Merge branch 'main' into fix/discord-message-limit

This commit is contained in:
Andrew Ivory 2026-02-18 12:17:50 +00:00 committed by GitHub
commit bf5aa18909
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 1774 additions and 84 deletions

43
.github/pull_request_template.md vendored Normal file
View file

@ -0,0 +1,43 @@
## 📝 Description
<!-- Please briefly describe the changes and purpose of this PR -->
## 🗣️ Type of Change
- [ ] 🐞 Bug fix (non-breaking change which fixes an issue)
- [ ] ✨ New feature (non-breaking change which adds functionality)
- [ ] 📖 Documentation update
- [ ] ⚡ Code refactoring (no functional changes, no api changes)
## 🤖 AI Code Generation
- [ ] 🤖 Fully AI-generated (100% AI, 0% Human)
- [ ] 🛠️ Mostly AI-generated (AI draft, Human verified/modified)
- [ ] 👨‍💻 Mostly Human-written (Human lead, AI assisted or none)
## 🔗 Related Issue
<!-- Please link the related issue(s) (e.g., Fixes #123, Closes #456) -->
## 📚 Technical Context (Skip for Docs)
- **Reference URL:**
- **Reasoning:**
## 🧪 Test Environment
- **Hardware:** <!-- e.g. Raspberry Pi 5, Orange Pi, PC-->
- **OS:** <!-- e.g. Debian 12, Ubuntu 22.04 -->
- **Model/Provider:** <!-- e.g. OpenAI GPT-4o, Kimi k2, DeepSeek-V3 -->
- **Channels:** <!-- e.g. Discord, Telegram, Feishu, ... -->
## 📸 Evidence (Optional)
<details>
<summary>Click to view Logs/Screenshots</summary>
<!-- Please paste relevant screenshots or logs here -->
</details>
## ☑️ Checklist
- [ ] My code/docs follow the style of this project.
- [ ] I have performed a self-review of my own changes.
- [ ] I have updated the documentation accordingly.

View file

@ -32,11 +32,13 @@ jobs:
- name: Create and push tag
shell: bash
env:
RELEASE_TAG: ${{ inputs.tag }}
run: |
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
git tag -a "${{ inputs.tag }}" -m "Release ${{ inputs.tag }}"
git push origin "${{ inputs.tag }}"
git tag -a "$RELEASE_TAG" -m "Release $RELEASE_TAG"
git push origin "$RELEASE_TAG"
release:
name: GoReleaser Release
@ -53,6 +55,7 @@ jobs:
ref: ${{ inputs.tag }}
- name: Setup Go from go.mod
id: setup-go
uses: actions/setup-go@v5
with:
go-version-file: go.mod
@ -87,6 +90,7 @@ jobs:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
DOCKERHUB_IMAGE_NAME: ${{ vars.DOCKERHUB_REPOSITORY }}
GOVERSION: ${{ steps.setup-go.outputs.go-version }}
- name: Apply release flags
shell: bash

View file

@ -11,6 +11,14 @@ builds:
- id: picoclaw
env:
- CGO_ENABLED=0
tags:
- stdjson
ldflags:
- -s -w
- -X main.version={{ .Version }}
- -X main.gitCommit={{ .ShortCommit }}
- -X main.buildTime={{ .Date }}
- -X main.goVersion={{ .Env.GOVERSION }}
goos:
- linux
- windows

View file

@ -33,7 +33,14 @@ HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
# Copy the compiled binary from the builder stage
COPY --from=builder /src/build/picoclaw /usr/local/bin/picoclaw
# Create necessary directories and initialize
# Create non-root user and group
RUN addgroup -g 1000 picoclaw && \
adduser -D -u 1000 -G picoclaw picoclaw
# Switch to non-root user
USER picoclaw
# Run onboard to create initial directories and config
RUN /usr/local/bin/picoclaw onboard
# Set the binary as the entrypoint

View file

@ -11,11 +11,11 @@ VERSION?=$(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
GIT_COMMIT=$(shell git rev-parse --short=8 HEAD 2>/dev/null || echo "dev")
BUILD_TIME=$(shell date +%FT%T%z)
GO_VERSION=$(shell $(GO) version | awk '{print $$3}')
LDFLAGS=-ldflags "-X main.version=$(VERSION) -X main.gitCommit=$(GIT_COMMIT) -X main.buildTime=$(BUILD_TIME) -X main.goVersion=$(GO_VERSION)"
LDFLAGS=-ldflags "-X main.version=$(VERSION) -X main.gitCommit=$(GIT_COMMIT) -X main.buildTime=$(BUILD_TIME) -X main.goVersion=$(GO_VERSION) -s -w"
# Go variables
GO?=go
GOFLAGS?=-v
GOFLAGS?=-v -tags stdjson
# Installation
INSTALL_PREFIX?=$(HOME)/.local
@ -39,6 +39,8 @@ ifeq ($(UNAME_S),Linux)
ARCH=amd64
else ifeq ($(UNAME_M),aarch64)
ARCH=arm64
else ifeq ($(UNAME_M),loongarch64)
ARCH=loong64
else ifeq ($(UNAME_M),riscv64)
ARCH=riscv64
else
@ -84,6 +86,7 @@ build-all: generate
@mkdir -p $(BUILD_DIR)
GOOS=linux GOARCH=amd64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-linux-amd64 ./$(CMD_DIR)
GOOS=linux GOARCH=arm64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-linux-arm64 ./$(CMD_DIR)
GOOS=linux GOARCH=loong64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-linux-loong64 ./$(CMD_DIR)
GOOS=linux GOARCH=riscv64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-linux-riscv64 ./$(CMD_DIR)
GOOS=darwin GOARCH=arm64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-darwin-arm64 ./$(CMD_DIR)
GOOS=windows GOARCH=amd64 $(GO) build $(LDFLAGS) -o $(BUILD_DIR)/$(BINARY_NAME)-windows-amd64.exe ./$(CMD_DIR)

View file

@ -3,7 +3,7 @@
<h1>PicoClaw: Go で書かれた超効率 AI アシスタント</h1>
<h3>$10 ハードウェア · 10MB RAM · 1秒起動 · 皮皮虾,我们走</h3>
<h3>$10 ハードウェア · 10MB RAM · 1秒起動 · 行くぜ、シャコ</h3>
<h3></h3>
<p>
@ -12,7 +12,7 @@
<img src="https://img.shields.io/badge/license-MIT-green" alt="License">
</p>
**日本語** | [English](README.md)
[中文](README.zh.md) | **日本語** | [Português](README.pt-br.md) | [English](README.md)
</div>
@ -39,7 +39,7 @@
</table>
## 📢 ニュース
2026-02-09 🎉 PicoClaw リリース!$10 ハードウェアで 10MB 未満の RAM で動く AI エージェントを 1 日で構築。🦐 皮皮虾,我们走
2026-02-09 🎉 PicoClaw リリース!$10 ハードウェアで 10MB 未満の RAM で動く AI エージェントを 1 日で構築。🦐 行くぜ、シャコ
## ✨ 特徴
@ -195,6 +195,9 @@ picoclaw onboard
"api_key": "YOUR_BRAVE_API_KEY",
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {
@ -697,6 +700,9 @@ HEARTBEAT_OK 応答 ユーザーが直接結果を受け取る
"search": {
"apiKey": "BSA..."
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {
@ -729,7 +735,7 @@ Discord: https://discord.gg/V4sAZ9XWpN
## 🐛 トラブルシューティング
### Web 検索で「API 配置问题」と表示される
### Web 検索で「API 設定の問題」と表示される
検索 API キーをまだ設定していない場合、これは正常です。PicoClaw は手動検索用の便利なリンクを提供します。

View file

@ -14,7 +14,7 @@
<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>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | **English**
[中文](README.zh.md) | [日本語](README.ja.md) | [Português](README.pt-br.md) | **English**
</div>
---
@ -49,7 +49,7 @@
## 📢 News
2026-02-16 🎉 PicoClaw hit 12K stars in one week! Thank you all for your support! PicoClaw is growing faster than we ever imagined. Given the high volume of PRs, we urgently need community maintainers. Our volunteer roles and roadmap are officially posted [here](doc/picoclaw_community_roadmap_260216.md) —we cant wait to have you on board!
2026-02-16 🎉 PicoClaw hit 12K stars in one week! Thank you all for your support! PicoClaw is growing faster than we ever imagined. Given the high volume of PRs, we urgently need community maintainers. Our volunteer roles and roadmap are officially posted [here](docs/picoclaw_community_roadmap_260216.md) —we cant wait to have you on board!
2026-02-13 🎉 PicoClaw hit 5000 stars in 4days! Thank you for the community! There are so many PRs&issues come in (during Chinese New Year holidays), we are finalizing the Project Roadmap and setting up the Developer Group to accelerate PicoClaw's development.
🚀 Call to Action: Please submit your feature requests in GitHub Discussions. We will review and prioritize them during our upcoming weekly meeting.
@ -99,6 +99,20 @@
</tr>
</table>
### 📱 Run on old Android Phones
Give your decade-old phone a second life! Turn it into a smart AI Assistant with PicoClaw. Quick Start:
1. **Install Termux** (Available on F-Droid or Google Play).
2. **Execute cmds**
```bash
# Note: Replace v0.1.1 with the latest version from the Releases page
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-arm64
chmod +x picoclaw-linux-arm64
pkg install proot
termux-chroot ./picoclaw-linux-arm64 onboard
```
And then follow the instructions in the "Quick Start" section to complete the configuration!
<img src="assets/termux.jpg" alt="PicoClaw" width="512">
### 🐜 Innovative Low-Footprint Deploy
PicoClaw can be deployed on almost any Linux device!
@ -760,6 +774,9 @@ picoclaw agent -m "Hello"
"enabled": true,
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {

