mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-05-25 16:00:35 +00:00
docs: update documentation for Gemini native protocol (#2601)
* docs: update documentation for Gemini native protocol * docs: fix capitalization and grammar of Gemini
This commit is contained in:
LC
@@ -154,7 +154,7 @@ Identify protocol via prefix in `model` field:
|
||||
| `openai/` | OpenAI-compatible | Most common, includes DeepSeek, Qwen, Groq, etc. |
|
||||
| `anthropic/` | Anthropic | Claude series specific |
|
||||
| `antigravity/` | Antigravity | Google Cloud Code Assist |
|
||||
| `gemini/` | Gemini | Google Gemini native API (if needed) |
|
||||
| `gemini/` | Gemini | Google Gemini native API |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -339,7 +339,7 @@ Répond HEARTBEAT_OK Utilisateur reçoit le résultat
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Obtenir](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Obtenir](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Obtenir](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Obtenir](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Obtenir](https://aistudio.google.com/api-keys) |
|
||||
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Obtenir](https://console.groq.com) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Obtenir](https://dashscope.console.aliyun.com) |
|
||||
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (pas de clé) |
|
||||
@@ -369,9 +369,12 @@ L'ancienne configuration `providers` est **dépréciée** et a été supprimée
|
||||
PicoClaw route les providers par famille de protocole :
|
||||
|
||||
- **Compatible OpenAI** : OpenRouter, Groq, Zhipu, endpoints vLLM et la plupart des autres.
|
||||
- **Gemini natif** : Google Gemini via les endpoints natifs `models/*:generateContent` et `models/*:streamGenerateContent`.
|
||||
- **Anthropic** : Comportement natif de l'API Claude.
|
||||
- **Codex/OAuth** : Route d'authentification OAuth/token OpenAI.
|
||||
|
||||
Cela maintient le runtime léger tout en faisant des nouveaux backends compatibles OpenAI principalement une opération de configuration (`api_base` + `api_keys`).
|
||||
|
||||
### Tâches Planifiées / Rappels
|
||||
|
||||
PicoClaw supporte les tâches planifiées via l'outil `cron`. L'agent peut définir, lister et annuler des rappels ou tâches récurrentes.
|
||||
|
||||
@@ -340,7 +340,7 @@ HEARTBEAT_OK を返信 ユーザーが直接結果を受信
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [取得](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [取得](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [取得](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [取得](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [取得](https://aistudio.google.com/api-keys) |
|
||||
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [取得](https://console.groq.com) |
|
||||
| **通義千問 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [取得](https://dashscope.console.aliyun.com) |
|
||||
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | ローカル（キー不要） |
|
||||
@@ -370,9 +370,12 @@ HEARTBEAT_OK を返信 ユーザーが直接結果を受信
|
||||
PicoClaw はプロトコルファミリーで Provider をルーティングします：
|
||||
|
||||
- **OpenAI 互換**：OpenRouter、Groq、Zhipu、vLLM スタイルのエンドポイントなど。
|
||||
- **Gemini ネイティブ**：Google Gemini のネイティブ `models/*:generateContent` / `models/*:streamGenerateContent` エンドポイント。
|
||||
- **Anthropic**：Claude ネイティブ API の動作。
|
||||
- **Codex/OAuth**：OpenAI OAuth/トークン認証ルート。
|
||||
|
||||
これによりランタイムを軽量に保ちつつ、新しい OpenAI 互換バックエンドの追加をほぼ設定操作（`api_base` + `api_keys`）のみで実現します。
|
||||
|
||||
### 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 cron スタイルのスケジュールタスクをサポートします。
|
||||
|
||||
@@ -576,7 +576,7 @@ For complete documentation, see [`../security/security_configuration.md`](../sec
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Get Key](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Get Key](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Get Key](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
|
||||
@@ -820,6 +820,7 @@ The old `providers` configuration is **deprecated** and has been removed in V2.
