feat(provider): add Venice AI support and update related documentation (#2238)

* feat(provider): add Venice AI support and update related documentation

* revert(asr): restore asr files to previous commit

* feat(config): add Venice API base URL and local LM Studio configuration

* fix(config): update Venice API base URL to correct endpoint

config/config.example.json

@@ -48,6 +48,11 @@
       "model": "deepseek/deepseek-chat",
       "api_key": "sk-your-deepseek-key"
     },
+    {
+      "model_name": "venice-uncensored",
+      "model": "venice/venice-uncensored",
+      "api_key": "your-venice-api-key"
+    },
     {
       "model_name": "lmstudio-local",
       "model": "lmstudio/openai/gpt-oss-20b"

docs/providers.md

@@ -16,6 +16,7 @@
 | `openrouter` | LLM (recommended, access to all models) | [openrouter.ai](https://openrouter.ai)                       |
 | `anthropic`  | LLM (Claude direct)                     | [console.anthropic.com](https://console.anthropic.com)       |
 | `openai`     | LLM (GPT direct)                        | [platform.openai.com](https://platform.openai.com)           |
+| `venice`     | LLM (Venice AI direct)                  | [venice.ai](https://venice.ai)                               |
 | `deepseek`   | LLM (DeepSeek direct)                   | [platform.deepseek.com](https://platform.deepseek.com)       |
 | `qwen`       | LLM (Qwen direct)                       | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
 | `groq`       | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com)                 |
@@ -46,6 +47,7 @@ This design also enables **multi-agent support** with flexible provider selectio
 | Vendor              | `model` Prefix    | Default API Base                                    | Protocol  | API Key                                                          |
 | ------------------- | ----------------- |-----------------------------------------------------| --------- | ---------------------------------------------------------------- |
 | **OpenAI**          | `openai/`         | `https://api.openai.com/v1`                         | OpenAI    | [Get Key](https://platform.openai.com)                           |
+| **Venice AI**       | `venice/`         | `https://api.venice.ai/api/v1`                      | OpenAI    | [Get Key](https://venice.ai)                                     |
 | **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) |
 | **Z.AI Coding Plan** | `openai/`         | `https://api.z.ai/api/coding/paas/v4`              | OpenAI    | [Get Key](https://z.ai/manage-apikey/apikey-list) |

docs/zh/providers.md

@@ -15,6 +15,7 @@
 | `openrouter`         | LLM (推荐，可访问所有模型)   | [openrouter.ai](https://openrouter.ai)                               |
 | `anthropic`          | LLM (Claude 直连)            | [console.anthropic.com](https://console.anthropic.com)               |
 | `openai`             | LLM (GPT 直连)               | [platform.openai.com](https://platform.openai.com)                   |
+| `venice`             | LLM (Venice AI 直连)         | [venice.ai](https://venice.ai)                                       |
 | `deepseek`           | 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) |
 | `groq`               | LLM + **语音转录** (Whisper) | [console.groq.com](https://console.groq.com)                         |
@@ -44,6 +45,7 @@
 | 厂商                | `model` 前缀      | 默认 API Base                                       | 协议      | 获取 API Key                                                      |
 | ------------------- | ----------------- | --------------------------------------------------- | --------- | ----------------------------------------------------------------- |
 | **OpenAI**          | `openai/`         | `https://api.openai.com/v1`                         | OpenAI    | [获取密钥](https://platform.openai.com)                           |
+| **Venice AI**       | `venice/`         | `https://api.venice.ai/api/v1`                      | OpenAI    | [获取密钥](https://venice.ai)                                     |
 | **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)                         |

pkg/config/defaults.go

@@ -185,6 +185,13 @@ func DefaultConfig() *Config {
 				APIBase:   "https://api.deepseek.com/v1",
 			},
 
+			// Venice AI - https://venice.ai
+			{
+				ModelName: "venice-uncensored",
+				Model:     "venice/venice-uncensored",
+				APIBase:   "https://api.venice.ai/api/v1",
+			},
+
 			// Google Gemini - https://ai.google.dev/
 			{
 				ModelName: "gemini-2.0-flash",
@@ -335,6 +342,13 @@ func DefaultConfig() *Config {
 				APIBase:   "http://localhost:8000/v1",
 			},
 
+			// LM Studio (local) - http://localhost:1234
+			{
+				ModelName: "lmstudio-local",
+				Model:     "lmstudio/openai/gpt-oss-20b",
+				APIBase:   "http://localhost:1234/v1",
+			},
+
 			// Azure OpenAI - https://portal.azure.com
 			// model_name is a user-friendly alias; the model field's path after "azure/" is your deployment name
 			{

pkg/providers/factory_provider.go

@@ -24,6 +24,7 @@ type protocolMeta struct {
 
 var protocolMetaByName = map[string]protocolMeta{
 	"openai":                   {defaultAPIBase: "https://api.openai.com/v1"},
+	"venice":                   {defaultAPIBase: "https://api.venice.ai/api/v1"},
 	"openrouter":               {defaultAPIBase: "https://openrouter.ai/api/v1"},
 	"litellm":                  {defaultAPIBase: "http://localhost:4000/v1"},
 	"lmstudio":                 {defaultAPIBase: "http://localhost:1234/v1", emptyAPIKeyAllowed: true},
@@ -209,7 +210,7 @@ func CreateProviderFromConfig(cfg *config.ModelConfig) (LLMProvider, string, err
 		}
 		return provider, modelID, nil
 
