nil, fmt.Errorf("failed to read image data: %w", err)
// }
// if len(encryptedData) > maxImageSize {
// return nil, fmt.Errorf("image too large (exceeds %d MB)", maxImageSize>>20)
// }
// logger.DebugCF("wecom_aibot", "Image downloaded", map[string]any{
// "size": len(encryptedData),
// })
// // Decode AES key
// aesKey, err := decodeWeComAESKey(c.config.EncodingAESKey)
// if err != nil {
// return nil, err
// }
// // Decrypt image (AES-CBC with IV = first 16 bytes of key, PKCS7 padding stripped)
// decryptedData, err := decryptAESCBC(aesKey, encryptedData)
// if err != nil {
// return nil, fmt.Errorf("failed to decrypt image: %w", err)
// }
// logger.DebugCF("wecom_aibot", "Image decrypted", map[string]any{
// "size": len(decryptedData),
// })
// return decryptedData, nil
// }
// generateRandomID generates a cryptographically random alphanumeric ID of
// length n. Used for stream IDs and WebSocket request IDs.
func generateRandomID(n int) string {
const letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
b := make([]byte, 10)
b := make([]byte, n)
for i := range b {
n, _ := rand.Int(rand.Reader, big.NewInt(int64(len(letters))))
b[i] = letters[n.Int64()]
num, _ := rand.Int(rand.Reader, big.NewInt(int64(len(letters))))
b[i] = letters[num.Int64()]
}
return string(b)
}
// generateStreamID generates a random 10-character stream ID (webhook mode).
func (c *WeComAIBotChannel) generateStreamID() string {
return generateRandomID(10)
}
// cleanupLoop periodically cleans up old streaming tasks
func (c *WeComAIBotChannel) cleanupLoop() {
ticker := time.NewTicker(5 * time.Minute)

