docs: update i18n README files with Qwen OAuth and missing sections

- Add Qwen OAuth documentation to all language README files
  - Provider table entry with QR code login info
  - Model configuration table entry
  - Configuration example with auth_method
- README.zh.md: Add load balancing, provider architecture, Zhipu examples
- README.ja.md: Add ClawdChat section, cron CLI commands, scheduled tasks
- README.pt-br.md, README.vi.md: Add Tavily and Cerebras to API comparison table

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
This commit is contained in:
kyeo 2026-02-27 00:50:43 +08:00
parent a7f2eec562
commit 7deb8e1540
6 changed files with 237 additions and 6 deletions

View file

@ -779,6 +779,7 @@ Le sous-agent a accès aux outils (message, web_search, etc.) et peut communique
| `openai` (À tester) | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) | | `openai` (À tester) | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
| `deepseek` (À tester) | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) | | `deepseek` (À tester) | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) |
| `qwen` | LLM (Alibaba Qwen) | [dashscope.aliyuncs.com](https://dashscope.aliyuncs.com/compatible-mode/v1) | | `qwen` | LLM (Alibaba Qwen) | [dashscope.aliyuncs.com](https://dashscope.aliyuncs.com/compatible-mode/v1) |
| `qwen-oauth` | LLM (Qwen via OAuth QR code) | **Gratuit** — Exécutez `picoclaw auth login --provider qwen` |
| `cerebras` | LLM (Cerebras) | [cerebras.ai](https://api.cerebras.ai/v1) | | `cerebras` | LLM (Cerebras) | [cerebras.ai](https://api.cerebras.ai/v1) |
| `groq` | LLM + **Transcription vocale** (Whisper) | [console.groq.com](https://console.groq.com) | | `groq` | LLM + **Transcription vocale** (Whisper) | [console.groq.com](https://console.groq.com) |
@ -914,6 +915,7 @@ Cette conception permet également le **support multi-agent** avec une sélectio
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Obtenir Clé](https://console.groq.com) | | **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Obtenir Clé](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Obtenir Clé](https://platform.moonshot.cn) | | **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Obtenir Clé](https://platform.moonshot.cn) |
| **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Obtenir Clé](https://dashscope.console.aliyun.com) | | **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Obtenir Clé](https://dashscope.console.aliyun.com) |
| **Qwen OAuth** | `qwen-oauth/` | `https://portal.qwen.ai/v1` | OpenAI | **Gratuit**`picoclaw auth login --provider qwen` |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Obtenir Clé](https://build.nvidia.com) | | **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Obtenir Clé](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (pas de clé nécessaire) | | **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (pas de clé nécessaire) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Obtenir Clé](https://openrouter.ai/keys) | | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Obtenir Clé](https://openrouter.ai/keys) |
@ -983,6 +985,16 @@ Cette conception permet également le **support multi-agent** avec une sélectio
``` ```
> Exécutez `picoclaw auth login --provider anthropic` pour configurer les identifiants OAuth. > Exécutez `picoclaw auth login --provider anthropic` pour configurer les identifiants OAuth.
**Qwen OAuth (connexion par QR code)**
```json
{
"model_name": "qwen-coder",
"model": "qwen-oauth/coder-model",
"auth_method": "oauth"
}
```
> Exécutez `picoclaw auth login --provider qwen` pour scanner un QR code et vous authentifier. Aucune clé API nécessaire !