881
README.pt-br.md Normal file
View file

@ -0,0 +1,881 @@
<div align="center">
<img src="assets/logo.jpg" alt="PicoClaw" width="512">
<h1>PicoClaw: Assistente de IA Ultra-Eficiente em Go</h1>
<h3>Hardware de $10 · 10MB de RAM · Boot em 1s · 皮皮虾,我们走!</h3>
<p>
<img src="https://img.shields.io/badge/Go-1.21+-00ADD8?style=flat&logo=go&logoColor=white" alt="Go">
<img src="https://img.shields.io/badge/Arch-x86__64%2C%20ARM64%2C%20RISC--V-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://x.com/SipeedIO"><img src="https://img.shields.io/badge/X_(Twitter)-SipeedIO-black?style=flat&logo=x&logoColor=white" alt="Twitter"></a>
</p>
[中文](README.zh.md) | [日本語](README.ja.md) | [English](README.md) | **Português**
</div>
---
🦐 **PicoClaw** é um assistente pessoal de IA ultra-leve inspirado no [nanobot](https://github.com/HKUDS/nanobot), reescrito do zero em **Go** por meio de um processo de "auto-inicialização" (self-bootstrapping) — onde o próprio agente de IA conduziu toda a migração de arquitetura e otimização de código.
⚡️ **Extremamente leve:** Roda em hardware de apenas **$10** com **<10MB** de RAM. Isso é 99% menos memória que o OpenClaw e 98% mais barato que um 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]
> **🚨 DECLARACAO DE SEGURANCA & CANAIS OFICIAIS**
>
> * **SEM CRIPTOMOEDAS:** O PicoClaw **NAO** possui nenhum token/moeda oficial. Todas as alegacoes no `pump.fun` ou outras plataformas de negociacao sao **GOLPES**.
> * **DOMINIO OFICIAL:** O **UNICO** site oficial e **[picoclaw.io](https://picoclaw.io)**, e o site da empresa e **[sipeed.com](https://sipeed.com)**.
> * **Aviso:** Muitos dominios `.ai/.org/.com/.net/...` foram registrados por terceiros, nao sao nossos.
> * **Aviso:** O PicoClaw esta em fase inicial de desenvolvimento e pode ter problemas de seguranca de rede nao resolvidos. Nao implante em ambientes de producao antes da versao v1.0.
> * **Nota:** O PicoClaw recentemente fez merge de muitos PRs, o que pode resultar em maior consumo de memoria (10-20MB) nas versoes mais recentes. Planejamos priorizar a otimizacao de recursos assim que o conjunto de funcionalidades estiver estavel.
## 📢 Novidades
2026-02-16 🎉 PicoClaw atingiu 12K stars em uma semana! Obrigado a todos pelo apoio! O PicoClaw esta crescendo mais rapido do que jamais imaginamos. Dado o alto volume de PRs, precisamos urgentemente de maintainers da comunidade. Nossos papeis de voluntarios e roadmap foram publicados oficialmente [aqui](docs/picoclaw_community_roadmap_260216.md) — estamos ansiosos para ter voce a bordo!
2026-02-13 🎉 PicoClaw atingiu 5000 stars em 4 dias! Obrigado a comunidade! Estamos finalizando o **Roadmap do Projeto** e configurando o **Grupo de Desenvolvedores** para acelerar o desenvolvimento do PicoClaw.
🚀 **Chamada para Acao:** Envie suas solicitacoes de funcionalidades nas GitHub Discussions. Revisaremos e priorizaremos na proxima reuniao semanal.
2026-02-09 🎉 PicoClaw lancado oficialmente! Construido em 1 dia para trazer Agentes de IA para hardware de $10 com <10MB de RAM. 🦐 PicoClaw, Partiu!
## ✨ Funcionalidades
🪶 **Ultra-Leve**: Consumo de memoria <10MB 99% menor que o Clawdbot para funcionalidades essenciais.
💰 **Custo Minimo**: Eficiente o suficiente para rodar em hardware de $10 — 98% mais barato que um Mac mini.
⚡️ **Inicializacao Relampago**: Tempo de inicializacao 400X mais rapido, boot em 1 segundo mesmo em CPU single-core de 0.6GHz.
🌍 **Portabilidade Real**: Um unico binario auto-contido para RISC-V, ARM e x86. Um clique e ja era!
🤖 **Auto-Construido por IA**: Implementacao nativa em Go de forma autonoma — 95% do nucleo gerado pelo Agente com refinamento humano no loop.
| | OpenClaw | NanoBot | **PicoClaw** |
| ----------------------------- | ------------- | ------------------------ | ----------------------------------------- |
| **Linguagem** | TypeScript | Python | **Go** |
| **RAM** | >1GB | >100MB | **< 10MB** |
| **Inicializacao**</br>(CPU 0.8GHz) | >500s | >30s | **<1s** |
| **Custo** | Mac Mini $599 | Maioria dos SBC Linux </br>~$50 | **Qualquer placa Linux**</br>**A partir de $10** |
<img src="assets/compare.jpg" alt="PicoClaw" width="512">
## 🦾 Demonstracao
### 🛠️ Fluxos de Trabalho Padrao do Assistente
<table align="center">
<tr align="center">
<th><p align="center">🧩 Engenharia Full-Stack</p></th>
<th><p align="center">🗂️ Gerenciamento de Logs & Planejamento</p></th>
<th><p align="center">🔎 Busca Web & Aprendizado</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">Desenvolver • Implantar • Escalar</td>
<td align="center">Agendar • Automatizar • Memorizar</td>
<td align="center">Descobrir • Analisar • Tendencias</td>
</tr>
</table>
### 📱 Rode em celulares Android antigos
De uma segunda vida ao seu celular de dez anos atras! Transforme-o em um assistente de IA inteligente com o PicoClaw. Inicio rapido:
1. **Instale o Termux** (Disponivel no F-Droid ou Google Play).
2. **Execute os comandos**
```bash
# Nota: Substitua v0.1.1 pela versao mais recente da pagina de Releases
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-arm64
chmod +x picoclaw-linux-arm64
pkg install proot
termux-chroot ./picoclaw-linux-arm64 onboard
```
Depois siga as instrucoes na secao "Inicio Rapido" para completar a configuracao!
<img src="assets/termux.jpg" alt="PicoClaw" width="512">
### 🐜 Implantacao Inovadora com Baixo Consumo
O PicoClaw pode ser implantado em praticamente qualquer dispositivo Linux!
- $9.9 [LicheeRV-Nano](https://www.aliexpress.com/item/1005006519668532.html) versao E (Ethernet) ou W (WiFi6), para Assistente Domestico Minimalista
- $30~50 [NanoKVM](https://www.aliexpress.com/item/1005007369816019.html), ou $100 [NanoKVM-Pro](https://www.aliexpress.com/item/1005010048471263.html) para Manutencao Automatizada de Servidores
- $50 [MaixCAM](https://www.aliexpress.com/item/1005008053333693.html) ou $100 [MaixCAM2](https://www.kickstarter.com/projects/zepan/maixcam2-build-your-next-gen-4k-ai-camera) para Monitoramento Inteligente
https://private-user-images.githubusercontent.com/83055338/547056448-e7b031ff-d6f5-4468-bcca-5726b6fecb5c.mp4
🌟 Mais cenarios de implantacao aguardam voce!
## 📦 Instalacao
### Instalar com binario pre-compilado
Baixe o binario para sua plataforma na pagina de [releases](https://github.com/sipeed/picoclaw/releases).
### Instalar a partir do codigo-fonte (funcionalidades mais recentes, recomendado para desenvolvimento)
```bash
git clone https://github.com/sipeed/picoclaw.git
cd picoclaw
make deps
# Build, sem necessidade de instalar
make build
# Build para multiplas plataformas
make build-all
# Build e Instalar
make install
```
## 🐳 Docker Compose
Voce tambem pode rodar o PicoClaw usando Docker Compose sem instalar nada localmente.
```bash
# 1. Clone este repositorio
git clone https://github.com/sipeed/picoclaw.git
cd picoclaw
# 2. Configure suas API keys
cp config/config.example.json config/config.json
vim config/config.json # Configure DISCORD_BOT_TOKEN, API keys, etc.
# 3. Build & Iniciar
docker compose --profile gateway up -d
# 4. Ver logs
docker compose logs -f picoclaw-gateway
# 5. Parar
docker compose --profile gateway down
```
### Modo Agente (Execucao unica)
```bash
# Fazer uma pergunta
docker compose run --rm picoclaw-agent -m "Quanto e 2+2?"
# Modo interativo
docker compose run --rm picoclaw-agent
```
### Rebuild
```bash
docker compose --profile gateway build --no-cache
docker compose --profile gateway up -d
```
### 🚀 Inicio Rapido
> [!TIP]
> Configure sua API key em `~/.picoclaw/config.json`.
> Obtenha API keys: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
> Busca web e **opcional** — obtenha a [Brave Search API](https://brave.com/search/api) gratuita (2000 consultas gratis/mes) ou use o fallback automatico integrado.
**1. Inicializar**
```bash
picoclaw onboard
```
**2. Configurar** (`~/.picoclaw/config.json`)
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"model": "glm-4.7",
"max_tokens": 8192,
"temperature": 0.7,
"max_tool_iterations": 20
}
},
"providers": {
"openrouter": {
"api_key": "xxx",
"api_base": "https://openrouter.ai/api/v1"
}
},
"tools": {
"web": {
"brave": {
"enabled": false,
"api_key": "YOUR_BRAVE_API_KEY",
"max_results": 5
},
"duckduckgo": {
"enabled": true,
"max_results": 5
}
}
}
}
```
**3. Obter API Keys**
* **Provedor de LLM**: [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)
* **Busca Web** (opcional): [Brave Search](https://brave.com/search/api) - Plano gratuito disponivel (2000 consultas/mes)
> **Nota**: Veja `config.example.json` para um modelo de configuracao completo.
**4. Conversar**
```bash
picoclaw agent -m "Quanto e 2+2?"
```
Pronto! Voce tem um assistente de IA funcionando em 2 minutos.
---
## 💬 Integracao com Apps de Chat
Converse com seu PicoClaw via Telegram, Discord, DingTalk ou LINE.
| Canal | Nivel de Configuracao |
| --- | --- |
| **Telegram** | Facil (apenas um token) |
| **Discord** | Facil (bot token + intents) |
| **QQ** | Facil (AppID + AppSecret) |
| **DingTalk** | Medio (credenciais do app) |
| **LINE** | Medio (credenciais + webhook URL) |
<details>
<summary><b>Telegram</b> (Recomendado)</summary>
**1. Criar o bot**
* Abra o Telegram, busque `@BotFather`
* Envie `/newbot`, siga as instrucoes
* Copie o token
**2. Configurar**
```json
{
"channels": {
"telegram": {
"enabled": true,
"token": "YOUR_BOT_TOKEN",
"allowFrom": ["YOUR_USER_ID"]
}
}
}
```