|
||||
PicoClaw routes providers by protocol family:
|
||||
|
||||
- **OpenAI-compatible**: OpenRouter, Groq, Zhipu, vLLM-style endpoints, and most others.
|
||||
- **Gemini native**: Google Gemini via the native `models/*:generateContent` and `models/*:streamGenerateContent` endpoints.
|
||||
- **Anthropic**: Claude-native API behavior.
|
||||
- **Codex/OAuth**: OpenAI OAuth/token authentication route.
|
||||
|
||||
|
||||
@@ -340,7 +340,7 @@ Responde HEARTBEAT_OK Usuário recebe resultado diretamente
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Obter](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Obter](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Obter](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Obter](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Obter](https://aistudio.google.com/api-keys) |
|
||||
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Obter](https://console.groq.com) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Obter](https://dashscope.console.aliyun.com) |
|
||||
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (sem chave) |
|
||||
@@ -370,9 +370,12 @@ A configuração antiga `providers` está **depreciada** e foi removida no V2. C
|
||||
PicoClaw roteia providers por família de protocolo:
|
||||
|
||||
- **Compatível com OpenAI**: OpenRouter, Groq, Zhipu, endpoints vLLM e a maioria dos outros.
|
||||
- **Gemini nativo**: Google Gemini via endpoints nativos `models/*:generateContent` e `models/*:streamGenerateContent`.
|
||||
- **Anthropic**: Comportamento nativo da API Claude.
|
||||
- **Codex/OAuth**: Rota de autenticação OAuth/token OpenAI.
|
||||
|
||||
Isso mantém o runtime leve enquanto torna novos backends compatíveis com OpenAI basicamente uma operação de configuração (`api_base` + `api_keys`).
|
||||
|
||||
### Tarefas Agendadas / Lembretes
|
||||
|
||||
PicoClaw suporta tarefas agendadas via ferramenta `cron`.
|
||||
|
||||
@@ -340,7 +340,7 @@ Trả lời HEARTBEAT_OK Người dùng nhận kết quả trực tiếp
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Lấy](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Lấy](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Lấy](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Lấy](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Lấy](https://aistudio.google.com/api-keys) |
|
||||
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Lấy](https://console.groq.com) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Lấy](https://dashscope.console.aliyun.com) |
|
||||
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Cục bộ (không cần key) |
|
||||
@@ -370,9 +370,12 @@ Cấu hình `providers` cũ đã **bị deprecated** và đã được loại b
|
||||
PicoClaw định tuyến provider theo họ giao thức:
|
||||
|
||||
- **Tương thích OpenAI**: OpenRouter, Groq, Zhipu, endpoint kiểu vLLM và hầu hết các provider khác.
|
||||
- **Gemini native**: Google Gemini qua các endpoint native `models/*:generateContent` và `models/*:streamGenerateContent`.
|
||||
- **Anthropic**: Hành vi API Claude gốc.
|
||||
- **Codex/OAuth**: Tuyến xác thực OAuth/token OpenAI.
|
||||
|
||||
Điều này giữ runtime nhẹ trong khi khiến backend OpenAI-compatible mới chủ yếu chỉ là thao tác cấu hình (`api_base` + `api_keys`).
|
||||
|
||||
### Tác Vụ Đã Lên Lịch / Nhắc Nhở
|
||||
|
||||
PicoClaw hỗ trợ tác vụ theo lịch qua công cụ `cron`.