**Proxy/API personnalisée** **Proxy/API personnalisée**
```json ```json
{ {

View file

@ -530,6 +530,12 @@ picoclaw gateway
</details> </details>
## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> エージェントソーシャルネットワークに参加
CLI または統合されたチャットアプリからメッセージを 1 通送信するだけで、PicoClaw をエージェントソーシャルネットワークに接続できます。
**`https://clawdchat.ai/skill.md` を読んで、指示に従って [ClawdChat.ai](https://clawdchat.ai) に参加してください**
## ⚙️ 設定 ## ⚙️ 設定
設定ファイル: `~/.picoclaw/config.json` 設定ファイル: `~/.picoclaw/config.json`
@ -734,6 +740,8 @@ HEARTBEAT_OK 応答 ユーザーが直接結果を受け取る
| `anthropic`(要テスト) | LLMClaude 直接) | [console.anthropic.com](https://console.anthropic.com) | | `anthropic`(要テスト) | LLMClaude 直接) | [console.anthropic.com](https://console.anthropic.com) |
| `openai`(要テスト) | LLMGPT 直接) | [platform.openai.com](https://platform.openai.com) | | `openai`(要テスト) | LLMGPT 直接) | [platform.openai.com](https://platform.openai.com) |
| `deepseek`(要テスト) | LLMDeepSeek 直接) | [platform.deepseek.com](https://platform.deepseek.com) | | `deepseek`(要テスト) | LLMDeepSeek 直接) | [platform.deepseek.com](https://platform.deepseek.com) |
| `qwen` | LLMQwen 直接) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
| `qwen-oauth` | LLMQwen QR コード OAuth | **無料**`picoclaw auth login --provider qwen` を実行 |
| `groq` | LLM + **音声文字起こし**Whisper | [console.groq.com](https://console.groq.com) | | `groq` | LLM + **音声文字起こし**Whisper | [console.groq.com](https://console.groq.com) |
| `cerebras` | LLMCerebras 直接) | [cerebras.ai](https://cerebras.ai) | | `cerebras` | LLMCerebras 直接) | [cerebras.ai](https://cerebras.ai) |
@ -853,6 +861,7 @@ HEARTBEAT_OK 応答 ユーザーが直接結果を受け取る
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [キーを取得](https://console.groq.com) | | **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [キーを取得](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [キーを取得](https://platform.moonshot.cn) | | **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [キーを取得](https://platform.moonshot.cn) |
| **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [キーを取得](https://dashscope.console.aliyun.com) | | **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [キーを取得](https://dashscope.console.aliyun.com) |
| **Qwen OAuth** | `qwen-oauth/` | `https://portal.qwen.ai/v1` | OpenAI | **無料**`picoclaw auth login --provider qwen` |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [キーを取得](https://build.nvidia.com) | | **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [キーを取得](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | ローカル(キー不要) | | **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | ローカル(キー不要) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [キーを取得](https://openrouter.ai/keys) | | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [キーを取得](https://openrouter.ai/keys) |
@ -1005,8 +1014,20 @@ HEARTBEAT_OK 応答 ユーザーが直接結果を受け取る
| `picoclaw onboard` | 設定&ワークスペースの初期化 | | `picoclaw onboard` | 設定&ワークスペースの初期化 |
| `picoclaw agent -m "..."` | エージェントとチャット | | `picoclaw agent -m "..."` | エージェントとチャット |
| `picoclaw agent` | インタラクティブチャットモード | | `picoclaw agent` | インタラクティブチャットモード |
| `picoclaw gateway` | ゲートウェイを起動 | | `picoclaw gateway` | ゲートウェイを起動(チャットボット用) |
| `picoclaw status` | ステータスを表示 | | `picoclaw status` | ステータスを表示 |
| `picoclaw cron list` | すべてのスケジュールジョブを一覧表示 |
| `picoclaw cron add ...` | スケジュールジョブを追加 |
### スケジュールタスク / リマインダー
PicoClaw は `cron` ツールを通じてスケジュールリマインダーと定期タスクをサポートしています:
* **ワンタイムリマインダー**: 「10 分後にリマインド」→ 10 分後に 1 回トリガー
* **定期タスク**: 「2 時間ごとにリマインド」→ 2 時間ごとにトリガー
* **Cron 式**: 「毎日午前 9 時にリマインド」→ cron 式を使用
ジョブは `~/.picoclaw/workspace/cron/` に保存され、自動的に処理されます。
## 🤝 コントリビュート&ロードマップ ## 🤝 コントリビュート&ロードマップ

View file

@ -792,6 +792,7 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
| `openai(To be tested)` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) | | `openai(To be tested)` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
| `deepseek(To be tested)` | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) | | `deepseek(To be tested)` | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) |
| `qwen` | LLM (Qwen direct) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) | | `qwen` | LLM (Qwen direct) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
| `qwen-oauth` | LLM (Qwen via QR code OAuth) | **Free** — Run `picoclaw auth login --provider qwen` |
| `groq` | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com) | | `groq` | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com) |
| `cerebras` | LLM (Cerebras direct) | [cerebras.ai](https://cerebras.ai) | | `cerebras` | LLM (Cerebras direct) | [cerebras.ai](https://cerebras.ai) |