View file

@ -3,12 +3,16 @@ package wecom
import (
"context"
"testing"
"time"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
)
func TestNewWeComAIBotChannel(t *testing.T) {
// ---- Webhook mode tests ----
func TestNewWeComAIBotChannel_WebhookMode(t *testing.T) {
t.Run("success with valid config", func(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
@ -22,14 +26,16 @@ func TestNewWeComAIBotChannel(t *testing.T) {
if err != nil {
t.Fatalf("Expected no error, got %v", err)
}
if ch == nil {
t.Fatal("Expected channel to be created")
}
if ch.Name() != "wecom_aibot" {
t.Errorf("Expected name 'wecom_aibot', got '%s'", ch.Name())
}
// Webhook mode must implement WebhookHandler.
if _, ok := ch.(channels.WebhookHandler); !ok {
t.Error("Webhook mode channel should implement WebhookHandler")
}
})
t.Run("error with missing token", func(t *testing.T) {
@ -37,10 +43,8 @@ func TestNewWeComAIBotChannel(t *testing.T) {
Enabled: true,
EncodingAESKey: "testkey1234567890123456789012345678901234567",
}
messageBus := bus.NewMessageBus()
_, err := NewWeComAIBotChannel(cfg, messageBus)
if err == nil {
t.Fatal("Expected error for missing token, got nil")
}
@ -51,17 +55,15 @@ func TestNewWeComAIBotChannel(t *testing.T) {
Enabled: true,
Token: "test_token",
}
messageBus := bus.NewMessageBus()
_, err := NewWeComAIBotChannel(cfg, messageBus)
if err == nil {
t.Fatal("Expected error for missing encoding key, got nil")
}
})
}
func TestWeComAIBotChannelStartStop(t *testing.T) {
func TestWeComAIBotWebhookChannelStartStop(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
Token: "test_token",
@ -76,22 +78,18 @@ func TestWeComAIBotChannelStartStop(t *testing.T) {
ctx := context.Background()
// Test Start
if err := ch.Start(ctx); err != nil {
t.Fatalf("Failed to start channel: %v", err)
}
if !ch.IsRunning() {
t.Error("Expected channel to be running")
t.Error("Expected channel to be running after Start")
}
// Test Stop
if err := ch.Stop(ctx); err != nil {
t.Fatalf("Failed to stop channel: %v", err)
}
if ch.IsRunning() {
t.Error("Expected channel to be stopped")
t.Error("Expected channel to be stopped after Stop")
}
}
@ -102,13 +100,16 @@ func TestWeComAIBotChannelWebhookPath(t *testing.T) {
Token: "test_token",
EncodingAESKey: "testkey1234567890123456789012345678901234567",
}
messageBus := bus.NewMessageBus()
ch, _ := NewWeComAIBotChannel(cfg, messageBus)
wh, ok := ch.(channels.WebhookHandler)
if !ok {
t.Fatal("Expected channel to implement WebhookHandler")
}
expectedPath := "/webhook/wecom-aibot"
if ch.WebhookPath() != expectedPath {
t.Errorf("Expected webhook path '%s', got '%s'", expectedPath, ch.WebhookPath())
if wh.WebhookPath() != expectedPath {
t.Errorf("Expected webhook path '%s', got '%s'", expectedPath, wh.WebhookPath())
}
})
@ -120,12 +121,15 @@ func TestWeComAIBotChannelWebhookPath(t *testing.T) {
EncodingAESKey: "testkey1234567890123456789012345678901234567",
WebhookPath: customPath,
}
messageBus := bus.NewMessageBus()
ch, _ := NewWeComAIBotChannel(cfg, messageBus)
if ch.WebhookPath() != customPath {
t.Errorf("Expected webhook path '%s', got '%s'", customPath, ch.WebhookPath())
wh, ok := ch.(channels.WebhookHandler)
if !ok {
t.Fatal("Expected channel to implement WebhookHandler")
}
if wh.WebhookPath() != customPath {
t.Errorf("Expected webhook path '%s', got '%s'", customPath, wh.WebhookPath())
}
})
}
@ -136,19 +140,19 @@ func TestGenerateStreamID(t *testing.T) {
Token: "test_token",
EncodingAESKey: "testkey1234567890123456789012345678901234567",
}
messageBus := bus.NewMessageBus()
ch, _ := NewWeComAIBotChannel(cfg, messageBus)
webhookCh, ok := ch.(*WeComAIBotChannel)
if !ok {
t.Fatal("Expected webhook mode channel")
}
// Generate multiple IDs and check they are unique
ids := make(map[string]bool)
for i := 0; i < 100; i++ {
id := ch.generateStreamID()
id := webhookCh.generateStreamID()
if len(id) != 10 {
t.Errorf("Expected stream ID length 10, got %d", len(id))
}
if ids[id] {
t.Errorf("Duplicate stream ID generated: %s", id)
}
@ -157,35 +161,33 @@ func TestGenerateStreamID(t *testing.T) {
}
func TestEncryptDecrypt(t *testing.T) {
// Use a valid 43-character base64 key (企业微信标准格式)
cfg := config.WeComAIBotConfig{
Enabled: true,
Token: "test_token",
EncodingAESKey: "abcdefghijklmnopqrstuvwxyz0123456789ABCDEFG", // 43 characters
}
messageBus := bus.NewMessageBus()
ch, _ := NewWeComAIBotChannel(cfg, messageBus)
webhookCh, ok := ch.(*WeComAIBotChannel)
if !ok {
t.Fatal("Expected webhook mode channel")
}
plaintext := "Hello, World!"
receiveid := ""
// Encrypt
encrypted, err := ch.encryptMessage(plaintext, receiveid)
encrypted, err := webhookCh.encryptMessage(plaintext, receiveid)
if err != nil {
t.Fatalf("Failed to encrypt message: %v", err)
}
if encrypted == "" {
t.Fatal("Encrypted message is empty")
}
// Decrypt
decrypted, err := decryptMessageWithVerify(encrypted, cfg.EncodingAESKey, receiveid)
if err != nil {
t.Fatalf("Failed to decrypt message: %v", err)
}
if decrypted != plaintext {
t.Errorf("Expected decrypted message '%s', got '%s'", plaintext, decrypted)
}
@ -198,13 +200,256 @@ func TestGenerateSignature(t *testing.T) {
encrypt := "encrypted_msg"
signature := computeSignature(token, timestamp, nonce, encrypt)
if signature == "" {
t.Error("Generated signature is empty")
}
// Verify signature using verifySignature function
if !verifySignature(token, signature, timestamp, nonce, encrypt) {
t.Error("Generated signature does not verify correctly")
}
}
// ---- WebSocket long-connection mode tests ----
func TestNewWeComAIBotChannel_WSMode(t *testing.T) {
t.Run("success with bot_id and secret", func(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
BotID: "test_bot_id",
Secret: "test_secret",
}
messageBus := bus.NewMessageBus()
ch, err := NewWeComAIBotChannel(cfg, messageBus)
if err != nil {
t.Fatalf("Expected no error, got %v", err)
}
if ch == nil {
t.Fatal("Expected channel to be created")
}
if ch.Name() != "wecom_aibot" {
t.Errorf("Expected name 'wecom_aibot', got '%s'", ch.Name())
}
// WebSocket mode must NOT implement WebhookHandler.
if _, ok := ch.(channels.WebhookHandler); ok {
t.Error("WebSocket mode channel should NOT implement WebhookHandler")
}
})
t.Run("ws mode takes priority over webhook fields", func(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
BotID: "test_bot_id",
Secret: "test_secret",
Token: "also_set",
EncodingAESKey: "testkey1234567890123456789012345678901234567",
}
messageBus := bus.NewMessageBus()
ch, err := NewWeComAIBotChannel(cfg, messageBus)
if err != nil {
t.Fatalf("Expected no error, got %v", err)
}
if _, ok := ch.(*WeComAIBotWSChannel); !ok {
t.Error("Expected WebSocket mode channel when both BotID+Secret and Token+Key are set")
}
})
t.Run("error with missing bot_id", func(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
Secret: "test_secret",
}
messageBus := bus.NewMessageBus()
_, err := NewWeComAIBotChannel(cfg, messageBus)
// Missing bot_id alone means neither WS mode nor webhook mode is fully configured.
if err == nil {
t.Fatal("Expected error for missing bot_id, got nil")
}
})
t.Run("error with missing secret", func(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
BotID: "test_bot_id",
}
messageBus := bus.NewMessageBus()
_, err := NewWeComAIBotChannel(cfg, messageBus)
if err == nil {
t.Fatal("Expected error for missing secret, got nil")
}
})
}
func TestWeComAIBotWSChannelStartStop(t *testing.T) {
cfg := config.WeComAIBotConfig{
Enabled: true,
BotID: "test_bot_id",
Secret: "test_secret",
}
messageBus := bus.NewMessageBus()
ch, err := NewWeComAIBotChannel(cfg, messageBus)
if err != nil {
t.Fatalf("Failed to create channel: %v", err)
}
ctx := context.Background()
// Start launches a background goroutine; it should not block or return an error.
if err := ch.Start(ctx); err != nil {
t.Fatalf("Failed to start channel: %v", err)
}
if !ch.IsRunning() {
t.Error("Expected channel to be running after Start")
}
// Stop should work regardless of whether the WebSocket actually connected.
if err := ch.Stop(ctx); err != nil {
t.Fatalf("Failed to stop channel: %v", err)
}
if ch.IsRunning() {
t.Error("Expected channel to be stopped after Stop")
}
}
func TestGenerateRandomID(t *testing.T) {
ids := make(map[string]bool)
for i := 0; i < 200; i++ {
id := generateRandomID(10)
if len(id) != 10 {
t.Errorf("Expected ID length 10, got %d", len(id))
}
if ids[id] {
t.Errorf("Duplicate ID generated: %s", id)
}
ids[id] = true
}
}
func TestWSGenerateID(t *testing.T) {
ids := make(map[string]bool)
for i := 0; i < 200; i++ {
id := wsGenerateID()
if len(id) != 10 {
t.Errorf("Expected ID length 10, got %d", len(id))
}
if ids[id] {
t.Errorf("Duplicate wsGenerateID result: %s", id)
}
ids[id] = true
}
}
// ---- Webhook streaming fallback tests ----
// makeWebhookChannel creates a started WeComAIBotChannel for testing.
func makeWebhookChannel(t *testing.T) *WeComAIBotChannel {
t.Helper()
cfg := config.WeComAIBotConfig{
Enabled: true,
Token: "test_token",
EncodingAESKey: "abcdefghijklmnopqrstuvwxyz0123456789ABCDEFG",
}
ch, err := NewWeComAIBotChannel(cfg, bus.NewMessageBus())
if err != nil {
t.Fatalf("create channel: %v", err)
}
wc := ch.(*WeComAIBotChannel)
wc.ctx, wc.cancel = context.WithCancel(context.Background())
return wc
}
// makeStreamTask creates and registers a streamTask for testing.
func makeStreamTask(t *testing.T, ch *WeComAIBotChannel, streamID, chatID string, deadline time.Time) *streamTask {
t.Helper()
task := &streamTask{
StreamID: streamID,
ChatID: chatID,
Deadline: deadline,
answerCh: make(chan string, 1),
}
task.ctx, task.cancel = context.WithCancel(ch.ctx)
ch.taskMu.Lock()
ch.streamTasks[streamID] = task
ch.chatTasks[chatID] = append(ch.chatTasks[chatID], task)
ch.taskMu.Unlock()
return task
}
// TestGetStreamResponse_ImmediateAnswer verifies that when the agent has already
// placed its answer in answerCh, getStreamResponse returns a finish=true response
// and fully removes the task.
func TestGetStreamResponse_ImmediateAnswer(t *testing.T) {
ch := makeWebhookChannel(t)
defer ch.cancel()
task := makeStreamTask(t, ch, "stream-1", "chat-1", time.Now().Add(30*time.Second))
task.answerCh <- "hello from agent"
result := ch.getStreamResponse(task, "ts123", "nonce123")
if result == "" {
t.Fatal("expected non-empty encrypted response")
}
ch.taskMu.RLock()
_, exists := ch.streamTasks["stream-1"]
ch.taskMu.RUnlock()
if exists {
t.Error("task should have been removed from streamTasks after normal finish")
}
if !task.Finished {
t.Error("task.Finished should be true after normal finish")
}
}
// TestGetStreamResponse_DeadlinePassed verifies that when the stream deadline has
// elapsed (no agent reply yet), getStreamResponse closes the stream but keeps the
// task alive so the response_url fallback can still deliver the answer.
func TestGetStreamResponse_DeadlinePassed(t *testing.T) {
ch := makeWebhookChannel(t)
defer ch.cancel()
task := makeStreamTask(t, ch, "stream-2", "chat-2", time.Now().Add(-time.Millisecond))
result := ch.getStreamResponse(task, "ts456", "nonce456")
if result == "" {
t.Fatal("expected non-empty encrypted response")
}
ch.taskMu.RLock()
_, stillStreaming := ch.streamTasks["stream-2"]
ch.taskMu.RUnlock()
if stillStreaming {
t.Error("task should have been removed from streamTasks after deadline")
}
if !task.StreamClosed {
t.Error("task.StreamClosed should be true after deadline")
}
if task.Finished {
t.Error("task.Finished must remain false: agent reply still expected via response_url")
}
}
// TestGetStreamResponse_StillPending verifies that when neither the agent has
// replied nor the deadline has passed, getStreamResponse returns without altering
// task state (client should poll again).
func TestGetStreamResponse_StillPending(t *testing.T) {
ch := makeWebhookChannel(t)
defer ch.cancel()
task := makeStreamTask(t, ch, "stream-3", "chat-3", time.Now().Add(30*time.Second))
result := ch.getStreamResponse(task, "ts789", "nonce789")
if result == "" {
t.Fatal("expected non-empty encrypted response")
}
ch.taskMu.RLock()
_, exists := ch.streamTasks["stream-3"]
ch.taskMu.RUnlock()
if !exists {
t.Error("pending task should still be in streamTasks")
}
if task.Finished || task.StreamClosed {
t.Error("pending task should not be finished or stream-closed")
}
// Cleanup.
ch.removeTask(task)
}