|
||||
|
||||
@@ -441,7 +441,7 @@ Agent 读取 HEARTBEAT.md
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [获取](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [获取](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [获取](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [获取](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [获取](https://aistudio.google.com/api-keys) |
|
||||
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [获取](https://console.groq.com) |
|
||||
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [获取](https://platform.moonshot.cn) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [获取](https://dashscope.console.aliyun.com) |
|
||||
@@ -652,10 +652,11 @@ PicoClaw 只剥离最外层的 `litellm/` 前缀再发送请求，因此 `litell
|
||||
PicoClaw 按协议族路由提供商：
|
||||
|
||||
- **OpenAI 兼容**：OpenRouter、Groq、智谱、vLLM 风格端点及大多数其他提供商。
|
||||
- **Gemini 原生**：Google Gemini 通过原生 `models/*:generateContent` 和 `models/*:streamGenerateContent` 端点接入。
|
||||
- **Anthropic**：Claude 原生 API 行为。
|
||||
- **Codex/OAuth**：OpenAI OAuth/Token 认证路由。
|
||||
|
||||
这使运行时保持轻量，同时让接入新的 OpenAI 兼容后端基本只需配置 `api_base` + `api_key`。
|
||||
这使运行时保持轻量，同时让接入新的 OpenAI 兼容后端基本只需配置 `api_base` + `api_keys`。
|
||||
|
||||
<details>
|
||||
<summary><b>智谱（旧版 providers 格式）</b></summary>
|
||||
|
||||
@@ -46,7 +46,7 @@ Cette conception permet également le **support multi-agents** avec une sélecti
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Get Key](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Get Key](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Get Key](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
|
||||
@@ -108,7 +108,7 @@ Cette conception permet également le **support multi-agents** avec une sélecti
|
||||
| `api_keys` | string[] | Oui* | Clé(s) API pour l'authentification. Plusieurs clés permettent la rotation par requête. Non requis pour les fournisseurs locaux (Ollama, LM Studio, VLLM) |
|
||||
| `api_base` | string | Non | Remplace l'URL de base API par défaut |
|
||||
| `proxy` | string | Non | URL du proxy HTTP pour cette entrée de modèle |
|
||||
| `user_agent` | string | Non | En-tête `User-Agent` personnalisé pour les requêtes API (supporté par les providers OpenAI-compatible, Anthropic et Azure) |
|
||||
| `user_agent` | string | Non | En-tête `User-Agent` personnalisé pour les requêtes API (supporté par les providers compatibles OpenAI, Gemini, Anthropic et Azure) |
|
||||
| `request_timeout` | int | Non | Délai d'expiration de la requête en secondes (la valeur par défaut varie selon le provider) |
|
||||
| `max_tokens_field` | string | Non | Remplace le nom du champ max tokens dans le corps de la requête (ex : `max_completion_tokens` pour les modèles o1) |
|
||||
| `thinking_level` | string | Non | Niveau de pensée étendue : `off`, `low`, `medium`, `high`, `xhigh` ou `adaptive` |
|
||||
@@ -299,10 +299,11 @@ Pour un guide de migration détaillé, voir [migration/model-list-migration.md](
|
||||
PicoClaw route les fournisseurs par famille de protocoles :
|
||||
|
||||
- Protocole compatible OpenAI : OpenRouter, passerelles compatibles OpenAI, Groq, Zhipu et endpoints de type vLLM.
|
||||
- Protocole Gemini natif : Google Gemini via les endpoints natifs `models/*:generateContent` et `models/*:streamGenerateContent`.
|
||||
- Protocole Anthropic : Comportement natif de l'API Claude.
|
||||
- Chemin Codex/OAuth : Route d'authentification OAuth/token OpenAI.
|
||||
|
||||
Cela maintient le runtime léger tout en faisant des nouveaux backends compatibles OpenAI principalement une opération de configuration (`api_base` + `api_key`).
|
||||
Cela maintient le runtime léger tout en faisant des nouveaux backends compatibles OpenAI principalement une opération de configuration (`api_base` + `api_keys`).