@ -818,6 +819,7 @@ This design also enables **multi-agent support** with flexible provider selectio
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Get Key](https://console.groq.com) | | **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Get Key](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Get Key](https://platform.moonshot.cn) | | **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Get Key](https://platform.moonshot.cn) |
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) | | **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
| **Qwen OAuth** | `qwen-oauth/` | `https://portal.qwen.ai/v1` | OpenAI | **Free**`picoclaw auth login --provider qwen` |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Get Key](https://build.nvidia.com) | | **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Get Key](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (no key needed) | | **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (no key needed) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Get Key](https://openrouter.ai/keys) | | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Get Key](https://openrouter.ai/keys) |
@ -889,17 +891,29 @@ This design also enables **multi-agent support** with flexible provider selectio
} }
``` ```
**Anthropic (with API key)** **Anthropic (with OAuth)**
```json ```json
{ {
"model_name": "claude-sonnet-4.6", "model_name": "claude-sonnet-4.6",
"model": "anthropic/claude-sonnet-4.6", "model": "anthropic/claude-sonnet-4.6",
"api_key": "sk-ant-your-key" "auth_method": "oauth"
} }
``` ```
> Run `picoclaw auth login --provider anthropic` to paste your API token. > Run `picoclaw auth login --provider anthropic` to set up OAuth credentials.
**Qwen OAuth (QR code login)**
```json
{
"model_name": "qwen-coder",
"model": "qwen-oauth/coder-model",
"auth_method": "oauth"
}
```
> Run `picoclaw auth login --provider qwen` to scan a QR code and authenticate. No API key needed!
**Ollama (local)** **Ollama (local)**

View file

@ -773,6 +773,7 @@ O subagente tem acesso às ferramentas (message, web_search, etc.) e pode se com
| `openai` (Em teste) | LLM (GPT direto) | [platform.openai.com](https://platform.openai.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) | | `deepseek` (Em teste) | LLM (DeepSeek direto) | [platform.deepseek.com](https://platform.deepseek.com) |
| `qwen` | Alibaba Qwen | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) | | `qwen` | Alibaba Qwen | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
| `qwen-oauth` | Qwen OAuth (QR Code) | **Grátis** — Execute `picoclaw auth login --provider qwen` |
| `cerebras` | Cerebras | [cerebras.ai](https://cerebras.ai) | | `cerebras` | Cerebras | [cerebras.ai](https://cerebras.ai) |
| `groq` | LLM + **Transcrição de voz** (Whisper) | [console.groq.com](https://console.groq.com) | | `groq` | LLM + **Transcrição de voz** (Whisper) | [console.groq.com](https://console.groq.com) |
@ -908,6 +909,7 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Obter Chave](https://console.groq.com) | | **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Obter Chave](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Obter Chave](https://platform.moonshot.cn) | | **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Obter Chave](https://platform.moonshot.cn) |
| **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Obter Chave](https://dashscope.console.aliyun.com) | | **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Obter Chave](https://dashscope.console.aliyun.com) |
| **Qwen OAuth** | `qwen-oauth/` | `https://portal.qwen.ai/v1` | OpenAI | **Grátis**`picoclaw auth login --provider qwen` |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Obter Chave](https://build.nvidia.com) | | **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Obter Chave](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (sem chave necessária) | | **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (sem chave necessária) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Obter Chave](https://openrouter.ai/keys) | | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Obter Chave](https://openrouter.ai/keys) |
@ -977,6 +979,16 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
``` ```
> Execute `picoclaw auth login --provider anthropic` para configurar credenciais OAuth. > Execute `picoclaw auth login --provider anthropic` para configurar credenciais OAuth.