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,295 @@
package wecom
import (
"bytes"
"context"
"net/http"
"net/http/httptest"
"os"
"strings"
"testing"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/channels"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/media"
)
// newTestWSChannel creates a WeComAIBotWSChannel ready for unit testing.
func newTestWSChannel(t *testing.T) *WeComAIBotWSChannel {
t.Helper()
cfg := config.WeComAIBotConfig{
Enabled: true,
BotID: "test_bot_id",
Secret: "test_secret",
}
ch, err := newWeComAIBotWSChannel(cfg, bus.NewMessageBus())
if err != nil {
t.Fatalf("create WS channel: %v", err)
}
return ch
}
// TestStoreWSMedia_NilStore verifies that storeWSMedia returns an error when no
// MediaStore has been injected.
func TestStoreWSMedia_NilStore(t *testing.T) {
ch := newTestWSChannel(t)
_, err := ch.storeWSMedia(context.Background(), "chat1", "msg1", "http://any", "", ".jpg")
if err == nil {
t.Fatal("expected error when no MediaStore is set")
}
}
// TestStoreWSMedia_HTTPError verifies that storeWSMedia propagates HTTP errors
// from the media server.
func TestStoreWSMedia_HTTPError(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
http.Error(w, "not found", http.StatusNotFound)
}))
defer srv.Close()
ch := newTestWSChannel(t)
ch.SetMediaStore(media.NewFileMediaStore())
_, err := ch.storeWSMedia(context.Background(), "chat1", "msg1", srv.URL, "", ".jpg")
if err == nil {
t.Fatal("expected error for HTTP 404")
}
}
// TestStoreWSMedia_ServerUnavailable verifies that storeWSMedia returns a clear
// error when the media server cannot be reached.
func TestStoreWSMedia_ServerUnavailable(t *testing.T) {
ch := newTestWSChannel(t)
ch.SetMediaStore(media.NewFileMediaStore())
// Port 1 is reserved and will refuse the connection immediately.
_, err := ch.storeWSMedia(context.Background(), "chat1", "msg1", "http://127.0.0.1:1", "", ".jpg")
if err == nil {
t.Fatal("expected error for unreachable server")
}
}
// TestStoreWSMedia_Success_NoAES verifies the happy path: the media is downloaded,
// a media ref is returned, and the file persists and is readable via Resolve until
// ReleaseAll is called. The server returns no Content-Type, so the defaultExt is used.
func TestStoreWSMedia_Success_NoAES(t *testing.T) {
imageData := bytes.Repeat([]byte("x"), 256)
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
_, _ = w.Write(imageData)
}))
defer srv.Close()
ch := newTestWSChannel(t)
store := media.NewFileMediaStore()
ch.SetMediaStore(store)
ref, err := ch.storeWSMedia(context.Background(), "chat1", "msg1", srv.URL, "", ".jpg")
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if ref == "" {
t.Fatal("expected non-empty ref")
}
// File must be accessible after storeWSMedia returns (no premature deletion).
path, err := store.Resolve(ref)
if err != nil {
t.Fatalf("ref should resolve: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("file should exist at %s: %v", path, err)
}
if !bytes.Equal(got, imageData) {
t.Errorf("content mismatch: got len=%d, want len=%d", len(got), len(imageData))
}
// ReleaseAll must delete the file (store owns lifecycle).
scope := channels.BuildMediaScope("wecom_aibot", "chat1", "msg1")
if err := store.ReleaseAll(scope); err != nil {
t.Fatalf("ReleaseAll failed: %v", err)
}
if _, err := os.Stat(path); !os.IsNotExist(err) {
t.Errorf("file should have been deleted by ReleaseAll, stat err: %v", err)
}
}
// TestStoreWSMedia_MultipleMessages verifies that concurrent media messages with
// different msgIDs do not collide and each resolve to distinct files.
func TestStoreWSMedia_MultipleMessages(t *testing.T) {
imageA := bytes.Repeat([]byte("a"), 64)
imageB := bytes.Repeat([]byte("b"), 64)
srvA := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
_, _ = w.Write(imageA)
}))
defer srvA.Close()
srvB := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
_, _ = w.Write(imageB)
}))
defer srvB.Close()
ch := newTestWSChannel(t)
store := media.NewFileMediaStore()
ch.SetMediaStore(store)
refA, err := ch.storeWSMedia(context.Background(), "chat1", "msgA", srvA.URL, "", ".jpg")
if err != nil {
t.Fatalf("storeWSMedia A: %v", err)
}
refB, err := ch.storeWSMedia(context.Background(), "chat1", "msgB", srvB.URL, "", ".jpg")
if err != nil {
t.Fatalf("storeWSMedia B: %v", err)
}
if refA == refB {
t.Fatal("distinct messages must produce distinct refs")
}
pathA, _ := store.Resolve(refA)
pathB, _ := store.Resolve(refB)
if pathA == pathB {
t.Fatal("distinct messages must be stored at distinct paths")
}
gotA, _ := os.ReadFile(pathA)
gotB, _ := os.ReadFile(pathB)
if !bytes.Equal(gotA, imageA) {
t.Errorf("content mismatch for message A")
}
if !bytes.Equal(gotB, imageB) {
t.Errorf("content mismatch for message B")
}
}
// TestStoreWSMedia_ContentTypeExt verifies that the file extension is inferred
// from the HTTP Content-Type header and the defaultExt fallback is used when the
// type is absent or unrecognized.
func TestStoreWSMedia_ContentTypeExt(t *testing.T) {
tests := []struct {
contentType string
wantExt string
}{
{"image/jpeg", ".jpg"},
{"image/png", ".png"},
{"video/mp4", ".mp4"},
{"application/pdf", ".pdf"},
{"application/zip", ".zip"},
// With parameters stripped.
{"video/mp4; codecs=avc1", ".mp4"},
// Unknown type → falls back to defaultExt.
{"", ""},
{"application/octet-stream", ""},
}
for _, tc := range tests {
got := wsMediaExtFromContentType(tc.contentType)
if got != tc.wantExt {
t.Errorf("wsMediaExtFromContentType(%q) = %q, want %q", tc.contentType, got, tc.wantExt)
}
}
// End-to-end: server returns Content-Type: video/mp4, defaultExt is .bin.
// The stored file should carry the .mp4 extension, not .bin.
payload := bytes.Repeat([]byte("v"), 128)
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", "video/mp4")
w.WriteHeader(http.StatusOK)
_, _ = w.Write(payload)
}))
defer srv.Close()
ch := newTestWSChannel(t)
store := media.NewFileMediaStore()
ch.SetMediaStore(store)
ref, err := ch.storeWSMedia(context.Background(), "chat1", "vid1", srv.URL, "", ".bin")
if err != nil {
t.Fatalf("storeWSMedia: %v", err)
}
path, err := store.Resolve(ref)
if err != nil {
t.Fatalf("resolve: %v", err)
}
if ext := path[len(path)-4:]; ext != ".mp4" {
t.Errorf("expected .mp4 extension from Content-Type, got %q", ext)
}
}
// TestSplitWSContent verifies byte-aware splitting of stream content.
func TestSplitWSContent(t *testing.T) {
t.Run("short content is not split", func(t *testing.T) {
chunks := splitWSContent("hello", 20480)
if len(chunks) != 1 || chunks[0] != "hello" {
t.Fatalf("unexpected chunks: %v", chunks)
}
})
t.Run("ASCII content split at byte boundary", func(t *testing.T) {
// Build a string just over the limit.
content := strings.Repeat("a", 20481)
chunks := splitWSContent(content, 20480)
if len(chunks) < 2 {
t.Fatalf("expected >= 2 chunks, got %d", len(chunks))
}
for i, c := range chunks {
if len(c) > 20480 {
t.Errorf("chunk %d has %d bytes, want <= 20480", i, len(c))
}
}
// Reassembled content must equal the original (possibly without leading
// whitespace that splitWSContent trims between chunks).
joined := strings.Join(chunks, "")
if len(joined) < len(content)-len(chunks) {
t.Errorf("joined length %d too short (original %d)", len(joined), len(content))
}
})
t.Run("CJK content split within byte limit", func(t *testing.T) {
// Each CJK rune is 3 bytes in UTF-8.
// 7000 CJK chars = 21000 bytes, which exceeds 20480.
content := strings.Repeat("\u4e2d", 7000)
chunks := splitWSContent(content, 20480)
if len(chunks) < 2 {
t.Fatalf("expected >= 2 chunks for 21000-byte CJK content, got %d", len(chunks))
}
for i, c := range chunks {
if len(c) > 20480 {
t.Errorf("chunk %d has %d bytes, want <= 20480", i, len(c))
}
// Every chunk must be valid UTF-8.
if !strings.ContainsRune(c, '\u4e2d') && len(c) > 0 {
// quick plausibility check — content was pure CJK
}
}
})
}
// TestSplitAtByteBoundary verifies the last-resort byte-boundary splitter.
func TestSplitAtByteBoundary(t *testing.T) {
t.Run("ASCII fits in one chunk", func(t *testing.T) {
parts := splitAtByteBoundary("hello world", 100)
if len(parts) != 1 {
t.Fatalf("expected 1 part, got %d", len(parts))
}
})
t.Run("splits at byte boundary, never mid-rune", func(t *testing.T) {
// 10 CJK characters = 30 bytes; split at 20 bytes.
s := strings.Repeat("\u6587", 10) // 10 × 3 bytes = 30 bytes
parts := splitAtByteBoundary(s, 20)
for i, p := range parts {
if len(p) > 20 {
t.Errorf("part %d has %d bytes, want <= 20", i, len(p))
}
// Must be valid UTF-8 (no torn multi-byte sequences).
for j, r := range p {
if r == '\uFFFD' {
t.Errorf("part %d has replacement rune at position %d: torn UTF-8", i, j)
}
}
}
})
}