|
||||
|
||||
<details>
|
||||
<summary><b>Zhipu</b></summary>
|
||||
|
||||
@@ -47,7 +47,7 @@
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [キーを取得](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [キーを取得](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [キーを取得](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [キーを取得](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [キーを取得](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通義千問 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [キーを取得](https://dashscope.console.aliyun.com) |
|
||||
@@ -109,7 +109,7 @@
|
||||
| `api_keys` | string[] | はい* | 認証キー。複数キーでリクエストごとのローテーションが可能。ローカル provider（Ollama、LM Studio、VLLM）には不要 |
|
||||
| `api_base` | string | いいえ | デフォルトの API エンドポイント URL を上書き |
|
||||
| `proxy` | string | いいえ | このモデルエントリの HTTP プロキシ URL |
|
||||
| `user_agent` | string | いいえ | カスタム `User-Agent` リクエストヘッダー（OpenAI 互換、Anthropic、Azure provider で対応） |
|
||||
| `user_agent` | string | いいえ | カスタム `User-Agent` リクエストヘッダー（OpenAI 互換、Gemini、Anthropic、Azure provider で対応） |
|
||||
| `request_timeout` | int | いいえ | リクエストタイムアウト（秒）。デフォルト値は provider により異なる |
|
||||
| `max_tokens_field` | string | いいえ | リクエストボディの max tokens フィールド名を上書き（例：o1 モデルでは `max_completion_tokens`） |
|
||||
| `thinking_level` | string | いいえ | 拡張思考レベル：`off`、`low`、`medium`、`high`、`xhigh`、`adaptive` |
|
||||
@@ -311,6 +311,7 @@ PicoClaw はリクエスト送信前に外側の `litellm/` プレフィック
|
||||
PicoClaw はプロトコルファミリーごとに Provider をルーティングします：
|
||||
|
||||
- OpenAI 互換プロトコル：OpenRouter、OpenAI 互換ゲートウェイ、Groq、Zhipu、vLLM スタイルのエンドポイント。
|
||||
- Gemini ネイティブプロトコル：Google Gemini のネイティブ `models/*:generateContent` / `models/*:streamGenerateContent` エンドポイント。
|
||||
- Anthropic プロトコル：Claude ネイティブ API 動作。
|
||||
- Codex/OAuth パス：OpenAI OAuth/Token 認証ルート。
|
||||
|
||||
|
||||
@@ -54,7 +54,7 @@ This design also enables **multi-agent support** with flexible provider selectio
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Get Key](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **Z.AI Coding Plan** | `openai/` | `https://api.z.ai/api/coding/paas/v4` | OpenAI | [Get Key](https://z.ai/manage-apikey/apikey-list) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Get Key](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
|
||||
@@ -119,7 +119,7 @@ This design also enables **multi-agent support** with flexible provider selectio
|
||||
| `api_keys` | string[] | Yes* | API key(s) for authentication. Multiple keys enable per-request rotation. Not required for local providers (Ollama, LM Studio, VLLM) |
|
||||
| `api_base` | string | No | Override the default API endpoint URL |
|
||||
| `proxy` | string | No | HTTP proxy URL for this model entry |
|
||||
| `user_agent` | string | No | Custom `User-Agent` header sent with API requests (supported by OpenAI-compatible, Anthropic, and Azure providers) |
|
||||
| `user_agent` | string | No | Custom `User-Agent` header sent with API requests (supported by OpenAI-compatible, Gemini, Anthropic, and Azure providers) |
|
||||
| `request_timeout` | int | No | Request timeout in seconds (default varies by provider) |
|
||||
| `max_tokens_field` | string | No | Override the max tokens field name in request body (e.g., `max_completion_tokens` for o1 models) |
|
||||
| `thinking_level` | string | No | Extended thinking level: `off`, `low`, `medium`, `high`, `xhigh`, or `adaptive` |
|
||||
@@ -415,10 +415,11 @@ For detailed migration guide, see [migration/model-list-migration.md](../migrati
|
||||
PicoClaw routes providers by protocol family:
|
||||
|
||||
- OpenAI-compatible protocol: OpenRouter, OpenAI-compatible gateways, Groq, Zhipu, and vLLM-style endpoints.
|
||||
- Gemini native protocol: Google Gemini via the native `models/*:generateContent` and `models/*:streamGenerateContent` endpoints.