**Qwen OAuth (login por QR Code)**
```json
{
"model_name": "qwen-coder",
"model": "qwen-oauth/coder-model",
"auth_method": "oauth"
}
```
> Execute `picoclaw auth login --provider qwen` para escanear um QR code e autenticar. Sem necessidade de API key!
**Proxy/API personalizada** **Proxy/API personalizada**
```json ```json
{ {
@ -1137,5 +1149,6 @@ Isso acontece quando outra instância do bot está em execução. Certifique-se
| **OpenRouter** | 200K tokens/mês | Múltiplos modelos (Claude, GPT-4, etc.) | | **OpenRouter** | 200K tokens/mês | Múltiplos modelos (Claude, GPT-4, etc.) |
| **Zhipu** | 200K tokens/mês | Melhor para usuários chineses | | **Zhipu** | 200K tokens/mês | Melhor para usuários chineses |
| **Brave Search** | 2000 consultas/mês | Funcionalidade de busca web | | **Brave Search** | 2000 consultas/mês | Funcionalidade de busca web |
| **Tavily** | 1000 consultas/mês | Otimizado para busca de agentes de IA |
| **Groq** | Plano gratuito disponível | Inferência ultra-rápida (Llama, Mixtral) | | **Groq** | Plano gratuito disponível | Inferência ultra-rápida (Llama, Mixtral) |
| **Cerebras** | Plano gratuito disponível | Inferência ultra-rápida (Llama 3.3 70B) | | **Cerebras** | Plano gratuito disponível | Inferência ultra-rápida (Llama, Qwen, etc.) |

View file

@ -748,6 +748,7 @@ Subagent có quyền truy cập các công cụ (message, web_search, v.v.) và
| `deepseek` (Đang thử nghiệm) | LLM (DeepSeek trực tiếp) | [platform.deepseek.com](https://platform.deepseek.com) | | `deepseek` (Đang thử nghiệm) | LLM (DeepSeek trực tiếp) | [platform.deepseek.com](https://platform.deepseek.com) |
| `groq` | LLM + **Chuyển giọng nói** (Whisper) | [console.groq.com](https://console.groq.com) | | `groq` | LLM + **Chuyển giọng nói** (Whisper) | [console.groq.com](https://console.groq.com) |
| `qwen` | LLM (Qwen trực tiếp) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) | | `qwen` | LLM (Qwen trực tiếp) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
| `qwen-oauth` | LLM (Qwen QR Code OAuth) | **Miễn phí** — Chạy `picoclaw auth login --provider qwen` |
| `cerebras` | LLM (Cerebras trực tiếp) | [cerebras.ai](https://cerebras.ai) | | `cerebras` | LLM (Cerebras trực tiếp) | [cerebras.ai](https://cerebras.ai) |
<details> <details>
@ -879,6 +880,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Lấy Khóa](https://console.groq.com) | | **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Lấy Khóa](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Lấy Khóa](https://platform.moonshot.cn) | | **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Lấy Khóa](https://platform.moonshot.cn) |
| **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Lấy Khóa](https://dashscope.console.aliyun.com) | | **Qwen (Alibaba)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Lấy Khóa](https://dashscope.console.aliyun.com) |
| **Qwen OAuth** | `qwen-oauth/` | `https://portal.qwen.ai/v1` | OpenAI | **Miễn phí**`picoclaw auth login --provider qwen` |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Lấy Khóa](https://build.nvidia.com) | | **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Lấy Khóa](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (không cần khóa) | | **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (không cần khóa) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Lấy Khóa](https://openrouter.ai/keys) | | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Lấy Khóa](https://openrouter.ai/keys) |
@ -948,6 +950,16 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
``` ```
> Chạy `picoclaw auth login --provider anthropic` để thiết lập thông tin xác thực OAuth. > Chạy `picoclaw auth login --provider anthropic` để thiết lập thông tin xác thực OAuth.