View file

@ -219,23 +219,32 @@ type RoutingConfig struct {
Threshold float64 `json:"threshold"` // complexity score in [0,1]; score >= threshold → primary model
}
// ToolFeedbackConfig controls whether tool execution details are sent to the
// chat channel as real-time feedback messages. When enabled, every tool call
// produces a short notification with the tool name and its parameters.
type ToolFeedbackConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_AGENTS_DEFAULTS_TOOL_FEEDBACK_ENABLED"`
MaxArgsLength int `json:"max_args_length" env:"PICOCLAW_AGENTS_DEFAULTS_TOOL_FEEDBACK_MAX_ARGS_LENGTH"`
}
type AgentDefaults struct {
Workspace string `json:"workspace" env:"PICOCLAW_AGENTS_DEFAULTS_WORKSPACE"`
RestrictToWorkspace bool `json:"restrict_to_workspace" env:"PICOCLAW_AGENTS_DEFAULTS_RESTRICT_TO_WORKSPACE"`
AllowReadOutsideWorkspace bool `json:"allow_read_outside_workspace" env:"PICOCLAW_AGENTS_DEFAULTS_ALLOW_READ_OUTSIDE_WORKSPACE"`
Provider string `json:"provider" env:"PICOCLAW_AGENTS_DEFAULTS_PROVIDER"`
ModelName string `json:"model_name" env:"PICOCLAW_AGENTS_DEFAULTS_MODEL_NAME"`
Model string `json:"model,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_MODEL"` // Deprecated: use model_name instead
ModelFallbacks []string `json:"model_fallbacks,omitempty"`
ImageModel string `json:"image_model,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_IMAGE_MODEL"`
ImageModelFallbacks []string `json:"image_model_fallbacks,omitempty"`
MaxTokens int `json:"max_tokens" env:"PICOCLAW_AGENTS_DEFAULTS_MAX_TOKENS"`
Temperature *float64 `json:"temperature,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_TEMPERATURE"`
MaxToolIterations int `json:"max_tool_iterations" env:"PICOCLAW_AGENTS_DEFAULTS_MAX_TOOL_ITERATIONS"`
SummarizeMessageThreshold int `json:"summarize_message_threshold" env:"PICOCLAW_AGENTS_DEFAULTS_SUMMARIZE_MESSAGE_THRESHOLD"`
SummarizeTokenPercent int `json:"summarize_token_percent" env:"PICOCLAW_AGENTS_DEFAULTS_SUMMARIZE_TOKEN_PERCENT"`
MaxMediaSize int `json:"max_media_size,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_MAX_MEDIA_SIZE"`
Routing *RoutingConfig `json:"routing,omitempty"`
Workspace string `json:"workspace" env:"PICOCLAW_AGENTS_DEFAULTS_WORKSPACE"`
RestrictToWorkspace bool `json:"restrict_to_workspace" env:"PICOCLAW_AGENTS_DEFAULTS_RESTRICT_TO_WORKSPACE"`
AllowReadOutsideWorkspace bool `json:"allow_read_outside_workspace" env:"PICOCLAW_AGENTS_DEFAULTS_ALLOW_READ_OUTSIDE_WORKSPACE"`
Provider string `json:"provider" env:"PICOCLAW_AGENTS_DEFAULTS_PROVIDER"`
ModelName string `json:"model_name" env:"PICOCLAW_AGENTS_DEFAULTS_MODEL_NAME"`
Model string `json:"model,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_MODEL"` // Deprecated: use model_name instead
ModelFallbacks []string `json:"model_fallbacks,omitempty"`
ImageModel string `json:"image_model,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_IMAGE_MODEL"`
ImageModelFallbacks []string `json:"image_model_fallbacks,omitempty"`
MaxTokens int `json:"max_tokens" env:"PICOCLAW_AGENTS_DEFAULTS_MAX_TOKENS"`
Temperature *float64 `json:"temperature,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_TEMPERATURE"`
MaxToolIterations int `json:"max_tool_iterations" env:"PICOCLAW_AGENTS_DEFAULTS_MAX_TOOL_ITERATIONS"`
SummarizeMessageThreshold int `json:"summarize_message_threshold" env:"PICOCLAW_AGENTS_DEFAULTS_SUMMARIZE_MESSAGE_THRESHOLD"`
SummarizeTokenPercent int `json:"summarize_token_percent" env:"PICOCLAW_AGENTS_DEFAULTS_SUMMARIZE_TOKEN_PERCENT"`
MaxMediaSize int `json:"max_media_size,omitempty" env:"PICOCLAW_AGENTS_DEFAULTS_MAX_MEDIA_SIZE"`
Routing *RoutingConfig `json:"routing,omitempty"`
ToolFeedback ToolFeedbackConfig `json:"tool_feedback,omitempty"`
}
const DefaultMaxMediaSize = 20 * 1024 * 1024 // 20 MB
@ -247,6 +256,19 @@ func (d *AgentDefaults) GetMaxMediaSize() int {
return DefaultMaxMediaSize
}
// GetToolFeedbackMaxArgsLength returns the max args preview length for tool feedback messages.
func (d *AgentDefaults) GetToolFeedbackMaxArgsLength() int {
if d.ToolFeedback.MaxArgsLength > 0 {
return d.ToolFeedback.MaxArgsLength
}
return 300
}
// IsToolFeedbackEnabled returns true when tool feedback messages should be sent to the chat.
func (d *AgentDefaults) IsToolFeedbackEnabled() bool {
return d.ToolFeedback.Enabled
}
// GetModelName returns the effective model name for the agent defaults.
// It prefers the new "model_name" field but falls back to "model" for backward compatibility.
func (d *AgentDefaults) GetModelName() string {
@ -349,14 +371,15 @@ type MaixCamConfig struct {
}
type QQConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_CHANNELS_QQ_ENABLED"`
AppID string `json:"app_id" env:"PICOCLAW_CHANNELS_QQ_APP_ID"`
AppSecret string `json:"app_secret" env:"PICOCLAW_CHANNELS_QQ_APP_SECRET"`
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_QQ_ALLOW_FROM"`
GroupTrigger GroupTriggerConfig `json:"group_trigger,omitempty"`
MaxMessageLength int `json:"max_message_length" env:"PICOCLAW_CHANNELS_QQ_MAX_MESSAGE_LENGTH"`
SendMarkdown bool `json:"send_markdown" env:"PICOCLAW_CHANNELS_QQ_SEND_MARKDOWN"`
ReasoningChannelID string `json:"reasoning_channel_id" env:"PICOCLAW_CHANNELS_QQ_REASONING_CHANNEL_ID"`
Enabled bool `json:"enabled" env:"PICOCLAW_CHANNELS_QQ_ENABLED"`
AppID string `json:"app_id" env:"PICOCLAW_CHANNELS_QQ_APP_ID"`
AppSecret string `json:"app_secret" env:"PICOCLAW_CHANNELS_QQ_APP_SECRET"`
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_QQ_ALLOW_FROM"`
GroupTrigger GroupTriggerConfig `json:"group_trigger,omitempty"`
MaxMessageLength int `json:"max_message_length" env:"PICOCLAW_CHANNELS_QQ_MAX_MESSAGE_LENGTH"`
MaxBase64FileSizeMiB int64 `json:"max_base64_file_size_mib" env:"PICOCLAW_CHANNELS_QQ_MAX_BASE64_FILE_SIZE_MIB"`
SendMarkdown bool `json:"send_markdown" env:"PICOCLAW_CHANNELS_QQ_SEND_MARKDOWN"`
ReasoningChannelID string `json:"reasoning_channel_id" env:"PICOCLAW_CHANNELS_QQ_REASONING_CHANNEL_ID"`
}
type DingTalkConfig struct {
@ -451,15 +474,17 @@ type WeComAppConfig struct {
}
type WeComAIBotConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ENABLED"`
Token string `json:"token" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_TOKEN"`
EncodingAESKey string `json:"encoding_aes_key" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ENCODING_AES_KEY"`
WebhookPath string `json:"webhook_path" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_WEBHOOK_PATH"`
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ALLOW_FROM"`
ReplyTimeout int `json:"reply_timeout" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_REPLY_TIMEOUT"`
MaxSteps int `json:"max_steps" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_MAX_STEPS"` // Maximum streaming steps
WelcomeMessage string `json:"welcome_message" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_WELCOME_MESSAGE"` // Sent on enter_chat event; empty = no welcome
ReasoningChannelID string `json:"reasoning_channel_id" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_REASONING_CHANNEL_ID"`
Enabled bool `json:"enabled" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ENABLED"`
BotID string `json:"bot_id,omitempty" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_BOT_ID"`
Secret string `json:"secret,omitempty" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_SECRET"`
Token string `json:"token,omitempty" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_TOKEN"`
EncodingAESKey string `json:"encoding_aes_key,omitempty" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ENCODING_AES_KEY"`
WebhookPath string `json:"webhook_path,omitempty" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_WEBHOOK_PATH"`
AllowFrom FlexibleStringSlice `json:"allow_from" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ALLOW_FROM"`
ReplyTimeout int `json:"reply_timeout" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_REPLY_TIMEOUT"`
MaxSteps int `json:"max_steps" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_MAX_STEPS"`
WelcomeMessage string `json:"welcome_message" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_WELCOME_MESSAGE"`
ReasoningChannelID string `json:"reasoning_channel_id" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_REASONING_CHANNEL_ID"`
}
type PicoConfig struct {
@ -805,6 +830,10 @@ type ClawHubRegistryConfig struct {
type MCPServerConfig struct {
// Enabled indicates whether this MCP server is active
Enabled bool `json:"enabled"`
// Deferred controls whether this server's tools are registered as hidden (deferred/discovery mode).
// When nil, the global Discovery.Enabled setting applies.
// When explicitly set to true or false, it overrides the global setting for this server only.
Deferred *bool `json:"deferred,omitempty"`
// Command is the executable to run (e.g., "npx", "python", "/path/to/server")
Command string `json:"command"`
// Args are the arguments to pass to the command
@ -887,6 +916,15 @@ func LoadConfig(path string) (*Config, error) {
cfg.ModelList = ConvertProvidersToModelList(cfg)
}
// Inherit credentials from providers to model_list entries (#1635).
// When both providers and model_list are present, model_list entries
// whose api_key/api_base are empty will inherit from the matching
// provider (matched by protocol prefix). Explicit model_list values
// always take precedence.
if cfg.HasProvidersConfig() {
InheritProviderCredentials(cfg.ModelList, cfg.Providers)
}
// Validate model_list for uniqueness and required fields
if err := cfg.ValidateModelList(); err != nil {
return nil, err