|
||||
- Anthropic protocol: Claude-native API behavior.
|
||||
- Codex/OAuth path: OpenAI OAuth/token authentication route.
|
||||
|
||||
This keeps the runtime lightweight while making new OpenAI-compatible backends mostly a config operation (`api_base` + `api_key`).
|
||||
This keeps the runtime lightweight while making new OpenAI-compatible backends mostly a config operation (`api_base` + `api_keys`).
|
||||
|
||||
<details>
|
||||
<summary><b>Zhipu</b></summary>
|
||||
|
||||
@@ -46,7 +46,7 @@ Este design também permite **suporte multi-agente** com seleção flexível de
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Get Key](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Get Key](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Get Key](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
|
||||
@@ -108,7 +108,7 @@ Este design também permite **suporte multi-agente** com seleção flexível de
|
||||
| `api_keys` | string[] | Sim* | Chave(s) API para autenticação. Múltiplas chaves permitem rotação por requisição. Não necessário para providers locais (Ollama, LM Studio, VLLM) |
|
||||
| `api_base` | string | Não | Substitui a URL base da API padrão |
|
||||
| `proxy` | string | Não | URL do proxy HTTP para esta entrada de modelo |
|
||||
| `user_agent` | string | Não | Cabeçalho `User-Agent` personalizado enviado com requisições API (suportado por providers OpenAI-compatible, Anthropic e Azure) |
|
||||
| `user_agent` | string | Não | Cabeçalho `User-Agent` personalizado enviado com requisições API (suportado por providers OpenAI-compatible, Gemini, Anthropic e Azure) |
|
||||
| `request_timeout` | int | Não | Timeout de requisição em segundos (o padrão varia por provider) |
|
||||
| `max_tokens_field` | string | Não | Substitui o nome do campo max tokens no corpo da requisição (ex: `max_completion_tokens` para modelos o1) |
|
||||
| `thinking_level` | string | Não | Nível de pensamento estendido: `off`, `low`, `medium`, `high`, `xhigh` ou `adaptive` |
|
||||
@@ -299,6 +299,7 @@ Para guia de migração detalhado, veja [migration/model-list-migration.md](../m
|
||||
O PicoClaw roteia provedores por família de protocolo:
|
||||
|
||||
- Protocolo compatível com OpenAI: OpenRouter, gateways compatíveis com OpenAI, Groq, Zhipu e endpoints estilo vLLM.
|
||||
- Protocolo Gemini nativo: Google Gemini via endpoints nativos `models/*:generateContent` e `models/*:streamGenerateContent`.
|
||||
- Protocolo Anthropic: Comportamento nativo da API Claude.
|
||||
- Caminho Codex/OAuth: Rota de autenticação OAuth/token da OpenAI.
|
||||
|
||||
|
||||
@@ -46,7 +46,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa agent** với lựa chọn pr
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Get Key](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Get Key](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Get Key](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [Get Key](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
|
||||
@@ -108,7 +108,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa agent** với lựa chọn pr
|
||||
| `api_keys` | string[] | Có* | Khóa API xác thực. Nhiều khóa cho phép xoay vòng theo yêu cầu. Không cần thiết cho provider nội bộ (Ollama, LM Studio, VLLM) |
|
||||
| `api_base` | string | Không | Ghi đè URL endpoint API mặc định |
|
||||
| `proxy` | string | Không | URL proxy HTTP cho entry model này |
|
||||
| `user_agent` | string | Không | Header `User-Agent` tùy chỉnh gửi với yêu cầu API (được hỗ trợ bởi provider OpenAI-compatible, Anthropic và Azure) |
|
||||
| `user_agent` | string | Không | Header `User-Agent` tùy chỉnh gửi với yêu cầu API (được hỗ trợ bởi provider OpenAI-compatible, Gemini, Anthropic và Azure) |
|
||||
| `request_timeout` | int | Không | Timeout yêu cầu tính bằng giây (mặc định khác nhau tùy provider) |
|
||||
| `max_tokens_field` | string | Không | Ghi đè tên trường max tokens trong request body (ví dụ: `max_completion_tokens` cho model o1) |
|
||||
| `thinking_level` | string | Không | Mức độ tư duy mở rộng: `off`, `low`, `medium`, `high`, `xhigh` hoặc `adaptive` |
|
||||
@@ -299,6 +299,7 @@ Cấu hình `providers` cũ đã **bị deprecated** và đã được loại b
|
||||
PicoClaw định tuyến provider theo họ giao thức:
|
||||
|
||||
- Giao thức tương thích OpenAI: OpenRouter, gateway tương thích OpenAI, Groq, Zhipu, và endpoint kiểu vLLM.