> Obtenha seu User ID pelo `@userinfobot` no Telegram.
**3. Executar**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>Discord</b></summary>
**1. Criar o bot**
* Acesse <https://discord.com/developers/applications>
* Crie um aplicativo → Bot → Add Bot
* Copie o token do bot
**2. Habilitar Intents**
* Nas configuracoes do Bot, habilite **MESSAGE CONTENT INTENT**
* (Opcional) Habilite **SERVER MEMBERS INTENT** se quiser usar lista de permissoes baseada em dados dos membros
**3. Obter seu User ID**
* Configuracoes do Discord → Avancado → habilite **Modo Desenvolvedor**
* Clique com botao direito no seu avatar → **Copiar ID do Usuario**
**4. Configurar**
```json
{
"channels": {
"discord": {
"enabled": true,
"token": "YOUR_BOT_TOKEN",
"allowFrom": ["YOUR_USER_ID"]
}
}
}
```
**5. Convidar o bot**
* OAuth2 → URL Generator
* Scopes: `bot`
* Bot Permissions: `Send Messages`, `Read Message History`
* Abra a URL de convite gerada e adicione o bot ao seu servidor
**6. Executar**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>QQ</b></summary>
**1. Criar o bot**
- Acesse a [QQ Open Platform](https://q.qq.com/#)
- Crie um aplicativo → Obtenha **AppID** e **AppSecret**
**2. Configurar**
```json
{
"channels": {
"qq": {
"enabled": true,
"app_id": "YOUR_APP_ID",
"app_secret": "YOUR_APP_SECRET",
"allow_from": []
}
}
}
```
> Deixe `allow_from` vazio para permitir todos os usuarios, ou especifique numeros QQ para restringir o acesso.
**3. Executar**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>DingTalk</b></summary>
**1. Criar o bot**
* Acesse a [Open Platform](https://open.dingtalk.com/)
* Crie um app interno
* Copie o Client ID e Client Secret
**2. Configurar**
```json
{
"channels": {
"dingtalk": {
"enabled": true,
"client_id": "YOUR_CLIENT_ID",
"client_secret": "YOUR_CLIENT_SECRET",
"allow_from": []
}
}
}
```
> Deixe `allow_from` vazio para permitir todos os usuarios, ou especifique IDs para restringir o acesso.
**3. Executar**
```bash
picoclaw gateway
```
</details>
<details>
<summary><b>LINE</b></summary>
**1. Criar uma Conta Oficial LINE**
- Acesse o [LINE Developers Console](https://developers.line.biz/)
- Crie um provider → Crie um canal Messaging API
- Copie o **Channel Secret** e o **Channel Access Token**
**2. Configurar**
```json
{
"channels": {
"line": {
"enabled": true,
"channel_secret": "YOUR_CHANNEL_SECRET",
"channel_access_token": "YOUR_CHANNEL_ACCESS_TOKEN",
"webhook_host": "0.0.0.0",
"webhook_port": 18791,
"webhook_path": "/webhook/line",
"allow_from": []
}
}
}
```
**3. Configurar URL do Webhook**
O LINE requer HTTPS para webhooks. Use um reverse proxy ou tunnel:
```bash
# Exemplo com ngrok
ngrok http 18791
```
Em seguida, configure a Webhook URL no LINE Developers Console para `https://seu-dominio/webhook/line` e habilite **Use webhook**.
**4. Executar**
```bash
picoclaw gateway
```
> Em chats de grupo, o bot responde apenas quando mencionado com @. As respostas citam a mensagem original.
> **Docker Compose**: Adicione `ports: ["18791:18791"]` ao servico `picoclaw-gateway` para expor a porta do webhook.
</details>
## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Junte-se a Rede Social de Agentes
Conecte o PicoClaw a Rede Social de Agentes simplesmente enviando uma unica mensagem via CLI ou qualquer App de Chat integrado.
**Leia `https://clawdchat.ai/skill.md` e siga as instrucoes para entrar no [ClawdChat.ai](https://clawdchat.ai)**
## ⚙️ Configuracao Detalhada
Arquivo de configuracao: `~/.picoclaw/config.json`
### Estrutura do Workspace
O PicoClaw armazena dados no workspace configurado (padrao: `~/.picoclaw/workspace`):
```
~/.picoclaw/workspace/
├── sessions/ # Sessoes de conversa e historico
├── memory/ # Memoria de longo prazo (MEMORY.md)
├── state/ # Estado persistente (ultimo canal, etc.)
├── cron/ # Banco de dados de tarefas agendadas
├── skills/ # Skills personalizadas
├── AGENTS.md # Guia de comportamento do Agente
├── HEARTBEAT.md # Prompts de tarefas periodicas (verificado a cada 30 min)
├── IDENTITY.md # Identidade do Agente
├── SOUL.md # Alma do Agente
├── TOOLS.md # Descricao das ferramentas
└── USER.md # Preferencias do usuario
```
### 🔒 Sandbox de Seguranca
O PicoClaw roda em um ambiente sandbox por padrao. O agente so pode acessar arquivos e executar comandos dentro do workspace configurado.
#### Configuracao Padrao
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"restrict_to_workspace": true
}
}
}
```
| Opcao | Padrao | Descricao |
|-------|--------|-----------|
| `workspace` | `~/.picoclaw/workspace` | Diretorio de trabalho do agente |
| `restrict_to_workspace` | `true` | Restringir acesso de arquivos/comandos ao workspace |
#### Ferramentas Protegidas
Quando `restrict_to_workspace: true`, as seguintes ferramentas sao restritas ao sandbox:
| Ferramenta | Funcao | Restricao |
|------------|--------|-----------|
| `read_file` | Ler arquivos | Apenas arquivos dentro do workspace |
| `write_file` | Escrever arquivos | Apenas arquivos dentro do workspace |
| `list_dir` | Listar diretorios | Apenas diretorios dentro do workspace |
| `edit_file` | Editar arquivos | Apenas arquivos dentro do workspace |
| `append_file` | Adicionar a arquivos | Apenas arquivos dentro do workspace |
| `exec` | Executar comandos | Caminhos dos comandos devem estar dentro do workspace |
#### Protecao Adicional do Exec
Mesmo com `restrict_to_workspace: false`, a ferramenta `exec` bloqueia estes comandos perigosos:
* `rm -rf`, `del /f`, `rmdir /s` — Exclusao em massa
* `format`, `mkfs`, `diskpart` — Formatacao de disco
* `dd if=` — Criacao de imagem de disco
* Escrita em `/dev/sd[a-z]` — Escrita direta no disco
* `shutdown`, `reboot`, `poweroff` — Desligamento do sistema
* Fork bomb `:(){ :|:& };:`
#### Exemplos de Erro
```
[ERROR] tool: Tool execution failed
{tool=exec, error=Command blocked by safety guard (path outside working dir)}
```
```
[ERROR] tool: Tool execution failed
{tool=exec, error=Command blocked by safety guard (dangerous pattern detected)}
```
#### Desabilitar Restricoes (Risco de Seguranca)
Se voce precisa que o agente acesse caminhos fora do workspace:
**Metodo 1: Arquivo de configuracao**
```json
{
"agents": {
"defaults": {
"restrict_to_workspace": false
}
}
}
```
**Metodo 2: Variavel de ambiente**
```bash
export PICOCLAW_AGENTS_DEFAULTS_RESTRICT_TO_WORKSPACE=false
```
> ⚠️ **Aviso**: Desabilitar esta restricao permite que o agente acesse qualquer caminho no seu sistema. Use com cuidado apenas em ambientes controlados.
#### Consistencia do Limite de Seguranca
A configuracao `restrict_to_workspace` se aplica consistentemente em todos os caminhos de execucao:
| Caminho de Execucao | Limite de Seguranca |
|----------------------|---------------------|
| Agente Principal | `restrict_to_workspace` ✅ |
| Subagente / Spawn | Herda a mesma restricao ✅ |
| Tarefas Heartbeat | Herda a mesma restricao ✅ |
Todos os caminhos compartilham a mesma restricao de workspace — nao ha como contornar o limite de seguranca por meio de subagentes ou tarefas agendadas.
### Heartbeat (Tarefas Periodicas)
O PicoClaw pode executar tarefas periodicas automaticamente. Crie um arquivo `HEARTBEAT.md` no seu workspace:
```markdown
# Tarefas Periodicas
- Verificar meu email para mensagens importantes
- Revisar minha agenda para proximos eventos
- Verificar a previsao do tempo
```
O agente lera este arquivo a cada 30 minutos (configuravel) e executara as tarefas usando as ferramentas disponiveis.
#### Tarefas Assincronas com Spawn
Para tarefas de longa duracao (busca web, chamadas de API), use a ferramenta `spawn` para criar um **subagente**:
```markdown
# Tarefas Periodicas
## Tarefas Rapidas (resposta direta)
- Informar hora atual
## Tarefas Longas (usar spawn para async)
- Buscar noticias de IA na web e resumir
- Verificar email e reportar mensagens importantes
```
**Comportamentos principais:**
| Funcionalidade | Descricao |
|----------------|-----------|
| **spawn** | Cria subagente assincrono, nao bloqueia o heartbeat |
| **Contexto independente** | Subagente tem seu proprio contexto, sem historico de sessao |
| **Ferramenta message** | Subagente se comunica diretamente com o usuario via ferramenta message |
| **Nao-bloqueante** | Apos o spawn, o heartbeat continua para a proxima tarefa |
#### Como Funciona a Comunicacao do Subagente
```
Heartbeat dispara
Agente le HEARTBEAT.md
Para tarefa longa: spawn subagente
↓ ↓
Continua proxima tarefa Subagente trabalha independentemente
↓ ↓
Todas tarefas concluidas Subagente usa ferramenta "message"
↓ ↓
Responde HEARTBEAT_OK Usuario recebe resultado diretamente
```
O subagente tem acesso as ferramentas (message, web_search, etc.) e pode se comunicar com o usuario independentemente sem passar pelo agente principal.
**Configuracao:**
```json
{
"heartbeat": {
"enabled": true,
"interval": 30
}
}
```
| Opcao | Padrao | Descricao |
|-------|--------|-----------|
| `enabled` | `true` | Habilitar/desabilitar heartbeat |
| `interval` | `30` | Intervalo de verificacao em minutos (min: 5) |
**Variaveis de ambiente:**
* `PICOCLAW_HEARTBEAT_ENABLED=false` para desabilitar
* `PICOCLAW_HEARTBEAT_INTERVAL=60` para alterar o intervalo
### Provedores
> [!NOTE]
> O Groq fornece transcricao de voz gratuita via Whisper. Se configurado, mensagens de voz do Telegram serao automaticamente transcritas.
| Provedor | Finalidade | Obter API Key |
| --- | --- | --- |