View file

@ -35,6 +35,10 @@ func DefaultConfig() *Config {
MaxToolIterations: 50,
SummarizeMessageThreshold: 20,
SummarizeTokenPercent: 75,
ToolFeedback: ToolFeedbackConfig{
Enabled: true,
MaxArgsLength: 300,
},
},
},
Bindings: []AgentBinding{},
@ -81,11 +85,12 @@ func DefaultConfig() *Config {
AllowFrom: FlexibleStringSlice{},
},
QQ: QQConfig{
Enabled: false,
AppID: "",
AppSecret: "",
AllowFrom: FlexibleStringSlice{},
MaxMessageLength: 2000,
Enabled: false,
AppID: "",
AppSecret: "",
AllowFrom: FlexibleStringSlice{},
MaxMessageLength: 2000,
MaxBase64FileSizeMiB: 0,
},
DingTalk: DingTalkConfig{
Enabled: false,

View file

@ -468,3 +468,84 @@ func ConvertProvidersToModelList(cfg *Config) []ModelConfig {
return result
}
// protocolProviderMapping maps a model protocol prefix (the part before "/" in
// the Model field) to a function that extracts the corresponding ProviderConfig
// from the legacy ProvidersConfig. Used by InheritProviderCredentials.
var protocolProviderMapping = map[string]func(p ProvidersConfig) ProviderConfig{
"openai": func(p ProvidersConfig) ProviderConfig { return p.OpenAI.ProviderConfig },
"anthropic": func(p ProvidersConfig) ProviderConfig { return p.Anthropic },
"litellm": func(p ProvidersConfig) ProviderConfig { return p.LiteLLM },
"openrouter": func(p ProvidersConfig) ProviderConfig { return p.OpenRouter },
"groq": func(p ProvidersConfig) ProviderConfig { return p.Groq },
"zhipu": func(p ProvidersConfig) ProviderConfig { return p.Zhipu },
"vllm": func(p ProvidersConfig) ProviderConfig { return p.VLLM },
"gemini": func(p ProvidersConfig) ProviderConfig { return p.Gemini },
"nvidia": func(p ProvidersConfig) ProviderConfig { return p.Nvidia },
"ollama": func(p ProvidersConfig) ProviderConfig { return p.Ollama },
"moonshot": func(p ProvidersConfig) ProviderConfig { return p.Moonshot },
"shengsuanyun": func(p ProvidersConfig) ProviderConfig { return p.ShengSuanYun },
"deepseek": func(p ProvidersConfig) ProviderConfig { return p.DeepSeek },
"cerebras": func(p ProvidersConfig) ProviderConfig { return p.Cerebras },
"vivgrid": func(p ProvidersConfig) ProviderConfig { return p.Vivgrid },
"volcengine": func(p ProvidersConfig) ProviderConfig { return p.VolcEngine },
"github-copilot": func(p ProvidersConfig) ProviderConfig { return p.GitHubCopilot },
"antigravity": func(p ProvidersConfig) ProviderConfig { return p.Antigravity },
"qwen": func(p ProvidersConfig) ProviderConfig { return p.Qwen },
"mistral": func(p ProvidersConfig) ProviderConfig { return p.Mistral },
"avian": func(p ProvidersConfig) ProviderConfig { return p.Avian },
"minimax": func(p ProvidersConfig) ProviderConfig { return p.Minimax },
"longcat": func(p ProvidersConfig) ProviderConfig { return p.LongCat },
"modelscope": func(p ProvidersConfig) ProviderConfig { return p.ModelScope },
"novita": func(p ProvidersConfig) ProviderConfig { return p.Novita },
}
// InheritProviderCredentials fills in missing api_key, api_base, proxy, and
// request_timeout on model_list entries from the matching legacy providers
// configuration. The match is determined by the protocol prefix in the Model
// field (e.g. "deepseek/deepseek-chat" matches providers.deepseek).
//
// Only empty fields are filled — any value explicitly set on a model_list entry
// takes precedence. This function modifies the slice in place.
//
// This bridges the gap described in issue #1635: users who configure
// credentials once in the providers section expect model_list entries using
// the same protocol to "just work" without duplicating credentials.
func InheritProviderCredentials(models []ModelConfig, providers ProvidersConfig) {
if providers.IsEmpty() {
return
}
for i := range models {
m := &models[i]
// Extract protocol prefix from Model field
protocol := ""
if idx := strings.Index(m.Model, "/"); idx > 0 {
protocol = strings.ToLower(m.Model[:idx])
}
if protocol == "" {
continue
}
getProvider, ok := protocolProviderMapping[protocol]
if !ok {
continue
}
pc := getProvider(providers)
// Only fill empty fields — explicit model_list values win
if m.APIKey == "" && pc.APIKey != "" {
m.APIKey = pc.APIKey
}
if m.APIBase == "" && pc.APIBase != "" {
m.APIBase = pc.APIBase
}
if m.Proxy == "" && pc.Proxy != "" {
m.Proxy = pc.Proxy
}
if m.RequestTimeout == 0 && pc.RequestTimeout != 0 {
m.RequestTimeout = pc.RequestTimeout
}
}
}