|
||||
- Giao thức Gemini native: Google Gemini qua các endpoint native `models/*:generateContent` và `models/*:streamGenerateContent`.
|
||||
- Giao thức Anthropic: Hành vi API native của Claude.
|
||||
- Đường dẫn Codex/OAuth: Tuyến xác thực OAuth/token của OpenAI.
|
||||
|
||||
|
||||
@@ -52,7 +52,7 @@
|
||||
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [获取密钥](https://console.anthropic.com) |
|
||||
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [获取密钥](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
|
||||
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [获取密钥](https://platform.deepseek.com) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [获取密钥](https://aistudio.google.com/api-keys) |
|
||||
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | Gemini | [获取密钥](https://aistudio.google.com/api-keys) |
|
||||
| **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) |
|
||||
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [获取密钥](https://dashscope.console.aliyun.com) |
|
||||
@@ -116,7 +116,7 @@
|
||||
| `api_keys` | string[] | 是* | 认证密钥。多个密钥可按请求轮换。本地 provider（Ollama、LM Studio、VLLM）不需要 |
|
||||
| `api_base` | string | 否 | 覆盖默认的 API 端点 URL |
|
||||
| `proxy` | string | 否 | 此模型条目的 HTTP 代理 URL |
|
||||
| `user_agent` | string | 否 | 自定义 `User-Agent` 请求头（支持 OpenAI 兼容、Anthropic 和 Azure provider） |
|
||||
| `user_agent` | string | 否 | 自定义 `User-Agent` 请求头（支持 OpenAI 兼容、Gemini、Anthropic 和 Azure provider） |
|
||||
| `request_timeout` | int | 否 | 请求超时时间（秒），默认值因 provider 而异 |
|
||||
| `max_tokens_field` | string | 否 | 覆盖请求体中 max tokens 的字段名（如 o1 模型使用 `max_completion_tokens`） |
|
||||
| `thinking_level` | string | 否 | 扩展思考级别：`off`、`low`、`medium`、`high`、`xhigh` 或 `adaptive` |
|
||||
@@ -386,10 +386,11 @@ PicoClaw 在发送请求前仅去除外层 `litellm/` 前缀，因此 `litellm/l
|
||||
PicoClaw 按协议族路由 Provider：
|
||||
|
||||
- OpenAI 兼容协议：OpenRouter、OpenAI 兼容网关、Groq、智谱、vLLM 风格端点。
|
||||
- Gemini 原生协议：Google Gemini 通过原生 `models/*:generateContent` 和 `models/*:streamGenerateContent` 端点接入。
|
||||
- Anthropic 协议：Claude 原生 API 行为。
|
||||
- Codex/OAuth 路径：OpenAI OAuth/Token 认证路由。
|
||||
|
||||
这使得运行时保持轻量，同时让新的 OpenAI 兼容后端基本只需配置操作（`api_base` + `api_key`）。
|
||||
这使得运行时保持轻量，同时让新的 OpenAI 兼容后端基本只需配置操作（`api_base` + `api_keys`）。
|
||||
|
||||
<details>
|
||||
<summary><b>智谱 (Zhipu) 配置示例</b></summary>
|
||||
|
||||
Reference in New Issue
Block a user