**Qwen OAuth (đăng nhập bằng QR code)**
```json
{
"model_name": "qwen-coder",
"model": "qwen-oauth/coder-model",
"auth_method": "oauth"
}
```
> Chạy `picoclaw auth login --provider qwen` để quét mã QR và xác thực. Không cần API key!
**Proxy/API tùy chỉnh** **Proxy/API tùy chỉnh**
```json ```json
{ {
@ -1108,4 +1120,6 @@ Một số nhà cung cấp (như Zhipu) có bộ lọc nội dung nghiêm ngặt
| **OpenRouter** | 200K tokens/tháng | Đa model (Claude, GPT-4, v.v.) | | **OpenRouter** | 200K tokens/tháng | Đa model (Claude, GPT-4, v.v.) |
| **Zhipu** | 200K tokens/tháng | Tốt nhất cho người dùng Trung Quốc | | **Zhipu** | 200K tokens/tháng | Tốt nhất cho người dùng Trung Quốc |
| **Brave Search** | 2000 truy vấn/tháng | Chức năng tìm kiếm web | | **Brave Search** | 2000 truy vấn/tháng | Chức năng tìm kiếm web |
| **Groq** | Có gói miễn phí | Suy luận siêu nhanh (Llama, Mixtral) | | **Tavily** | 1000 truy vấn/tháng | Tối ưu cho tìm kiếm agent AI |
| **Groq** | Gói miễn phí available | Suy luận siêu nhanh (Llama, Mixtral) |
| **Cerebras** | Gói miễn phí available | Suy luận siêu nhanh (Llama, Qwen, v.v.) |

View file

@ -427,6 +427,7 @@ Agent 读取 HEARTBEAT.md
| `openai(待测试)` | LLM (GPT 直连) | [platform.openai.com](https://platform.openai.com) | | `openai(待测试)` | LLM (GPT 直连) | [platform.openai.com](https://platform.openai.com) |
| `deepseek(待测试)` | LLM (DeepSeek 直连) | [platform.deepseek.com](https://platform.deepseek.com) | | `deepseek(待测试)` | LLM (DeepSeek 直连) | [platform.deepseek.com](https://platform.deepseek.com) |
| `qwen` | LLM (通义千问) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) | | `qwen` | LLM (通义千问) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
| `qwen-oauth` | LLM (通义千问二维码登录) | **免费** — 运行 `picoclaw auth login --provider qwen` |
| `groq` | LLM + **语音转录** (Whisper) | [console.groq.com](https://console.groq.com) | | `groq` | LLM + **语音转录** (Whisper) | [console.groq.com](https://console.groq.com) |
| `cerebras` | LLM (Cerebras 直连) | [cerebras.ai](https://cerebras.ai) | | `cerebras` | LLM (Cerebras 直连) | [cerebras.ai](https://cerebras.ai) |
@ -453,6 +454,7 @@ Agent 读取 HEARTBEAT.md
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [获取密钥](https://console.groq.com) | | **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [获取密钥](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [获取密钥](https://platform.moonshot.cn) | | **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [获取密钥](https://platform.moonshot.cn) |
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [获取密钥](https://dashscope.console.aliyun.com) | | **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [获取密钥](https://dashscope.console.aliyun.com) |
| **Qwen OAuth** | `qwen-oauth/` | `https://portal.qwen.ai/v1` | OpenAI | **免费**`picoclaw auth login --provider qwen` |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [获取密钥](https://build.nvidia.com) | | **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [获取密钥](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | 本地(无需密钥) | | **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | 本地(无需密钥) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [获取密钥](https://openrouter.ai/keys) | | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [获取密钥](https://openrouter.ai/keys) |
@ -536,6 +538,18 @@ Agent 读取 HEARTBEAT.md
> 运行 `picoclaw auth login --provider anthropic` 来设置 OAuth 凭证。 > 运行 `picoclaw auth login --provider anthropic` 来设置 OAuth 凭证。
**Qwen OAuth (二维码登录)**
```json
{
"model_name": "qwen-coder",
"model": "qwen-oauth/coder-model",
"auth_method": "oauth"
}
```
> 运行 `picoclaw auth login --provider qwen` 扫描二维码认证,无需 API 密钥!