| `gemini` | LLM (Gemini direto) | [aistudio.google.com](https://aistudio.google.com) |
| `zhipu` | LLM (Zhipu direto) | [bigmodel.cn](bigmodel.cn) |
| `openrouter` (Em teste) | LLM (recomendado, acesso a todos os modelos) | [openrouter.ai](https://openrouter.ai) |
| `anthropic` (Em teste) | LLM (Claude direto) | [console.anthropic.com](https://console.anthropic.com) |
| `openai` (Em teste) | LLM (GPT direto) | [platform.openai.com](https://platform.openai.com) |
| `deepseek` (Em teste) | LLM (DeepSeek direto) | [platform.deepseek.com](https://platform.deepseek.com) |
| `groq` | LLM + **Transcricao de voz** (Whisper) | [console.groq.com](https://console.groq.com) |
<details>
<summary><b>Configuracao Zhipu</b></summary>
**1. Obter API key**
* Obtenha a [API key](https://bigmodel.cn/usercenter/proj-mgmt/apikeys)
**2. Configurar**
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"model": "glm-4.7",
"max_tokens": 8192,
"temperature": 0.7,
"max_tool_iterations": 20
}
},
"providers": {
"zhipu": {
"api_key": "Sua API Key",
"api_base": "https://open.bigmodel.cn/api/paas/v4"
}
}
}
```
**3. Executar**
```bash
picoclaw agent -m "Ola, como vai?"
```
</details>
<details>
<summary><b>Exemplo de configuracao completa</b></summary>
```json
{
"agents": {
"defaults": {
"model": "anthropic/claude-opus-4-5"
}
},
"providers": {
"openrouter": {
"api_key": "sk-or-v1-xxx"
},
"groq": {
"api_key": "gsk_xxx"
}
},
"channels": {
"telegram": {
"enabled": true,
"token": "123456:ABC...",
"allow_from": ["123456789"]
},
"discord": {
"enabled": true,
"token": "",
"allow_from": [""]
},
"whatsapp": {
"enabled": false
},
"feishu": {
"enabled": false,
"app_id": "cli_xxx",
"app_secret": "xxx",
"encrypt_key": "",
"verification_token": "",
"allow_from": []
},
"qq": {
"enabled": false,
"app_id": "",
"app_secret": "",
"allow_from": []
}
},
"tools": {
"web": {
"brave": {
"enabled": false,
"api_key": "BSA...",
"max_results": 5
},
"duckduckgo": {
"enabled": true,
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {
"enabled": true,
"interval": 30
}
}
```
</details>
## Referencia CLI
| Comando | Descricao |
| --- | --- |
| `picoclaw onboard` | Inicializar configuracao & workspace |
| `picoclaw agent -m "..."` | Conversar com o agente |
| `picoclaw agent` | Modo de chat interativo |
| `picoclaw gateway` | Iniciar o gateway (para bots de chat) |
| `picoclaw status` | Mostrar status |
| `picoclaw cron list` | Listar todas as tarefas agendadas |
| `picoclaw cron add ...` | Adicionar uma tarefa agendada |
### Tarefas Agendadas / Lembretes
O PicoClaw suporta lembretes agendados e tarefas recorrentes por meio da ferramenta `cron`:
* **Lembretes unicos**: "Remind me in 10 minutes" (Me lembre em 10 minutos) → dispara uma vez apos 10min
* **Tarefas recorrentes**: "Remind me every 2 hours" (Me lembre a cada 2 horas) → dispara a cada 2 horas
* **Expressoes Cron**: "Remind me at 9am daily" (Me lembre as 9h todos os dias) → usa expressao cron
As tarefas sao armazenadas em `~/.picoclaw/workspace/cron/` e processadas automaticamente.
## 🤝 Contribuir & Roadmap
PRs sao bem-vindos! O codigo-fonte e intencionalmente pequeno e legivel. 🤗
Roadmap em breve...
Grupo de desenvolvedores em formacao. Requisito de entrada: Pelo menos 1 PR com merge.
Grupos de usuarios:
Discord: <https://discord.gg/V4sAZ9XWpN>
<img src="assets/wechat.png" alt="PicoClaw" width="512">
## 🐛 Solucao de Problemas
### Busca web mostra "API 配置问题"
Isso e normal se voce ainda nao configurou uma API key de busca. O PicoClaw fornecera links uteis para busca manual.
Para habilitar a busca web:
1. **Opcao 1 (Recomendado)**: Obtenha uma API key gratuita em [https://brave.com/search/api](https://brave.com/search/api) (2000 consultas gratis/mes) para os melhores resultados.
2. **Opcao 2 (Sem Cartao de Credito)**: Se voce nao tem uma key, o sistema automaticamente usa o **DuckDuckGo** como fallback (sem necessidade de key).
Adicione a key em `~/.picoclaw/config.json` se usar o Brave:
```json
{
"tools": {
"web": {
"brave": {
"enabled": true,
"api_key": "YOUR_BRAVE_API_KEY",
"max_results": 5
},
"duckduckgo": {
"enabled": true,
"max_results": 5
}
}
}
}
```
### Erros de filtragem de conteudo
Alguns provedores (como Zhipu) possuem filtragem de conteudo. Tente reformular sua pergunta ou use um modelo diferente.
### Bot do Telegram diz "Conflict: terminated by other getUpdates"
Isso acontece quando outra instancia do bot esta rodando. Certifique-se de que apenas um `picoclaw gateway` esteja rodando por vez.
---
## 📝 Comparacao de API Keys
| Servico | Plano Gratuito | Caso de Uso |
| --- | --- | --- |
| **OpenRouter** | 200K tokens/mes | Multiplos modelos (Claude, GPT-4, etc.) |
| **Zhipu** | 200K tokens/mes | Melhor para usuarios chineses |
| **Brave Search** | 2000 consultas/mes | Funcionalidade de busca web |
| **Groq** | Plano gratuito disponivel | Inferencia ultra-rapida (Llama, Mixtral) |

View file

@ -14,7 +14,7 @@
<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>
</p>
**中文** | [日本語](README.ja.md) | [English](README.md)
**中文** | [日本語](README.ja.md) | [Português](README.pt-br.md) | [English](README.md)
</div>
---
@ -50,7 +50,7 @@
## 📢 新闻 (News)
2026-02-16 🎉 PicoClaw 在一周内突破了12K star! 感谢大家的关注PicoClaw 的成长速度超乎我们预期. 由于PR数量的快速膨胀我们亟需社区开发者参与维护. 我们需要的志愿者角色和roadmap已经发布到了[这里](doc/picoclaw_community_roadmap_260216.md), 期待你的参与!
2026-02-16 🎉 PicoClaw 在一周内突破了12K star! 感谢大家的关注PicoClaw 的成长速度超乎我们预期. 由于PR数量的快速膨胀我们亟需社区开发者参与维护. 我们需要的志愿者角色和roadmap已经发布到了[这里](docs/picoclaw_community_roadmap_260216.md), 期待你的参与!
2026-02-13 🎉 **PicoClaw 在 4 天内突破 5000 Stars** 感谢社区的支持由于正值中国春节假期PR 和 Issue 涌入较多,我们正在利用这段时间敲定 **项目路线图 (Roadmap)** 并组建 **开发者群组**,以便加速 PicoClaw 的开发。
🚀 **行动号召:** 请在 GitHub Discussions 中提交您的功能请求 (Feature Requests)。我们将在接下来的周会上进行审查和优先级排序。
@ -100,6 +100,23 @@
</tr>
</table>
### 📱 在手机上轻松运行
picoclaw 可以将你10年前的老旧手机废物利用变身成为你的AI助理快速指南:
1. 先去应用商店下载安装Termux
2. 打开后执行指令
```bash
# 注意: 下面的v0.1.1 可以换为你实际看到的最新版本
wget https://github.com/sipeed/picoclaw/releases/download/v0.1.1/picoclaw-linux-arm64
chmod +x picoclaw-linux-arm64
pkg install proot
termux-chroot ./picoclaw-linux-arm64 onboard
```
然后跟随下面的“快速开始”章节继续配置picoclaw即可使用
<img src="assets/termux.jpg" alt="PicoClaw" width="512">
### 🐜 创新的低占用部署
PicoClaw 几乎可以部署在任何 Linux 设备上!
@ -219,6 +236,9 @@ picoclaw onboard
"api_key": "YOUR_BRAVE_API_KEY",
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
}
}
@ -627,6 +647,9 @@ picoclaw agent -m "你好"
"search": {
"api_key": "BSA..."
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {

116
ROADMAP.md Normal file
View file

@ -0,0 +1,116 @@
# 🦐 PicoClaw Roadmap
> **Vision**: To build the ultimate lightweight, secure, and fully autonomous AI Agent infrastructure.automate the mundane, unleash your creativity
---
## 🚀 1. Core Optimization: Extreme Lightweight
*Our defining characteristic. We fight software bloat to ensure PicoClaw runs smoothly on the smallest embedded devices.*
* [**Memory Footprint Reduction**](https://github.com/sipeed/picoclaw/issues/346)
* **Goal**: Run smoothly on 64MB RAM embedded boards (e.g., low-end RISC-V SBCs) with the core process consuming < 20MB.
* **Context**: RAM is expensive and scarce on edge devices. Memory optimization takes precedence over storage size.
* **Action**: Analyze memory growth between releases, remove redundant dependencies, and optimize data structures.
## 🛡️ 2. Security Hardening: Defense in Depth
*Paying off early technical debt. We invite security experts to help build a "Secure-by-Default" agent.*
* **Input Defense & Permission Control**
* **Prompt Injection Defense**: Harden JSON extraction logic to prevent LLM manipulation.
* **Tool Abuse Prevention**: Strict parameter validation to ensure generated commands stay within safe boundaries.
* **SSRF Protection**: Built-in blocklists for network tools to prevent accessing internal IPs (LAN/Metadata services).
* **Sandboxing & Isolation**
* **Filesystem Sandbox**: Restrict file R/W operations to specific directories only.
* **Context Isolation**: Prevent data leakage between different user sessions or channels.
* **Privacy Redaction**: Auto-redact sensitive info (API Keys, PII) from logs and standard outputs.
* **Authentication & Secrets**
* **Crypto Upgrade**: Adopt modern algorithms like `ChaCha20-Poly1305` for secret storage.
* **OAuth 2.0 Flow**: Deprecate hardcoded API keys in the CLI; move to secure OAuth flows.
## 🔌 3. Connectivity: Protocol-First Architecture
*Connect every model, reach every platform.*
* **Provider**
* [**Architecture Upgrade**](https://github.com/sipeed/picoclaw/issues/283): Refactor from "Vendor-based" to "Protocol-based" classification (e.g., OpenAI-compatible, Ollama-compatible). *(Status: In progress by @Daming, ETA 5 days)*
* **Local Models**: Deep integration with **Ollama**, **vLLM**, **LM Studio**, and **Mistral** (local inference).
* **Online Models**: Continued support for frontier closed-source models.
* **Channel**
* **IM Matrix**: QQ, WeChat (Work), DingTalk, Feishu (Lark), Telegram, Discord, WhatsApp, LINE, Slack, Email, KOOK, Signal, ...
* **Standards**: Support for the **OneBot** protocol.
* [**attachment**](https://github.com/sipeed/picoclaw/issues/348): Native handling of images, audio, and video attachments.
* **Skill Marketplace**
* [**Discovery skills**](https://github.com/sipeed/picoclaw/issues/287): Implement `find_skill` to automatically discover and install skills from the [GitHub Skills Repo] or other registries.