View file

@ -613,3 +613,143 @@ func TestConvertProvidersToModelList_LegacyModelWithProtocolPrefix(t *testing.T)
t.Errorf("Model = %q, want %q (should not duplicate prefix)", result[0].Model, "openrouter/auto")
}
}
// ---------- InheritProviderCredentials tests ----------
func TestInheritProviderCredentials_FillsMissingAPIKey(t *testing.T) {
models := []ModelConfig{
{ModelName: "my-deepseek", Model: "deepseek/deepseek-chat"},
}
providers := ProvidersConfig{
DeepSeek: ProviderConfig{
APIKey: "sk-deepseek-from-providers",
APIBase: "https://api.deepseek.com/v1",
},
}
InheritProviderCredentials(models, providers)
if models[0].APIKey != "sk-deepseek-from-providers" {
t.Errorf("APIKey = %q, want %q", models[0].APIKey, "sk-deepseek-from-providers")
}
if models[0].APIBase != "https://api.deepseek.com/v1" {
t.Errorf("APIBase = %q, want %q", models[0].APIBase, "https://api.deepseek.com/v1")
}
}
func TestInheritProviderCredentials_ExplicitValuesTakePrecedence(t *testing.T) {
models := []ModelConfig{
{
ModelName: "my-openai",
Model: "openai/gpt-5.4",
APIKey: "sk-explicit-model-key",
APIBase: "https://my-custom-endpoint.com/v1",
},
}
providers := ProvidersConfig{
OpenAI: OpenAIProviderConfig{
ProviderConfig: ProviderConfig{
APIKey: "sk-provider-key",
APIBase: "https://api.openai.com/v1",
},
},
}
InheritProviderCredentials(models, providers)
if models[0].APIKey != "sk-explicit-model-key" {
t.Errorf("APIKey = %q, want %q (explicit should win)", models[0].APIKey, "sk-explicit-model-key")
}
if models[0].APIBase != "https://my-custom-endpoint.com/v1" {
t.Errorf("APIBase = %q, want %q (explicit should win)", models[0].APIBase, "https://my-custom-endpoint.com/v1")
}
}
func TestInheritProviderCredentials_MultipleModels(t *testing.T) {
models := []ModelConfig{
{ModelName: "groq-llama", Model: "groq/llama-3.1-70b"},
{ModelName: "zhipu-glm", Model: "zhipu/glm-4"},
{ModelName: "custom-openai", Model: "openai/gpt-5.4", APIKey: "sk-already-set"},
}
providers := ProvidersConfig{
Groq: ProviderConfig{APIKey: "gsk-groq-key", Proxy: "http://proxy:8080"},
Zhipu: ProviderConfig{APIKey: "zhipu-key-123", APIBase: "https://zhipu.example.com"},
OpenAI: OpenAIProviderConfig{
ProviderConfig: ProviderConfig{APIKey: "sk-should-not-override"},
},
}
InheritProviderCredentials(models, providers)
// groq model should inherit
if models[0].APIKey != "gsk-groq-key" {
t.Errorf("groq APIKey = %q, want %q", models[0].APIKey, "gsk-groq-key")
}
if models[0].Proxy != "http://proxy:8080" {
t.Errorf("groq Proxy = %q, want %q", models[0].Proxy, "http://proxy:8080")
}
// zhipu model should inherit
if models[1].APIKey != "zhipu-key-123" {
t.Errorf("zhipu APIKey = %q, want %q", models[1].APIKey, "zhipu-key-123")
}
if models[1].APIBase != "https://zhipu.example.com" {
t.Errorf("zhipu APIBase = %q, want %q", models[1].APIBase, "https://zhipu.example.com")
}
// openai model already has key — should NOT be overridden
if models[2].APIKey != "sk-already-set" {
t.Errorf("openai APIKey = %q, want %q (should not be overridden)", models[2].APIKey, "sk-already-set")
}
}
func TestInheritProviderCredentials_NoMatchingProvider(t *testing.T) {
models := []ModelConfig{
{ModelName: "my-model", Model: "novelai/some-model"},
}
providers := ProvidersConfig{
DeepSeek: ProviderConfig{APIKey: "sk-deepseek"},
}
InheritProviderCredentials(models, providers)
// No matching provider for "novelai" protocol — should stay empty
if models[0].APIKey != "" {
t.Errorf("APIKey = %q, want empty (no matching provider)", models[0].APIKey)
}
}
func TestInheritProviderCredentials_EmptyProviders(t *testing.T) {
models := []ModelConfig{
{ModelName: "my-model", Model: "openai/gpt-5.4"},
}
providers := ProvidersConfig{} // all empty
InheritProviderCredentials(models, providers)
// Empty providers — nothing to inherit
if models[0].APIKey != "" {
t.Errorf("APIKey = %q, want empty", models[0].APIKey)
}
}
func TestInheritProviderCredentials_InheritsRequestTimeout(t *testing.T) {
models := []ModelConfig{
{ModelName: "my-ollama", Model: "ollama/llama3.2:3b"},
}
providers := ProvidersConfig{
Ollama: ProviderConfig{
APIBase: "http://localhost:11434",
RequestTimeout: 120,
},
}
InheritProviderCredentials(models, providers)
if models[0].APIBase != "http://localhost:11434" {
t.Errorf("APIBase = %q, want %q", models[0].APIBase, "http://localhost:11434")
}
if models[0].RequestTimeout != 120 {
t.Errorf("RequestTimeout = %d, want 120", models[0].RequestTimeout)
}
}

View file

@ -324,11 +324,12 @@ func setupAndStartServices(
return runningServices, nil
}
func stopAndCleanupServices(runningServices *services, shutdownTimeout time.Duration) {
func stopAndCleanupServices(runningServices *services, shutdownTimeout time.Duration, isReload bool) {
shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), shutdownTimeout)
defer shutdownCancel()
if runningServices.ChannelManager != nil {
// reload should not stop channel manager
if !isReload && runningServices.ChannelManager != nil {
runningServices.ChannelManager.StopAll(shutdownCtx)
}
if runningServices.DeviceService != nil {
@ -357,7 +358,7 @@ func shutdownGateway(
cp.Close()
}
stopAndCleanupServices(runningServices, gracefulShutdownTimeout)
stopAndCleanupServices(runningServices, gracefulShutdownTimeout, false)
agentLoop.Stop()
agentLoop.Close()
@ -384,7 +385,7 @@ func handleConfigReload(
logger.Infof(" New model is '%s', recreating provider...", newModel)
logger.Info(" Stopping all services...")
stopAndCleanupServices(runningServices, serviceShutdownTimeout)
stopAndCleanupServices(runningServices, serviceShutdownTimeout, true)
newProvider, newModelID, err := createStartupProvider(newCfg, allowEmptyStartup)
if err != nil {
@ -494,8 +495,8 @@ func restartServices(
}
runningServices.ChannelManager.SetupHTTPServer(addr, runningServices.HealthServer)
if err = runningServices.ChannelManager.StartAll(context.Background()); err != nil {
return fmt.Errorf("error restarting channels: %w", err)
if err = runningServices.ChannelManager.Reload(context.Background(), cfg); err != nil {
return fmt.Errorf("error reload channels: %w", err)
}
fmt.Println(" ✓ Channels restarted.")