-	case "litellm", "lmstudio", "openrouter", "groq", "zhipu", "gemini", "nvidia",
+	case "litellm", "lmstudio", "openrouter", "groq", "zhipu", "gemini", "nvidia", "venice",
 		"ollama", "moonshot", "shengsuanyun", "deepseek", "cerebras",
 		"vivgrid", "volcengine", "vllm", "qwen", "qwen-intl", "qwen-international", "dashscope-intl",
 		"qwen-us", "dashscope-us", "mistral", "avian", "longcat", "modelscope", "novita",

pkg/providers/factory_provider_test.go

@@ -112,6 +112,7 @@ func TestCreateProviderFromConfig_DefaultAPIBase(t *testing.T) {
 		protocol string
 	}{
 		{"openai", "openai"},
+		{"venice", "venice"},
 		{"groq", "groq"},
 		{"novita", "novita"},
 		{"openrouter", "openrouter"},
@@ -160,6 +161,12 @@ func TestGetDefaultAPIBase_LMStudio(t *testing.T) {
 	}
 }
 
+func TestGetDefaultAPIBase_Venice(t *testing.T) {
+	if got := getDefaultAPIBase("venice"); got != "https://api.venice.ai/api/v1" {
+		t.Fatalf("getDefaultAPIBase(%q) = %q, want %q", "venice", got, "https://api.venice.ai/api/v1")
+	}
+}
+
 func TestCreateProviderFromConfig_LiteLLM(t *testing.T) {
 	cfg := &config.ModelConfig{
 		ModelName: "test-litellm",
@@ -362,6 +369,28 @@ func TestCreateProviderFromConfig_Mimo(t *testing.T) {
 	}
 }
 
+func TestCreateProviderFromConfig_Venice(t *testing.T) {
+	cfg := &config.ModelConfig{
+		ModelName: "test-venice",
+		Model:     "venice/venice-uncensored",
+	}
+	cfg.SetAPIKey("test-key")
+
+	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 != "venice-uncensored" {
+		t.Errorf("modelID = %q, want %q", modelID, "venice-uncensored")
+	}
+	if _, ok := provider.(*HTTPProvider); !ok {
+		t.Fatalf("expected *HTTPProvider, got %T", provider)
+	}
+}
+
 func TestGetDefaultAPIBase_Mimo(t *testing.T) {
 	if got := getDefaultAPIBase("mimo"); got != "https://api.xiaomimimo.com/v1" {
 		t.Fatalf("getDefaultAPIBase(%q) = %q, want %q", "mimo", got, "https://api.xiaomimimo.com/v1")

pkg/providers/openai_compat/provider.go

@@ -44,6 +44,7 @@ const defaultRequestTimeout = common.DefaultRequestTimeout
 
 var stripModelPrefixProviders = map[string]struct{}{
 	"litellm":    {},
+	"venice":     {},
 	"moonshot":   {},
 	"nvidia":     {},
 	"groq":       {},

pkg/providers/openai_compat/provider_test.go

@@ -479,6 +479,11 @@ func TestProviderChat_StripsKnownProviderPrefixes(t *testing.T) {
 			input:     "lmstudio/openai/gpt-oss-20b",
 			wantModel: "openai/gpt-oss-20b",
 		},
+		{
+			name:      "strips venice prefix",
+			input:     "venice/venice-uncensored",
+			wantModel: "venice-uncensored",
+		},
 		{
 			name:      "strips deepseek prefix",
 			input:     "deepseek/deepseek-chat",
@@ -587,6 +592,9 @@ func TestNormalizeModel_UsesAPIBase(t *testing.T) {
 	if got := normalizeModel("lmstudio/openai/gpt-oss-20b", "http://localhost:1234/v1"); got != "openai/gpt-oss-20b" {
 		t.Fatalf("normalizeModel(lmstudio) = %q, want %q", got, "openai/gpt-oss-20b")
 	}
+	if got := normalizeModel("venice/venice-uncensored", "https://api.venice.ai/api/v1"); got != "venice-uncensored" {
+		t.Fatalf("normalizeModel(venice) = %q, want %q", got, "venice-uncensored")
+	}
 	if got := normalizeModel("openrouter/auto", "https://openrouter.ai/api/v1"); got != "openrouter/auto" {
 		t.Fatalf("normalizeModel(openrouter) = %q, want %q", got, "openrouter/auto")
 	}