## 🧠 4. Advanced Capabilities: From Chatbot to Agentic AI
*Beyond conversation—focusing on action and collaboration.*
* **Operations**
* [**MCP Support**](https://github.com/sipeed/picoclaw/issues/290): Native support for the **Model Context Protocol (MCP)**.
* [**Browser Automation**](https://github.com/sipeed/picoclaw/issues/293): Headless browser control via CDP (Chrome DevTools Protocol) or ActionBook.
* [**Mobile Operation**](https://github.com/sipeed/picoclaw/issues/292): Android device control (similar to BotDrop).
* **Multi-Agent Collaboration**
* [**Basic Multi-Agent**](https://github.com/sipeed/picoclaw/issues/294) implement
* [**Model Routing**](https://github.com/sipeed/picoclaw/issues/295): "Smart Routing" — dispatch simple tasks to small/local models (fast/cheap) and complex tasks to SOTA models (smart).
* [**Swarm Mode**](https://github.com/sipeed/picoclaw/issues/284): Collaboration between multiple PicoClaw instances on the same network.
* [**AIEOS**](https://github.com/sipeed/picoclaw/issues/296): Exploring AI-Native Operating System interaction paradigms.
## 📚 5. Developer Experience (DevEx) & Documentation
*Lowering the barrier to entry so anyone can deploy in minutes.*
* [**QuickGuide (Zero-Config Start)**](https://github.com/sipeed/picoclaw/issues/350)
* Interactive CLI Wizard: If launched without config, automatically detect the environment and guide the user through Token/Network setup step-by-step.
* **Comprehensive Documentation**
* **Platform Guides**: Dedicated guides for Windows, macOS, Linux, and Android.
* **Step-by-Step Tutorials**: "Babysitter-level" guides for configuring Providers and Channels.
* **AI-Assisted Docs**: Using AI to auto-generate API references and code comments (with human verification to prevent hallucinations).
## 🤖 6. Engineering: AI-Powered Open Source
*Born from Vibe Coding, we continue to use AI to accelerate development.*
* **AI-Enhanced CI/CD**
* Integrate AI for automated Code Review, Linting, and PR Labeling.
* **Bot Noise Reduction**: Optimize bot interactions to keep PR timelines clean.
* **Issue Triage**: AI agents to analyze incoming issues and suggest preliminary fixes.
## 🎨 7. Brand & Community
* [**Logo Design**](https://github.com/sipeed/picoclaw/issues/297): We are looking for a **Mantis Shrimp (Stomatopoda)** logo design!
* *Concept*: Needs to reflect "Small but Mighty" and "Lightning Fast Strikes."
---
### 🤝 Call for Contributions
We welcome community contributions to any item on this roadmap! Please comment on the relevant Issue or submit a PR. Let's build the best Edge AI Agent together!

BIN
assets/termux.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 97 KiB

View file

@ -562,7 +562,8 @@ func gatewayCmd() {
})
// Setup cron tool and service
cronService := setupCronTool(agentLoop, msgBus, cfg.WorkspacePath(), cfg.Agents.Defaults.RestrictToWorkspace)
execTimeout := time.Duration(cfg.Tools.Cron.ExecTimeoutMinutes) * time.Minute
cronService := setupCronTool(agentLoop, msgBus, cfg.WorkspacePath(), cfg.Agents.Defaults.RestrictToWorkspace, execTimeout, cfg)
heartbeatService := heartbeat.NewHeartbeatService(
cfg.WorkspacePath(),
@ -987,14 +988,14 @@ func getConfigPath() string {
return filepath.Join(home, ".picoclaw", "config.json")
}
func setupCronTool(agentLoop *agent.AgentLoop, msgBus *bus.MessageBus, workspace string, restrict bool) *cron.CronService {
func setupCronTool(agentLoop *agent.AgentLoop, msgBus *bus.MessageBus, workspace string, restrict bool, execTimeout time.Duration, config *config.Config) *cron.CronService {
cronStorePath := filepath.Join(workspace, "cron", "jobs.json")
// Create cron service
cronService := cron.NewCronService(cronStorePath, nil)
// Create and register CronTool
cronTool := tools.NewCronTool(cronService, agentLoop, msgBus, workspace, restrict)
cronTool := tools.NewCronTool(cronService, agentLoop, msgBus, workspace, restrict, execTimeout, config)
agentLoop.RegisterTool(cronTool)
// Set the onJob handler

View file

@ -14,7 +14,9 @@
"enabled": false,
"token": "YOUR_TELEGRAM_BOT_TOKEN",
"proxy": "",
"allow_from": ["YOUR_USER_ID"]
"allow_from": [
"YOUR_USER_ID"
]
},
"discord": {
"enabled": false,
@ -77,7 +79,8 @@
},
"openai": {
"api_key": "",
"api_base": ""
"api_base": "",
"web_search": true
},
"openrouter": {
"api_key": "sk-or-v1-xxx",
@ -115,10 +118,19 @@
},
"tools": {
"web": {
"search": {
"brave": {
"enabled": false,
"api_key": "YOUR_BRAVE_API_KEY",
"max_results": 5
},
"perplexity": {
"enabled": false,
"api_key": "pplx-xxx",
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {

View file

@ -11,8 +11,8 @@ services:
profiles:
- agent
volumes:
- ./config/config.json:/root/.picoclaw/config.json:ro
- picoclaw-workspace:/root/.picoclaw/workspace
- ./config/config.json:/home/picoclaw/.picoclaw/config.json:ro
- picoclaw-workspace:/home/picoclaw/.picoclaw/workspace
entrypoint: ["picoclaw", "agent"]
stdin_open: true
tty: true
@ -31,9 +31,9 @@ services:
- gateway
volumes:
# Configuration file
- ./config/config.json:/root/.picoclaw/config.json:ro
- ./config/config.json:/home/picoclaw/.picoclaw/config.json:ro
# Persistent workspace (sessions, memory, logs)
- picoclaw-workspace:/root/.picoclaw/workspace
- picoclaw-workspace:/home/picoclaw/.picoclaw/workspace
command: ["gateway"]
volumes:

122
docs/tools_configuration.md Normal file
View file

@ -0,0 +1,122 @@
# Tools Configuration
PicoClaw's tools configuration is located in the `tools` field of `config.json`.
## Directory Structure
```json
{
"tools": {
"web": { ... },
"exec": { ... },
"approval": { ... },
"cron": { ... }
}
}
```
## Web Tools
Web tools are used for web search and fetching.
### Brave
| Config | Type | Default | Description |
|--------|------|---------|-------------|
| `enabled` | bool | false | Enable Brave search |
| `api_key` | string | - | Brave Search API key |
| `max_results` | int | 5 | Maximum number of results |
### DuckDuckGo
| Config | Type | Default | Description |
|--------|------|---------|-------------|
| `enabled` | bool | true | Enable DuckDuckGo search |
| `max_results` | int | 5 | Maximum number of results |
### Perplexity
| Config | Type | Default | Description |
|--------|------|---------|-------------|
| `enabled` | bool | false | Enable Perplexity search |
| `api_key` | string | - | Perplexity API key |
| `max_results` | int | 5 | Maximum number of results |
## Exec Tool
The exec tool is used to execute shell commands.
| Config | Type | Default | Description |
|--------|------|---------|-------------|
| `enable_deny_patterns` | bool | true | Enable default dangerous command blocking |
| `custom_deny_patterns` | array | [] | Custom deny patterns (regular expressions) |
### Functionality
- **`enable_deny_patterns`**: Set to `false` to completely disable the default dangerous command blocking patterns
- **`custom_deny_patterns`**: Add custom deny regex patterns; commands matching these will be blocked
### Default Blocked Command Patterns
By default, PicoClaw blocks the following dangerous commands:
- Delete commands: `rm -rf`, `del /f/q`, `rmdir /s`
- Disk operations: `format`, `mkfs`, `diskpart`, `dd if=`, writing to `/dev/sd*`
- System operations: `shutdown`, `reboot`, `poweroff`
- Command substitution: `$()`, `${}`, backticks
- Pipe to shell: `| sh`, `| bash`
- Privilege escalation: `sudo`, `chmod`, `chown`
- Process control: `pkill`, `killall`, `kill -9`
- Remote operations: `curl | sh`, `wget | sh`, `ssh`
- Package management: `apt`, `yum`, `dnf`, `npm install -g`, `pip install --user`
- Containers: `docker run`, `docker exec`
- Git: `git push`, `git force`
- Other: `eval`, `source *.sh`
### Configuration Example
```json
{
"tools": {
"exec": {
"enable_deny_patterns": true,
"custom_deny_patterns": [
"\\brm\\s+-r\\b",
"\\bkillall\\s+python"
],
}
}
}
```
## Approval Tool
The approval tool controls permissions for dangerous operations.
| Config | Type | Default | Description |
|--------|------|---------|-------------|
| `enabled` | bool | true | Enable approval functionality |
| `write_file` | bool | true | Require approval for file writes |
| `edit_file` | bool | true | Require approval for file edits |
| `append_file` | bool | true | Require approval for file appends |
| `exec` | bool | true | Require approval for command execution |
| `timeout_minutes` | int | 5 | Approval timeout in minutes |
## Cron Tool
The cron tool is used for scheduling periodic tasks.
| Config | Type | Default | Description |
|--------|------|---------|-------------|
| `exec_timeout_minutes` | int | 5 | Execution timeout in minutes, 0 means no limit |
## Environment Variables
All configuration options can be overridden via environment variables with the format `PICOCLAW_TOOLS_<SECTION>_<KEY>`:
For example:
- `PICOCLAW_TOOLS_WEB_BRAVE_ENABLED=true`
- `PICOCLAW_TOOLS_EXEC_ENABLE_DENY_PATTERNS=false`
- `PICOCLAW_TOOLS_CRON_EXEC_TIMEOUT_MINUTES=10`
Note: Array-type environment variables are not currently supported and must be set via the config file.

View file

@ -71,7 +71,7 @@ func createToolRegistry(workspace string, restrict bool, cfg *config.Config, msg
registry.Register(tools.NewAppendFileTool(workspace, restrict))
// Shell execution
registry.Register(tools.NewExecTool(workspace, restrict))
registry.Register(tools.NewExecToolWithConfig(workspace, restrict, cfg))
if searchTool := tools.NewWebSearchTool(tools.WebSearchToolOptions{