View file

@ -221,6 +221,10 @@ func buildRequestBody(
// Add tool_use blocks
for _, tc := range msg.ToolCalls {
if strings.TrimSpace(tc.Name) == "" {
continue
}
// Handle nil Arguments (GLM-4 may return null input)
input := tc.Arguments
if input == nil {

View file

@ -492,6 +492,20 @@ func TestBuildRequestBodyEdgeCases(t *testing.T) {
},
wantErr: false,
},
{
name: "skip tool calls with empty names",
messages: []Message{
{Role: "assistant", Content: "Calling tool", ToolCalls: []ToolCall{
{ID: "tool-empty", Name: "", Arguments: map[string]any{"ignored": true}},
{ID: "tool-valid", Name: "test_tool", Arguments: map[string]any{"arg": "value"}},
}},
},
model: "test-model",
options: map[string]any{
"max_tokens": 8192,
},
wantErr: false,
},
}
for _, tt := range tests {
@ -513,6 +527,37 @@ func TestBuildRequestBodyEdgeCases(t *testing.T) {
if got["model"] != tt.model {
t.Errorf("model = %v, want %v", got["model"], tt.model)
}
if tt.name == "skip tool calls with empty names" {
messages, ok := got["messages"].([]any)
if !ok || len(messages) != 1 {
t.Fatalf("messages = %#v, want single assistant message", got["messages"])
}
assistantMsg, ok := messages[0].(map[string]any)
if !ok {
t.Fatalf("assistant message = %#v, want map", messages[0])
}
content, ok := assistantMsg["content"].([]any)
if !ok {
t.Fatalf("assistant content = %#v, want []any", assistantMsg["content"])
}
if len(content) != 2 {
t.Fatalf("assistant content length = %d, want 2", len(content))
}
toolUse, ok := content[1].(map[string]any)
if !ok {
t.Fatalf("tool_use block = %#v, want map", content[1])
}
if gotName := toolUse["name"]; gotName != "test_tool" {
t.Fatalf("tool_use name = %v, want %q", gotName, "test_tool")
}
if gotID := toolUse["id"]; gotID != "tool-valid" {
t.Fatalf("tool_use id = %v, want %q", gotID, "tool-valid")
}
}
})
}
}

View file

@ -16,12 +16,14 @@ import (
"sync/atomic"
"time"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/utils"
)
const (
userAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
userAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
userAgentHonest = "picoclaw/%s (+https://github.com/sipeed/picoclaw; AI assistant bot)"
// HTTP client timeouts for web tool providers.
searchTimeout = 10 * time.Second // Brave, Tavily, DuckDuckGo
@ -913,28 +915,58 @@ func (t *WebFetchTool) Execute(ctx context.Context, args map[string]any) *ToolRe
}
}
req, err := http.NewRequestWithContext(ctx, "GET", urlStr, nil)
if err != nil {
return ErrorResult(fmt.Sprintf("failed to create request: %v", err))
doFetch := func(ua string) (*http.Response, []byte, error) {
req, reqErr := http.NewRequestWithContext(ctx, "GET", urlStr, nil)
if reqErr != nil {
return nil, nil, fmt.Errorf("failed to create request: %w", reqErr)
}
req.Header.Set("User-Agent", ua)
resp, doErr := t.client.Do(req)
if doErr != nil {
return nil, nil, fmt.Errorf("request failed: %w", doErr)
}
resp.Body = http.MaxBytesReader(nil, resp.Body, t.fetchLimitBytes)
b, readErr := io.ReadAll(resp.Body)
return resp, b, readErr
}
req.Header.Set("User-Agent", userAgent)
resp, err := t.client.Do(req)
if err != nil {
return ErrorResult(fmt.Sprintf("request failed: %v", err))
resp, body, err := doFetch(userAgent)
if resp != nil && resp.Body != nil {
defer resp.Body.Close()
}
resp.Body = http.MaxBytesReader(nil, resp.Body, t.fetchLimitBytes)
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
var maxBytesErr *http.MaxBytesError
if errors.As(err, &maxBytesErr) {
return ErrorResult(fmt.Sprintf("failed to read response: size exceeded %d bytes limit", t.fetchLimitBytes))
}
return ErrorResult(fmt.Sprintf("failed to read response: %v", err))
return ErrorResult(err.Error())
}
// Cloudflare (and similar WAFs) signal bot challenges with 403 + cf-mitigated: challenge.
// Retry once with an honest User-Agent that identifies picoclaw, which some
// operators explicitly allow-list for AI assistants.
if resp.StatusCode == http.StatusForbidden && resp.Header.Get("Cf-Mitigated") == "challenge" {
logger.DebugCF("tool", "Cloudflare challenge detected, retrying with honest User-Agent",
map[string]any{"url": urlStr})
honestUA := fmt.Sprintf(userAgentHonest, config.Version)
resp2, body2, err2 := doFetch(honestUA)
if resp2 != nil && resp2.Body != nil {
defer resp2.Body.Close()
}
if err2 == nil {
resp, body = resp2, body2
} else {
var maxBytesErr *http.MaxBytesError
if errors.As(err2, &maxBytesErr) {
return ErrorResult(
fmt.Sprintf("failed to read response: size exceeded %d bytes limit", t.fetchLimitBytes),
)
}
return ErrorResult(err2.Error())
}
}
bodyStr := string(body)
@ -1004,7 +1036,7 @@ func (t *WebFetchTool) Execute(ctx context.Context, args map[string]any) *ToolRe
truncated := len(text) > maxChars
if truncated {
text = text[:maxChars]
text = text[:maxChars] + "\n[Content truncated due to size limit]"
}
result := map[string]any{

