lzh/picoclaw
1
0
Fork 0
mirror of https://github.com/sipeed/picoclaw.git synced 2026-05-25 16:00:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(provider): add ModelScope as OpenAI-compatible provider (#1486)

Browse Source 
* feat(provider): add ModelScope as OpenAI-compatible provider

* test(provider): add ModelScope provider and migration tests

* docs: add ModelScope to README provider tables and free tier sections

* chore: add ModelScope to example config and env template
This commit is contained in:
dataCenter430
2026-03-13 07:02:23 +01:00
committed by GitHub
parent 83e24e8ceb
commit b811e9186c
14 changed files with 88 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+1
View File
@@ -5,6 +5,7 @@
# ANTHROPIC_API_KEY=sk-ant-xxx
# OPENAI_API_KEY=sk-xxx
# GEMINI_API_KEY=xxx
# MODELSCOPE_API_KEY=xxx
# CLAUDE_CODE_OAUTH=xxx
# ── Chat Channel ──────────────────────────
# TELEGRAM_BOT_TOKEN=123456:ABC...
README.fr.md
+2
View File
@@ -985,6 +985,7 @@ Cette conception permet également le **support multi-agent** avec une sélectio
| **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [Obtenir Clé](https://www.byteplus.com/) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [Obtenir une clé](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [Obtenir un Token](https://modelscope.cn/my/tokens) |
| **Antigravity** | `antigravity/` | Google Cloud | Custom | OAuth uniquement |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
@@ -1223,6 +1224,7 @@ Cela se produit lorsqu'une autre instance du bot est en cours d'exécution. Assu
| **Zhipu** | 200K tokens/mois | Convient aux utilisateurs chinois |
| **Brave Search** | 2000 requêtes/mois | Fonctionnalité de recherche web |
| **Groq** | Offre gratuite dispo | Inférence ultra-rapide (Llama, Mixtral) |
| **ModelScope** | 2000 requêtes/jour | Inférence gratuite (Qwen, GLM, DeepSeek, etc.) |
---
README.ja.md
+2
View File
@@ -926,6 +926,7 @@ HEARTBEAT_OK 応答 ユーザーが直接結果を受け取る
| **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [キーを取得](https://www.byteplus.com) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [キーを取得](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [トークンを取得](https://modelscope.cn/my/tokens) |
| **Antigravity** | `antigravity/` | Google Cloud | カスタム | OAuthのみ |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
@@ -1146,6 +1147,7 @@ Web 検索を有効にするには：
| **Tavily** | 月 1000 クエリ | AI エージェント検索最適化 |
| **Groq** | 無料枠あり | 高速推論（Llama, Mixtral） |
| **Cerebras** | 無料枠あり | 高速推論（Llama, Qwen など） |
| **ModelScope** | 1 日 2000 リクエスト | 無料推論（Qwen, GLM, DeepSeek など） |
---
README.md
+2
View File
@@ -1039,6 +1039,7 @@ This design also enables **multi-agent support** with flexible provider selectio
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [Get Key](https://www.byteplus.com) |
| **Vivgrid** | `vivgrid/` | `https://api.vivgrid.com/v1` | OpenAI | [Get Key](https://vivgrid.com) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [Get Key](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [Get Token](https://modelscope.cn/my/tokens) |
| **Antigravity** | `antigravity/` | Google Cloud | Custom | OAuth only |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
@@ -1526,6 +1527,7 @@ This happens when another instance of the bot is running. Make sure only one `pi
| **Groq** | Free tier available | Fast inference (Llama, Mixtral) |
| **Cerebras** | Free tier available | Fast inference (Llama, Qwen, etc.) |
| **LongCat** | Up to 5M tokens/day | Fast inference (free tier) |
| **ModelScope** | 2000 requests/day | Free inference (Qwen, GLM, DeepSeek, etc.) |
---
README.pt-br.md
+2
View File
@@ -981,6 +981,7 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