BraveAPIKey: cfg.Tools.Web.Brave.APIKey,
@ -79,6 +79,9 @@ func createToolRegistry(workspace string, restrict bool, cfg *config.Config, msg
BraveEnabled: cfg.Tools.Web.Brave.Enabled,
DuckDuckGoMaxResults: cfg.Tools.Web.DuckDuckGo.MaxResults,
DuckDuckGoEnabled: cfg.Tools.Web.DuckDuckGo.Enabled,
PerplexityAPIKey: cfg.Tools.Web.Perplexity.APIKey,
PerplexityMaxResults: cfg.Tools.Web.Perplexity.MaxResults,
PerplexityEnabled: cfg.Tools.Web.Perplexity.Enabled,
}); searchTool != nil {
registry.Register(searchTool)
}

View file

@ -18,7 +18,6 @@ type MaixCamChannel struct {
listener net.Listener
clients map[net.Conn]bool
clientsMux sync.RWMutex
running bool
}
type MaixCamMessage struct {
@ -35,7 +34,6 @@ func NewMaixCamChannel(cfg config.MaixCamConfig, bus *bus.MessageBus) (*MaixCamC
BaseChannel: base,
config: cfg,
clients: make(map[net.Conn]bool),
running: false,
}, nil
}

View file

@ -167,19 +167,19 @@ type DevicesConfig struct {
}
type ProvidersConfig struct {
Anthropic ProviderConfig `json:"anthropic"`
OpenAI ProviderConfig `json:"openai"`
OpenRouter ProviderConfig `json:"openrouter"`
Groq ProviderConfig `json:"groq"`
Zhipu ProviderConfig `json:"zhipu"`
VLLM ProviderConfig `json:"vllm"`
Gemini ProviderConfig `json:"gemini"`
Nvidia ProviderConfig `json:"nvidia"`
Ollama ProviderConfig `json:"ollama"`
Moonshot ProviderConfig `json:"moonshot"`
ShengSuanYun ProviderConfig `json:"shengsuanyun"`
DeepSeek ProviderConfig `json:"deepseek"`
GitHubCopilot ProviderConfig `json:"github_copilot"`
Anthropic ProviderConfig `json:"anthropic"`
OpenAI OpenAIProviderConfig `json:"openai"`
OpenRouter ProviderConfig `json:"openrouter"`
Groq ProviderConfig `json:"groq"`
Zhipu ProviderConfig `json:"zhipu"`
VLLM ProviderConfig `json:"vllm"`
Gemini ProviderConfig `json:"gemini"`
Nvidia ProviderConfig `json:"nvidia"`
Ollama ProviderConfig `json:"ollama"`
Moonshot ProviderConfig `json:"moonshot"`
ShengSuanYun ProviderConfig `json:"shengsuanyun"`
DeepSeek ProviderConfig `json:"deepseek"`
GitHubCopilot ProviderConfig `json:"github_copilot"`
}
type ProviderConfig struct {
@ -190,6 +190,11 @@ type ProviderConfig struct {
ConnectMode string `json:"connect_mode,omitempty" env:"PICOCLAW_PROVIDERS_{{.Name}}_CONNECT_MODE"` //only for Github Copilot, `stdio` or `grpc`
}
type OpenAIProviderConfig struct {
ProviderConfig
WebSearch bool `json:"web_search" env:"PICOCLAW_PROVIDERS_OPENAI_WEB_SEARCH"`
}
type GatewayConfig struct {
Host string `json:"host" env:"PICOCLAW_GATEWAY_HOST"`
Port int `json:"port" env:"PICOCLAW_GATEWAY_PORT"`
@ -206,13 +211,31 @@ type DuckDuckGoConfig struct {
MaxResults int `json:"max_results" env:"PICOCLAW_TOOLS_WEB_DUCKDUCKGO_MAX_RESULTS"`
}
type PerplexityConfig struct {
Enabled bool `json:"enabled" env:"PICOCLAW_TOOLS_WEB_PERPLEXITY_ENABLED"`
APIKey string `json:"api_key" env:"PICOCLAW_TOOLS_WEB_PERPLEXITY_API_KEY"`
MaxResults int `json:"max_results" env:"PICOCLAW_TOOLS_WEB_PERPLEXITY_MAX_RESULTS"`
}
type WebToolsConfig struct {
Brave BraveConfig `json:"brave"`
DuckDuckGo DuckDuckGoConfig `json:"duckduckgo"`
Perplexity PerplexityConfig `json:"perplexity"`
}
type CronToolsConfig struct {
ExecTimeoutMinutes int `json:"exec_timeout_minutes" env:"PICOCLAW_TOOLS_CRON_EXEC_TIMEOUT_MINUTES"` // 0 means no timeout
}
type ExecConfig struct {
EnableDenyPatterns bool `json:"enable_deny_patterns" env:"PICOCLAW_TOOLS_EXEC_ENABLE_DENY_PATTERNS"`
CustomDenyPatterns []string `json:"custom_deny_patterns" env:"PICOCLAW_TOOLS_EXEC_CUSTOM_DENY_PATTERNS"`
}
type ToolsConfig struct {
Web WebToolsConfig `json:"web"`
Web WebToolsConfig `json:"web"`
Cron CronToolsConfig `json:"cron"`
Exec ExecConfig `json:"exec"`
}
func DefaultConfig() *Config {
@ -296,7 +319,7 @@ func DefaultConfig() *Config {
},
Providers: ProvidersConfig{
Anthropic: ProviderConfig{},
OpenAI: ProviderConfig{},
OpenAI: OpenAIProviderConfig{WebSearch: true},
OpenRouter: ProviderConfig{},
Groq: ProviderConfig{},
Zhipu: ProviderConfig{},
@ -321,6 +344,17 @@ func DefaultConfig() *Config {
Enabled: true,
MaxResults: 5,
},
Perplexity: PerplexityConfig{
Enabled: false,
APIKey: "",
MaxResults: 5,
},
},
Cron: CronToolsConfig{
ExecTimeoutMinutes: 5, // default 5 minutes for LLM operations
},
Exec: ExecConfig{
EnableDenyPatterns: true,
},
},
Heartbeat: HeartbeatConfig{

View file

@ -204,3 +204,42 @@ func TestConfig_Complete(t *testing.T) {
t.Error("Heartbeat should be enabled by default")
}
}
func TestDefaultConfig_OpenAIWebSearchEnabled(t *testing.T) {
cfg := DefaultConfig()
if !cfg.Providers.OpenAI.WebSearch {
t.Fatal("DefaultConfig().Providers.OpenAI.WebSearch should be true")
}
}
func TestLoadConfig_OpenAIWebSearchDefaultsTrueWhenUnset(t *testing.T) {
dir := t.TempDir()
configPath := filepath.Join(dir, "config.json")
if err := os.WriteFile(configPath, []byte(`{"providers":{"openai":{"api_base":""}}}`), 0o600); err != nil {
t.Fatalf("WriteFile() error: %v", err)
}
cfg, err := LoadConfig(configPath)
if err != nil {
t.Fatalf("LoadConfig() error: %v", err)
}
if !cfg.Providers.OpenAI.WebSearch {
t.Fatal("OpenAI codex web search should remain true when unset in config file")
}
}
func TestLoadConfig_OpenAIWebSearchCanBeDisabled(t *testing.T) {
dir := t.TempDir()
configPath := filepath.Join(dir, "config.json")
if err := os.WriteFile(configPath, []byte(`{"providers":{"openai":{"web_search":false}}}`), 0o600); err != nil {
t.Fatalf("WriteFile() error: %v", err)
}
cfg, err := LoadConfig(configPath)
if err != nil {
t.Fatalf("LoadConfig() error: %v", err)
}
if cfg.Providers.OpenAI.WebSearch {
t.Fatal("OpenAI codex web search should be false when disabled in config file")
}
}

View file

@ -108,7 +108,10 @@ func ConvertConfig(data map[string]interface{}) (*config.Config, []string, error
case "anthropic":
cfg.Providers.Anthropic = pc
case "openai":
cfg.Providers.OpenAI = pc
cfg.Providers.OpenAI = config.OpenAIProviderConfig{
ProviderConfig: pc,
WebSearch: getBoolOrDefault(pMap, "web_search", true),
}
case "openrouter":
cfg.Providers.OpenRouter = pc
case "groq":
@ -363,6 +366,13 @@ func getBool(data map[string]interface{}, key string) (bool, bool) {
return b, ok
}
func getBoolOrDefault(data map[string]interface{}, key string, defaultVal bool) bool {
if v, ok := getBool(data, key); ok {
return v
}
return defaultVal
}
func getStringSlice(data map[string]interface{}, key string) []string {
v, ok := data[key]
if !ok {

View file

@ -18,9 +18,10 @@ const codexDefaultModel = "gpt-5.2"
const codexDefaultInstructions = "You are Codex, a coding assistant."
type CodexProvider struct {
client *openai.Client
accountID string
tokenSource func() (string, string, error)
client *openai.Client
accountID string
tokenSource func() (string, string, error)
enableWebSearch bool
}
const defaultCodexInstructions = "You are Codex, a coding assistant."
@ -37,8 +38,9 @@ func NewCodexProvider(token, accountID string) *CodexProvider {
}
client := openai.NewClient(opts...)
return &CodexProvider{
client: &client,
accountID: accountID,
client: &client,
accountID: accountID,
enableWebSearch: true,
}
}
@ -78,7 +80,7 @@ func (p *CodexProvider) Chat(ctx context.Context, messages []Message, tools []To
})
}
params := buildCodexParams(messages, tools, resolvedModel, options)
params := buildCodexParams(messages, tools, resolvedModel, options, p.enableWebSearch)
stream := p.client.Responses.NewStreaming(ctx, params, opts...)
defer stream.Close()
@ -182,7 +184,7 @@ func resolveCodexModel(model string) (string, string) {
return codexDefaultModel, "unsupported model family"
}
func buildCodexParams(messages []Message, tools []ToolDefinition, model string, options map[string]interface{}) responses.ResponseNewParams {
func buildCodexParams(messages []Message, tools []ToolDefinition, model string, options map[string]interface{}, enableWebSearch bool) responses.ResponseNewParams {
var inputItems responses.ResponseInputParam
var instructions string
@ -217,12 +219,18 @@ func buildCodexParams(messages []Message, tools []ToolDefinition, model string,
})
}
for _, tc := range msg.ToolCalls {
argsJSON, _ := json.Marshal(tc.Arguments)
name, args, ok := resolveCodexToolCall(tc)
if !ok {
logger.WarnCF("provider.codex", "Skipping invalid tool call in history", map[string]interface{}{
"call_id": tc.ID,
})
continue
}
inputItems = append(inputItems, responses.ResponseInputItemUnionParam{
OfFunctionCall: &responses.ResponseFunctionToolCallParam{
CallID: tc.ID,
Name: tc.Name,
Arguments: string(argsJSON),
Name: name,
Arguments: args,
},
})
}
@ -260,20 +268,50 @@ func buildCodexParams(messages []Message, tools []ToolDefinition, model string,
params.Instructions = openai.Opt(defaultCodexInstructions)
}
if maxTokens, ok := options["max_tokens"].(int); ok {
params.MaxOutputTokens = openai.Opt(int64(maxTokens))
}
if len(tools) > 0 {
params.Tools = translateToolsForCodex(tools)
if len(tools) > 0 || enableWebSearch {
params.Tools = translateToolsForCodex(tools, enableWebSearch)
}
return params
}
func translateToolsForCodex(tools []ToolDefinition) []responses.ToolUnionParam {
result := make([]responses.ToolUnionParam, 0, len(tools))
func resolveCodexToolCall(tc ToolCall) (name string, arguments string, ok bool) {
name = tc.Name
if name == "" && tc.Function != nil {
name = tc.Function.Name
}
if name == "" {
return "", "", false
}
if len(tc.Arguments) > 0 {
argsJSON, err := json.Marshal(tc.Arguments)
if err != nil {
return "", "", false
}
return name, string(argsJSON), true
}