View file

@ -212,6 +212,132 @@ func TestWebTool_WebFetch_Truncation(t *testing.T) {
if truncated, ok := resultMap["truncated"].(bool); !ok || !truncated {
t.Errorf("Expected 'truncated' to be true in result")
}
// Text should end with the truncation notice
if text, ok := resultMap["text"].(string); ok {
if !strings.HasSuffix(text, "[Content truncated due to size limit]") {
t.Errorf("Expected text to end with truncation notice, got: %q", text[max(0, len(text)-60):])
}
}
}
// TestWebTool_WebFetch_TruncationNotice verifies the truncation notice is appended
// for all content formats (text/plain, text/html, markdown, application/json).
func TestWebTool_WebFetch_TruncationNotice(t *testing.T) {
withPrivateWebFetchHostsAllowed(t)
const truncationNotice = "[Content truncated due to size limit]"
const maxChars = 100
tests := []struct {
name string
contentType string
body string
format string
}{
{
name: "plain text",
contentType: "text/plain",
body: strings.Repeat("a", 500),
format: "plaintext",
},
{
name: "html plaintext extractor",
contentType: "text/html",
body: "<html><body>" + strings.Repeat("b", 500) + "</body></html>",
format: "plaintext",
},
{
name: "html markdown extractor",
contentType: "text/html",
body: "<html><body>" + strings.Repeat("c", 500) + "</body></html>",
format: "markdown",
},
{
name: "json",
contentType: "application/json",
body: `"` + strings.Repeat("d", 500) + `"`,
format: "plaintext",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", tt.contentType)
w.WriteHeader(http.StatusOK)
w.Write([]byte(tt.body))
}))
defer server.Close()
tool, err := NewWebFetchTool(maxChars, tt.format, testFetchLimit)
if err != nil {
t.Fatalf("NewWebFetchTool() error: %v", err)
}
result := tool.Execute(context.Background(), map[string]any{"url": server.URL})
if result.IsError {
t.Fatalf("unexpected error: %s", result.ForLLM)
}
var resultMap map[string]any
if err := json.Unmarshal([]byte(result.ForLLM), &resultMap); err != nil {
t.Fatalf("failed to unmarshal result JSON: %v", err)
}
text, ok := resultMap["text"].(string)
if !ok {
t.Fatal("missing 'text' field in result")
}
if !strings.HasSuffix(text, truncationNotice) {
t.Errorf("expected text to end with %q, got suffix: %q", truncationNotice, text[max(0, len(text)-60):])
}
if truncated, ok := resultMap["truncated"].(bool); !ok || !truncated {
t.Errorf("expected truncated=true in result")
}
})
}
}
// TestWebTool_WebFetch_NoTruncationNoticeWhenFitsInLimit verifies that the notice
// is NOT appended when the content fits within the limit.
func TestWebTool_WebFetch_NoTruncationNoticeWhenFitsInLimit(t *testing.T) {
withPrivateWebFetchHostsAllowed(t)
const truncationNotice = "[Content truncated due to size limit]"
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "text/plain")
w.WriteHeader(http.StatusOK)
w.Write([]byte("short content"))
}))
defer server.Close()
tool, err := NewWebFetchTool(50000, format, testFetchLimit)
if err != nil {
t.Fatalf("NewWebFetchTool() error: %v", err)
}
result := tool.Execute(context.Background(), map[string]any{"url": server.URL})
if result.IsError {
t.Fatalf("unexpected error: %s", result.ForLLM)
}
var resultMap map[string]any
if err := json.Unmarshal([]byte(result.ForLLM), &resultMap); err != nil {
t.Fatalf("failed to unmarshal result JSON: %v", err)
}
text, _ := resultMap["text"].(string)
if strings.Contains(text, truncationNotice) {
t.Errorf("expected no truncation notice for content within limit, got: %q", text)
}
if truncated, _ := resultMap["truncated"].(bool); truncated {
t.Errorf("expected truncated=false for content within limit")
}
}
func TestWebFetchTool_PayloadTooLarge(t *testing.T) {
@ -943,6 +1069,119 @@ func TestWebTool_TavilySearch_Success(t *testing.T) {
}
}
// TestWebFetchTool_CloudflareChallenge_RetryWithHonestUA verifies that a 403 response
// with cf-mitigated: challenge triggers a retry using the honest picoclaw User-Agent,
// and that the retry response is returned when it succeeds.
func TestWebFetchTool_CloudflareChallenge_RetryWithHonestUA(t *testing.T) {
withPrivateWebFetchHostsAllowed(t)
requestCount := 0
var receivedUAs []string
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
requestCount++
receivedUAs = append(receivedUAs, r.Header.Get("User-Agent"))
if requestCount == 1 {
// First request: simulate Cloudflare challenge
w.Header().Set("Cf-Mitigated", "challenge")
w.Header().Set("Content-Type", "text/html")
w.WriteHeader(http.StatusForbidden)
w.Write([]byte("<html><body>Cloudflare challenge</body></html>"))
return
}
// Second request (honest UA retry): success
w.Header().Set("Content-Type", "text/plain")
w.WriteHeader(http.StatusOK)
w.Write([]byte("real content"))
}))
defer server.Close()
tool, err := NewWebFetchTool(50000, format, testFetchLimit)
if err != nil {
t.Fatalf("NewWebFetchTool() error: %v", err)
}
result := tool.Execute(context.Background(), map[string]any{"url": server.URL})
if result.IsError {
t.Fatalf("expected success after retry, got error: %s", result.ForLLM)
}
if !strings.Contains(result.ForLLM, "real content") {
t.Errorf("expected retry response content, got: %s", result.ForLLM)
}
if requestCount != 2 {
t.Errorf("expected exactly 2 requests, got %d", requestCount)
}
// First request must use the generic user agent
if receivedUAs[0] != userAgent {
t.Errorf("first request UA = %q, want %q", receivedUAs[0], userAgent)
}
// Second request must use the honest picoclaw user agent
if !strings.Contains(receivedUAs[1], "picoclaw") {
t.Errorf("retry request UA = %q, want it to contain 'picoclaw'", receivedUAs[1])
}
}
// TestWebFetchTool_CloudflareChallenge_NoRetryOnOtherErrors verifies that a plain 403
// (without cf-mitigated: challenge) does NOT trigger a retry.
func TestWebFetchTool_CloudflareChallenge_NoRetryOnOtherErrors(t *testing.T) {
withPrivateWebFetchHostsAllowed(t)
requestCount := 0
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
requestCount++
w.Header().Set("Content-Type", "text/plain")
w.WriteHeader(http.StatusForbidden)
w.Write([]byte("plain forbidden"))
}))
defer server.Close()
tool, err := NewWebFetchTool(50000, format, testFetchLimit)
if err != nil {
t.Fatalf("NewWebFetchTool() error: %v", err)
}
tool.Execute(context.Background(), map[string]any{"url": server.URL})
if requestCount != 1 {
t.Errorf("expected exactly 1 request for plain 403, got %d", requestCount)
}
}
// TestWebFetchTool_CloudflareChallenge_RetryFailsToo verifies that if the honest-UA
// retry also fails (e.g. still blocked), the error from the retry is returned.
func TestWebFetchTool_CloudflareChallenge_RetryFailsToo(t *testing.T) {
withPrivateWebFetchHostsAllowed(t)
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
// Always return CF challenge regardless of UA
w.Header().Set("Cf-Mitigated", "challenge")
w.Header().Set("Content-Type", "text/html")
w.WriteHeader(http.StatusForbidden)
w.Write([]byte("<html><body>still blocked</body></html>"))
}))
defer server.Close()
tool, err := NewWebFetchTool(50000, format, testFetchLimit)
if err != nil {
t.Fatalf("NewWebFetchTool() error: %v", err)
}
result := tool.Execute(context.Background(), map[string]any{"url": server.URL})
// Should not be an error — the retry response is used as-is (403 is a valid HTTP response)
if result.IsError {
t.Fatalf("expected non-error result even when retry is also blocked, got: %s", result.ForLLM)
}
// Status in the JSON result should reflect the 403
if !strings.Contains(result.ForLLM, "403") {
t.Errorf("expected status 403 in result, got: %s", result.ForLLM)
}
}
func TestAPIKeyPool(t *testing.T) {
pool := NewAPIKeyPool([]string{"key1", "key2", "key3"})
if len(pool.keys) != 3 {

View file

@ -138,6 +138,7 @@ export function GenericForm({
real_name: t("channels.form.desc.realName"),
channels: t("channels.form.desc.channels"),
request_caps: t("channels.form.desc.requestCaps"),
max_base64_file_size_mib: t("channels.form.desc.maxBase64FileSizeMiB"),
}
return (
descriptions[key] ??

View file

@ -327,6 +327,7 @@
"realName": "Displayed real name.",
"channels": "IRC channels to join.",
"requestCaps": "IRC capability list requested on connect.",
"maxBase64FileSizeMiB": "Maximum size in MiB for converting local files to base64 before upload. 0 means unlimited. Applies only to local files, not URL uploads.",
"genericField": "Used to configure {{field}}."
}
},

View file

@ -327,6 +327,7 @@
"realName": "显示名称。",
"channels": "要加入的 IRC 频道列表。",
"requestCaps": "连接时请求的 IRC 扩展能力列表。",
"maxBase64FileSizeMiB": "本地文件转为 base64 上传的最大体积,单位 MiB0 表示不限制,仅影响本地文件,不影响 URL 直传。",
"genericField": "用于配置{{field}}。"
}
},