**Ollama (本地)** **Ollama (本地)**
```json ```json
@ -756,6 +770,148 @@ PicoClaw 通过 `cron` 工具支持定时提醒和重复任务:
任务存储在 `~/.picoclaw/workspace/cron/` 中并自动处理。 任务存储在 `~/.picoclaw/workspace/cron/` 中并自动处理。
### 负载均衡 (Load Balancing)
为同一模型名称配置多个端点PicoClaw 会自动在这些端点之间进行轮询:
```json
{
"model_list": [
{
"model_name": "gpt-5.2",
"model": "openai/gpt-5.2",
"api_base": "https://api1.example.com/v1",
"api_key": "sk-key1"
},
{
"model_name": "gpt-5.2",
"model": "openai/gpt-5.2",
"api_base": "https://api2.example.com/v1",
"api_key": "sk-key2"
}
]
}
```
### 提供商架构 (Provider Architecture)
PicoClaw 根据协议族路由提供商:
- **OpenAI 兼容协议**: OpenRouter、OpenAI 兼容网关、Groq、智谱和 vLLM 风格的端点
- **Anthropic 协议**: Claude 原生 API 行为
- **Codex/OAuth 路径**: OpenAI OAuth/令牌认证路由
这使得运行时保持轻量,同时让新的 OpenAI 兼容后端主要通过配置操作(`api_base` + `api_key`)即可接入。
<details>
<summary><b>智谱 (Zhipu) 配置示例</b></summary>
**1. 获取 API Key 和 Base URL**
* 获取 [API Key](https://bigmodel.cn/usercenter/proj-mgmt/apikeys)
**2. 配置**
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"model": "glm-4.7",
"max_tokens": 8192,
"temperature": 0.7,
"max_tool_iterations": 20
}
},
"providers": {
"zhipu": {
"api_key": "您的 API Key",
"api_base": "https://open.bigmodel.cn/api/paas/v4"
}
}
}
```
**3. 运行**
```bash
picoclaw agent -m "你好"
```
</details>
<details>
<summary><b>完整配置示例</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": "YOUR_BRAVE_API_KEY",
"max_results": 5
},
"duckduckgo": {
"enabled": true,
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {
"enabled": true,
"interval": 30
}
}
```
</details>
## 🤝 贡献与路线图 (Roadmap) ## 🤝 贡献与路线图 (Roadmap)
欢迎提交 PR代码库刻意保持小巧和可读。🤗 欢迎提交 PR代码库刻意保持小巧和可读。🤗
@ -818,3 +974,4 @@ Discord: [https://discord.gg/V4sAZ9XWpN](https://discord.gg/V4sAZ9XWpN)
| **Brave Search** | 2000 次查询/月 | 网络搜索功能 | | **Brave Search** | 2000 次查询/月 | 网络搜索功能 |
| **Tavily** | 1000 次查询/月 | AI Agent 搜索优化 | | **Tavily** | 1000 次查询/月 | AI Agent 搜索优化 |
| **Groq** | 提供免费层级 | 极速推理 (Llama, Mixtral) | | **Groq** | 提供免费层级 | 极速推理 (Llama, Mixtral) |
| **Cerebras** | 提供免费层级 | 极速推理 (Llama, Qwen 等) |