if tc.Function != nil && tc.Function.Arguments != "" {
return name, tc.Function.Arguments, true
}
return name, "{}", true
}
func translateToolsForCodex(tools []ToolDefinition, enableWebSearch bool) []responses.ToolUnionParam {
capHint := len(tools)
if enableWebSearch {
capHint++
}
result := make([]responses.ToolUnionParam, 0, capHint)
for _, t := range tools {
if t.Type != "function" {
continue
}
if enableWebSearch && strings.EqualFold(t.Function.Name, "web_search") {
continue
}
ft := responses.FunctionToolParam{
Name: t.Function.Name,
Parameters: t.Function.Parameters,
@ -284,6 +322,9 @@ func translateToolsForCodex(tools []ToolDefinition) []responses.ToolUnionParam {
}
result = append(result, responses.ToolUnionParam{OfFunction: &ft})
}
if enableWebSearch {
result = append(result, responses.ToolParamOfWebSearch(responses.WebSearchToolTypeWebSearch))
}
return result
}

View file

@ -19,7 +19,7 @@ func TestBuildCodexParams_BasicMessage(t *testing.T) {
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{
"max_tokens": 2048,
"temperature": 0.7,
})
}, true)
if params.Model != "gpt-4o" {
t.Errorf("Model = %q, want %q", params.Model, "gpt-4o")
}
@ -29,6 +29,9 @@ func TestBuildCodexParams_BasicMessage(t *testing.T) {
if params.Instructions.Or("") != defaultCodexInstructions {
t.Errorf("Instructions = %q, want %q", params.Instructions.Or(""), defaultCodexInstructions)
}
if params.MaxOutputTokens.Valid() {
t.Fatalf("MaxOutputTokens should not be set for Codex backend")
}
}
func TestBuildCodexParams_SystemAsInstructions(t *testing.T) {
@ -36,7 +39,7 @@ func TestBuildCodexParams_SystemAsInstructions(t *testing.T) {
{Role: "system", Content: "You are helpful"},
{Role: "user", Content: "Hi"},
}
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{})
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{}, true)
if !params.Instructions.Valid() {
t.Fatal("Instructions should be set")
}
@ -56,7 +59,7 @@ func TestBuildCodexParams_ToolCallConversation(t *testing.T) {
},
{Role: "tool", Content: `{"temp": 72}`, ToolCallID: "call_1"},
}
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{})
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{}, false)
if params.Input.OfInputItemList == nil {
t.Fatal("Input.OfInputItemList should not be nil")
}
@ -65,6 +68,45 @@ func TestBuildCodexParams_ToolCallConversation(t *testing.T) {
}
}
func TestBuildCodexParams_ToolCallFunctionFallback(t *testing.T) {
messages := []Message{
{Role: "user", Content: "Read a file"},
{
Role: "assistant",
ToolCalls: []ToolCall{
{
ID: "call_1",
Type: "function",
Function: &FunctionCall{
Name: "read_file",
Arguments: `{"path":"README.md"}`,
},
},
},
},
{Role: "tool", Content: "ok", ToolCallID: "call_1"},
}
params := buildCodexParams(messages, nil, "gpt-4o", map[string]interface{}{}, false)
if params.Input.OfInputItemList == nil {
t.Fatal("Input.OfInputItemList should not be nil")
}
if len(params.Input.OfInputItemList) != 3 {
t.Fatalf("len(Input items) = %d, want 3", len(params.Input.OfInputItemList))
}
fc := params.Input.OfInputItemList[1].OfFunctionCall
if fc == nil {
t.Fatal("assistant tool call should be converted to function_call input item")
}
if fc.Name != "read_file" {
t.Errorf("Function call name = %q, want %q", fc.Name, "read_file")
}
if fc.Arguments != `{"path":"README.md"}` {
t.Errorf("Function call arguments = %q, want %q", fc.Arguments, `{"path":"README.md"}`)
}
}
func TestBuildCodexParams_WithTools(t *testing.T) {
tools := []ToolDefinition{
{
@ -81,7 +123,7 @@ func TestBuildCodexParams_WithTools(t *testing.T) {
},
},
}
params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, tools, "gpt-4o", map[string]interface{}{})
params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, tools, "gpt-4o", map[string]interface{}{}, false)
if len(params.Tools) != 1 {
t.Fatalf("len(Tools) = %d, want 1", len(params.Tools))
}
@ -94,12 +136,61 @@ func TestBuildCodexParams_WithTools(t *testing.T) {
}
func TestBuildCodexParams_StoreIsFalse(t *testing.T) {
params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, nil, "gpt-4o", map[string]interface{}{})
params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, nil, "gpt-4o", map[string]interface{}{}, false)
if !params.Store.Valid() || params.Store.Or(true) != false {
t.Error("Store should be explicitly set to false")
}
}
func TestBuildCodexParams_DefaultWebSearchEnabled(t *testing.T) {
params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, nil, "gpt-4o", map[string]interface{}{}, true)
if len(params.Tools) != 1 {
t.Fatalf("len(Tools) = %d, want 1", len(params.Tools))
}
if params.Tools[0].OfWebSearch == nil {
t.Fatal("Tool should include built-in web_search")
}
if params.Tools[0].OfWebSearch.Type != responses.WebSearchToolTypeWebSearch {
t.Errorf("Web search tool type = %q, want %q", params.Tools[0].OfWebSearch.Type, responses.WebSearchToolTypeWebSearch)
}
}
func TestBuildCodexParams_WebSearchFunctionReplacedWithBuiltin(t *testing.T) {
tools := []ToolDefinition{
{
Type: "function",
Function: ToolFunctionDefinition{
Name: "web_search",
Description: "local web search",
Parameters: map[string]interface{}{
"type": "object",
},
},
},
{
Type: "function",
Function: ToolFunctionDefinition{
Name: "read_file",
Description: "read file",
Parameters: map[string]interface{}{
"type": "object",
},
},
},
}
params := buildCodexParams([]Message{{Role: "user", Content: "Hi"}}, tools, "gpt-4o", map[string]interface{}{}, true)
if len(params.Tools) != 2 {
t.Fatalf("len(Tools) = %d, want 2", len(params.Tools))
}
if params.Tools[0].OfFunction == nil || params.Tools[0].OfFunction.Name != "read_file" {
t.Fatalf("first tool should be function read_file, got %#v", params.Tools[0])
}
if params.Tools[1].OfWebSearch == nil {
t.Fatalf("second tool should be built-in web_search, got %#v", params.Tools[1])
}
}
func TestParseCodexResponse_TextOutput(t *testing.T) {
respJSON := `{
"id": "resp_test",
@ -214,6 +305,20 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
http.Error(w, "stream must be true", http.StatusBadRequest)
return
}
if _, ok := reqBody["max_output_tokens"]; ok {
http.Error(w, "max_output_tokens is not supported", http.StatusBadRequest)
return
}
toolsAny, ok := reqBody["tools"].([]interface{})
if !ok || len(toolsAny) != 1 {
http.Error(w, "missing default web search tool", http.StatusBadRequest)
return
}
toolObj, ok := toolsAny[0].(map[string]interface{})
if !ok || toolObj["type"] != "web_search" {
http.Error(w, "expected web_search tool", http.StatusBadRequest)
return
}
resp := map[string]interface{}{
"id": "resp_test",
@ -261,6 +366,64 @@ func TestCodexProvider_ChatRoundTrip(t *testing.T) {
}
}
func TestCodexProvider_ChatRoundTrip_WebSearchDisabled(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/responses" {
http.Error(w, "not found: "+r.URL.Path, http.StatusNotFound)
return
}
var reqBody map[string]interface{}
if err := json.NewDecoder(r.Body).Decode(&reqBody); err != nil {
http.Error(w, "invalid json", http.StatusBadRequest)
return
}
if _, ok := reqBody["tools"]; ok {
http.Error(w, "tools should be absent when web search disabled", http.StatusBadRequest)
return
}
resp := map[string]interface{}{
"id": "resp_test",
"object": "response",
"status": "completed",
"output": []map[string]interface{}{
{
"id": "msg_1",
"type": "message",
"role": "assistant",
"status": "completed",
"content": []map[string]interface{}{
{"type": "output_text", "text": "Hi from Codex!"},
},
},
},
"usage": map[string]interface{}{
"input_tokens": 4,
"output_tokens": 3,
"total_tokens": 7,
"input_tokens_details": map[string]interface{}{"cached_tokens": 0},
"output_tokens_details": map[string]interface{}{"reasoning_tokens": 0},
},
}
writeCompletedSSE(w, resp)
}))
defer server.Close()
provider := NewCodexProvider("test-token", "acc-123")
provider.enableWebSearch = false
provider.client = createOpenAITestClient(server.URL, "test-token", "acc-123")
messages := []Message{{Role: "user", Content: "Hello"}}
resp, err := provider.Chat(t.Context(), messages, nil, "gpt-4o", map[string]interface{}{})
if err != nil {
t.Fatalf("Chat() error: %v", err)
}
if resp.Content != "Hi from Codex!" {
t.Errorf("Content = %q, want %q", resp.Content, "Hi from Codex!")
}
}
func TestCodexProvider_ChatRoundTrip_TokenSourceFallbackAccountID(t *testing.T) {
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/responses" {
@ -293,6 +456,10 @@ func TestCodexProvider_ChatRoundTrip_TokenSourceFallbackAccountID(t *testing.T)
http.Error(w, "temperature is not supported", http.StatusBadRequest)
return
}
if _, ok := reqBody["max_output_tokens"]; ok {
http.Error(w, "max_output_tokens is not supported", http.StatusBadRequest)
return
}
if reqBody["stream"] != true {
http.Error(w, "stream must be true", http.StatusBadRequest)
return

View file

@ -232,7 +232,7 @@ func createClaudeAuthProvider() (LLMProvider, error) {
return NewClaudeProviderWithTokenSource(cred.AccessToken, createClaudeTokenSource()), nil
}
func createCodexAuthProvider() (LLMProvider, error) {
func createCodexAuthProvider(enableWebSearch bool) (LLMProvider, error) {
cred, err := auth.GetCredential("openai")
if err != nil {
return nil, fmt.Errorf("loading auth credentials: %w", err)
@ -240,7 +240,9 @@ func createCodexAuthProvider() (LLMProvider, error) {
if cred == nil {
return nil, fmt.Errorf("no credentials for openai. Run: picoclaw auth login --provider openai")
}