| **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [Obter Chave](https://www.byteplus.com) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [Obter Chave](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [Obter Token](https://modelscope.cn/my/tokens) |
| **Antigravity** | `antigravity/` | Google Cloud | Custom | Apenas OAuth |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
@@ -1220,6 +1221,7 @@ Isso acontece quando outra instância do bot está em execução. Certifique-se
| **Brave Search** | 2000 consultas/mês | Funcionalidade de busca web |
| **Groq** | Plano gratuito disponível | Inferência ultra-rápida (Llama, Mixtral) |
| **Cerebras** | Plano gratuito disponível | Inferência ultra-rápida (Llama 3.3 70B) |
| **ModelScope** | 2000 requisições/dia | Inferência gratuita (Qwen, GLM, DeepSeek, etc.) |
---
README.vi.md
+2
View File
@@ -950,6 +950,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
| **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [Lấy Khóa](https://www.byteplus.com) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [Lấy Key](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [Lấy Token](https://modelscope.cn/my/tokens) |
| **Antigravity** | `antigravity/` | Google Cloud | Tùy chỉnh | Chỉ OAuth |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
@@ -1188,6 +1189,7 @@ Một số nhà cung cấp (như Zhipu) có bộ lọc nội dung nghiêm ngặt
| **Zhipu** | 200K tokens/tháng | Phù hợp cho người dùng Trung Quốc |
| **Brave Search** | 2000 truy vấn/tháng | Chức năng tìm kiếm web |
| **Groq** | Có gói miễn phí | Suy luận siêu nhanh (Llama, Mixtral) |
| **ModelScope** | 2000 yêu cầu/ngày | Suy luận miễn phí (Qwen, GLM, DeepSeek, v.v.) |
---
README.zh.md
+2
View File
@@ -522,6 +522,7 @@ Agent 读取 HEARTBEAT.md
| **神算云** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [获取密钥](https://www.byteplus.com) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [获取密钥](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [获取 Token](https://modelscope.cn/my/tokens) |
| **Antigravity** | `antigravity/` | Google Cloud | 自定义 | 仅 OAuth |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
@@ -901,6 +902,7 @@ Discord: [https://discord.gg/V4sAZ9XWpN](https://discord.gg/V4sAZ9XWpN)
| **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) |
| **LongCat** | 最多 5M tokens/天 | 推理速度快 (免费额度) |
| **ModelScope (魔搭)** | 2000 次请求/天 | 免费推理 (Qwen, GLM, DeepSeek 等) |
---
config/config.example.json
+10
View File
@@ -40,6 +40,12 @@
"model": "longcat/LongCat-Flash-Thinking",
"api_key": "your-longcat-api-key"
},
{
"model_name": "modelscope-qwen",
"model": "modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507",
"api_key": "your-modelscope-access-token",
"api_base": "https://api-inference.modelscope.cn/v1"
},
{
"model_name": "loadbalanced-gpt-5.4",
"model": "openai/gpt-5.4",
@@ -283,6 +289,10 @@
"longcat": {
"api_key": "",
"api_base": "https://api.longcat.chat/openai"
},
"modelscope": {
"api_key": "",
"api_base": "https://api-inference.modelscope.cn/v1"
}
},
"tools": {
pkg/config/config.go
+3 -1
View File
@@ -528,6 +528,7 @@ type ProvidersConfig struct {
Avian ProviderConfig `json:"avian"`
Minimax ProviderConfig `json:"minimax"`
LongCat ProviderConfig `json:"longcat"`
ModelScope ProviderConfig `json:"modelscope"`
}
// IsEmpty checks if all provider configs are empty (no API keys or API bases set)
@@ -555,7 +556,8 @@ func (p ProvidersConfig) IsEmpty() bool {
p.Mistral.APIKey == "" && p.Mistral.APIBase == "" &&
p.Avian.APIKey == "" && p.Avian.APIBase == "" &&
p.Minimax.APIKey == "" && p.Minimax.APIBase == "" &&
p.LongCat.APIKey == "" && p.LongCat.APIBase == ""
p.LongCat.APIKey == "" && p.LongCat.APIBase == "" &&
p.ModelScope.APIKey == "" && p.ModelScope.APIBase == ""
}
// MarshalJSON implements custom JSON marshaling for ProvidersConfig
pkg/config/defaults.go
+8
View File
@@ -369,6 +369,14 @@ func DefaultConfig() *Config {
APIKey: "",
},