return NewCodexProviderWithTokenSource(cred.AccessToken, cred.AccountID, createCodexTokenSource()), nil
p := NewCodexProviderWithTokenSource(cred.AccessToken, cred.AccountID, createCodexTokenSource())
p.enableWebSearch = enableWebSearch
return p, nil
}
func CreateProvider(cfg *config.Config) (LLMProvider, error) {
@ -265,10 +267,12 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
case "openai", "gpt":
if cfg.Providers.OpenAI.APIKey != "" || cfg.Providers.OpenAI.AuthMethod != "" {
if cfg.Providers.OpenAI.AuthMethod == "codex-cli" {
return NewCodexProviderWithTokenSource("", "", CreateCodexCliTokenSource()), nil
c := NewCodexProviderWithTokenSource("", "", CreateCodexCliTokenSource())
c.enableWebSearch = cfg.Providers.OpenAI.WebSearch
return c, nil
}
if cfg.Providers.OpenAI.AuthMethod == "oauth" || cfg.Providers.OpenAI.AuthMethod == "token" {
return createCodexAuthProvider()
return createCodexAuthProvider(cfg.Providers.OpenAI.WebSearch)
}
apiKey = cfg.Providers.OpenAI.APIKey
apiBase = cfg.Providers.OpenAI.APIBase
@ -393,7 +397,7 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
case (strings.Contains(lowerModel, "gpt") || strings.HasPrefix(model, "openai/")) && (cfg.Providers.OpenAI.APIKey != "" || cfg.Providers.OpenAI.AuthMethod != ""):
if cfg.Providers.OpenAI.AuthMethod == "oauth" || cfg.Providers.OpenAI.AuthMethod == "token" {
return createCodexAuthProvider()
return createCodexAuthProvider(cfg.Providers.OpenAI.WebSearch)
}
apiKey = cfg.Providers.OpenAI.APIKey
apiBase = cfg.Providers.OpenAI.APIBase

View file

@ -7,6 +7,7 @@ import (
"time"
"github.com/sipeed/picoclaw/pkg/bus"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/cron"
"github.com/sipeed/picoclaw/pkg/utils"
)
@ -28,12 +29,15 @@ type CronTool struct {
}
// NewCronTool creates a new CronTool
func NewCronTool(cronService *cron.CronService, executor JobExecutor, msgBus *bus.MessageBus, workspace string, restrict bool) *CronTool {
// execTimeout: 0 means no timeout, >0 sets the timeout duration
func NewCronTool(cronService *cron.CronService, executor JobExecutor, msgBus *bus.MessageBus, workspace string, restrict bool, execTimeout time.Duration, config *config.Config) *CronTool {
execTool := NewExecToolWithConfig(workspace, restrict, config)
execTool.SetTimeout(execTimeout)
return &CronTool{
cronService: cronService,
executor: executor,
msgBus: msgBus,
execTool: NewExecTool(workspace, restrict),
execTool: execTool,
}
}

View file

@ -4,6 +4,7 @@ import (
"bytes"
"context"
"fmt"
"github.com/sipeed/picoclaw/pkg/config"
"os"
"os/exec"
"path/filepath"
@ -21,16 +22,82 @@ type ExecTool struct {
restrictToWorkspace bool
}
var defaultDenyPatterns = []*regexp.Regexp{
regexp.MustCompile(`\brm\s+-[rf]{1,2}\b`),
regexp.MustCompile(`\bdel\s+/[fq]\b`),
regexp.MustCompile(`\brmdir\s+/s\b`),
regexp.MustCompile(`\b(format|mkfs|diskpart)\b\s`), // Match disk wiping commands (must be followed by space/args)
regexp.MustCompile(`\bdd\s+if=`),
regexp.MustCompile(`>\s*/dev/sd[a-z]\b`), // Block writes to disk devices (but allow /dev/null)
regexp.MustCompile(`\b(shutdown|reboot|poweroff)\b`),
regexp.MustCompile(`:\(\)\s*\{.*\};\s*:`),
regexp.MustCompile(`\$\([^)]+\)`),
regexp.MustCompile(`\$\{[^}]+\}`),
regexp.MustCompile("`[^`]+`"),
regexp.MustCompile(`\|\s*sh\b`),
regexp.MustCompile(`\|\s*bash\b`),
regexp.MustCompile(`;\s*rm\s+-[rf]`),
regexp.MustCompile(`&&\s*rm\s+-[rf]`),
regexp.MustCompile(`\|\|\s*rm\s+-[rf]`),
regexp.MustCompile(`>\s*/dev/null\s*>&?\s*\d?`),
regexp.MustCompile(`<<\s*EOF`),
regexp.MustCompile(`\$\(\s*cat\s+`),
regexp.MustCompile(`\$\(\s*curl\s+`),
regexp.MustCompile(`\$\(\s*wget\s+`),
regexp.MustCompile(`\$\(\s*which\s+`),
regexp.MustCompile(`\bsudo\b`),
regexp.MustCompile(`\bchmod\s+[0-7]{3,4}\b`),
regexp.MustCompile(`\bchown\b`),
regexp.MustCompile(`\bpkill\b`),
regexp.MustCompile(`\bkillall\b`),
regexp.MustCompile(`\bkill\s+-[9]\b`),
regexp.MustCompile(`\bcurl\b.*\|\s*(sh|bash)`),
regexp.MustCompile(`\bwget\b.*\|\s*(sh|bash)`),
regexp.MustCompile(`\bnpm\s+install\s+-g\b`),
regexp.MustCompile(`\bpip\s+install\s+--user\b`),
regexp.MustCompile(`\bapt\s+(install|remove|purge)\b`),
regexp.MustCompile(`\byum\s+(install|remove)\b`),
regexp.MustCompile(`\bdnf\s+(install|remove)\b`),
regexp.MustCompile(`\bdocker\s+run\b`),
regexp.MustCompile(`\bdocker\s+exec\b`),
regexp.MustCompile(`\bgit\s+push\b`),
regexp.MustCompile(`\bgit\s+force\b`),
regexp.MustCompile(`\bssh\b.*@`),
regexp.MustCompile(`\beval\b`),
regexp.MustCompile(`\bsource\s+.*\.sh\b`),
}
func NewExecTool(workingDir string, restrict bool) *ExecTool {
denyPatterns := []*regexp.Regexp{
regexp.MustCompile(`\brm\s+-[rf]{1,2}\b`),
regexp.MustCompile(`\bdel\s+/[fq]\b`),
regexp.MustCompile(`\brmdir\s+/s\b`),
regexp.MustCompile(`\b(format|mkfs|diskpart)\b\s`), // Match disk wiping commands (must be followed by space/args)
regexp.MustCompile(`\bdd\s+if=`),
regexp.MustCompile(`>\s*/dev/sd[a-z]\b`), // Block writes to disk devices (but allow /dev/null)
regexp.MustCompile(`\b(shutdown|reboot|poweroff)\b`),
regexp.MustCompile(`:\(\)\s*\{.*\};\s*:`),
return NewExecToolWithConfig(workingDir, restrict, nil)
}
func NewExecToolWithConfig(workingDir string, restrict bool, config *config.Config) *ExecTool {
denyPatterns := make([]*regexp.Regexp, 0)
enableDenyPatterns := true
if config != nil {
execConfig := config.Tools.Exec
enableDenyPatterns = execConfig.EnableDenyPatterns
if enableDenyPatterns {
if len(execConfig.CustomDenyPatterns) > 0 {
fmt.Printf("Using custom deny patterns: %v\n", execConfig.CustomDenyPatterns)
for _, pattern := range execConfig.CustomDenyPatterns {
re, err := regexp.Compile(pattern)
if err != nil {
fmt.Printf("Invalid custom deny pattern %q: %v\n", pattern, err)
continue
}
denyPatterns = append(denyPatterns, re)
}
} else {
denyPatterns = append(denyPatterns, defaultDenyPatterns...)
}
} else {
// If deny patterns are disabled, we won't add any patterns, allowing all commands.
fmt.Println("Warning: deny patterns are disabled. All commands will be allowed.")
}
} else {
denyPatterns = append(denyPatterns, defaultDenyPatterns...)
}
return &ExecTool{
@ -89,7 +156,14 @@ func (t *ExecTool) Execute(ctx context.Context, args map[string]interface{}) *To
return ErrorResult(guardError)
}
cmdCtx, cancel := context.WithTimeout(ctx, t.timeout)
// timeout == 0 means no timeout
var cmdCtx context.Context
var cancel context.CancelFunc
if t.timeout > 0 {
cmdCtx, cancel = context.WithTimeout(ctx, t.timeout)
} else {
cmdCtx, cancel = context.WithCancel(ctx)
}
defer cancel()
var cmd *exec.Cmd

View file

@ -176,6 +176,71 @@ func stripTags(content string) string {
return re.ReplaceAllString(content, "")
}
type PerplexitySearchProvider struct {
apiKey string
}
func (p *PerplexitySearchProvider) Search(ctx context.Context, query string, count int) (string, error) {
searchURL := "https://api.perplexity.ai/chat/completions"
payload := map[string]interface{}{
"model": "sonar",
"messages": []map[string]string{
{"role": "system", "content": "You are a search assistant. Provide concise search results with titles, URLs, and brief descriptions in the following format:\n1. Title\n URL\n Description\n\nDo not add extra commentary."},
{"role": "user", "content": fmt.Sprintf("Search for: %s. Provide up to %d relevant results.", query, count)},
},
"max_tokens": 1000,
}
payloadBytes, err := json.Marshal(payload)
if err != nil {
return "", fmt.Errorf("failed to marshal request: %w", err)
}
req, err := http.NewRequestWithContext(ctx, "POST", searchURL, strings.NewReader(string(payloadBytes)))
if err != nil {
return "", fmt.Errorf("failed to create request: %w", err)
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Authorization", "Bearer "+p.apiKey)
req.Header.Set("User-Agent", userAgent)
client := &http.Client{Timeout: 30 * time.Second}
resp, err := client.Do(req)
if err != nil {
return "", fmt.Errorf("request failed: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return "", fmt.Errorf("failed to read response: %w", err)
}
if resp.StatusCode != http.StatusOK {
return "", fmt.Errorf("Perplexity API error: %s", string(body))
}
var searchResp struct {
Choices []struct {
Message struct {
Content string `json:"content"`
} `json:"message"`
} `json:"choices"`
}
if err := json.Unmarshal(body, &searchResp); err != nil {
return "", fmt.Errorf("failed to parse response: %w", err)
}
if len(searchResp.Choices) == 0 {
return fmt.Sprintf("No results for: %s", query), nil
}
return fmt.Sprintf("Results for: %s (via Perplexity)\n%s", query, searchResp.Choices[0].Message.Content), nil
}
type WebSearchTool struct {
provider SearchProvider
maxResults int
@ -187,14 +252,22 @@ type WebSearchToolOptions struct {
BraveEnabled bool
DuckDuckGoMaxResults int
DuckDuckGoEnabled bool
PerplexityAPIKey string
PerplexityMaxResults int
PerplexityEnabled bool
}
func NewWebSearchTool(opts WebSearchToolOptions) *WebSearchTool {
var provider SearchProvider
maxResults := 5
// Priority: Brave > DuckDuckGo
if opts.BraveEnabled && opts.BraveAPIKey != "" {
// Priority: Perplexity > Brave > DuckDuckGo
if opts.PerplexityEnabled && opts.PerplexityAPIKey != "" {
provider = &PerplexitySearchProvider{apiKey: opts.PerplexityAPIKey}
if opts.PerplexityMaxResults > 0 {
maxResults = opts.PerplexityMaxResults
}
} else if opts.BraveEnabled && opts.BraveAPIKey != "" {
provider = &BraveSearchProvider{apiKey: opts.BraveAPIKey}
if opts.BraveMaxResults > 0 {
maxResults = opts.BraveMaxResults