// ModelScope (魔搭社区) - https://modelscope.cn/my/tokens
{
ModelName: "modelscope-qwen",
Model: "modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507",
APIBase: "https://api-inference.modelscope.cn/v1",
APIKey: "",
},
// VLLM (local) - http://localhost:8000
{
ModelName: "local-model",
pkg/config/migration.go
+17
View File
@@ -424,6 +424,23 @@ func ConvertProvidersToModelList(cfg *Config) []ModelConfig {
}, true
},
},
{
providerNames: []string{"modelscope"},
protocol: "modelscope",
buildConfig: func(p ProvidersConfig) (ModelConfig, bool) {
if p.ModelScope.APIKey == "" && p.ModelScope.APIBase == "" {
return ModelConfig{}, false
}
return ModelConfig{
ModelName: "modelscope",
Model: "modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507",
APIKey: p.ModelScope.APIKey,
APIBase: p.ModelScope.APIBase,
Proxy: p.ModelScope.Proxy,
RequestTimeout: p.ModelScope.RequestTimeout,
}, true
},
},
}
// Process each provider migration
pkg/config/migration_test.go
+4 -3
View File
@@ -163,14 +163,15 @@ func TestConvertProvidersToModelList_AllProviders(t *testing.T) {
Mistral: ProviderConfig{APIKey: "key18"},
Avian: ProviderConfig{APIKey: "key19"},
LongCat: ProviderConfig{APIKey: "key-longcat"},
ModelScope: ProviderConfig{APIKey: "key-modelscope"},
},
}
result := ConvertProvidersToModelList(cfg)
// All 22 providers should be converted
if len(result) != 22 {
t.Errorf("len(result) = %d, want 22", len(result))
// All 23 providers should be converted
if len(result) != 23 {
t.Errorf("len(result) = %d, want 23", len(result))
}
}
pkg/providers/factory_provider.go
+3 -1
View File
@@ -95,7 +95,7 @@ func CreateProviderFromConfig(cfg *config.ModelConfig) (LLMProvider, string, err
case "litellm", "openrouter", "groq", "zhipu", "gemini", "nvidia",
"ollama", "moonshot", "shengsuanyun", "deepseek", "cerebras",
"vivgrid", "volcengine", "vllm", "qwen", "mistral", "avian",
"minimax", "longcat":
"minimax", "longcat", "modelscope":
// All other OpenAI-compatible HTTP providers
if cfg.APIKey == "" && cfg.APIBase == "" {
return nil, "", fmt.Errorf("api_key or api_base is required for HTTP-based protocol %q", protocol)
@@ -217,6 +217,8 @@ func getDefaultAPIBase(protocol string) string {
return "https://api.minimaxi.com/v1"
case "longcat":
return "https://api.longcat.chat/openai"
case "modelscope":
return "https://api-inference.modelscope.cn/v1"
default:
return ""
}
pkg/providers/factory_provider_test.go
+30
View File
@@ -114,6 +114,7 @@ func TestCreateProviderFromConfig_DefaultAPIBase(t *testing.T) {
{"deepseek", "deepseek"},
{"ollama", "ollama"},
{"longcat", "longcat"},
{"modelscope", "modelscope"},
}
for _, tt := range tests {
@@ -186,6 +187,35 @@ func TestCreateProviderFromConfig_LongCat(t *testing.T) {
}
}
func TestCreateProviderFromConfig_ModelScope(t *testing.T) {
cfg := &config.ModelConfig{
ModelName: "test-modelscope",
Model: "modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507",
APIKey: "test-key",
APIBase: "https://api-inference.modelscope.cn/v1",
}
provider, modelID, err := CreateProviderFromConfig(cfg)
if err != nil {
t.Fatalf("CreateProviderFromConfig() error = %v", err)
}
if provider == nil {
t.Fatal("CreateProviderFromConfig() returned nil provider")
}
if modelID != "Qwen/Qwen3-235B-A22B-Instruct-2507" {
t.Errorf("modelID = %q, want %q", modelID, "Qwen/Qwen3-235B-A22B-Instruct-2507")
}
if _, ok := provider.(*HTTPProvider); !ok {
t.Fatalf("expected *HTTPProvider, got %T", provider)
}
}
func TestGetDefaultAPIBase_ModelScope(t *testing.T) {
if got := getDefaultAPIBase("modelscope"); got != "https://api-inference.modelscope.cn/v1" {
t.Fatalf("getDefaultAPIBase(%q) = %q, want %q", "modelscope", got, "https://api-inference.modelscope.cn/v1")
}
}
func TestCreateProviderFromConfig_Anthropic(t *testing.T) {
cfg := &config.ModelConfig{
ModelName: "test-anthropic",