feat: add MiniMax provider support via OpenAI-compatible endpoint

Register MiniMax as an OpenAI-compatible provider using the official
API at https://api.minimax.io/v1 with MiniMax-M2.5 as default model.

Changes across config, factory, migration, defaults, and docs.

README.md

@@ -924,6 +924,7 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
 | `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)                         |
 | `cerebras`                 | LLM (Cerebras direct)                   | [cerebras.ai](https://cerebras.ai)                                   |
+| `minimax`                  | LLM (MiniMax direct)                    | [platform.minimax.io](https://platform.minimax.io)               |
 
 ### Model Configuration (model_list)
 
@@ -956,6 +957,7 @@ This design also enables **multi-agent support** with flexible provider selectio
 | **Cerebras**        | `cerebras/`       | `https://api.cerebras.ai/v1`                        | OpenAI    | [Get Key](https://cerebras.ai)                                   |
 | **火山引擎**        | `volcengine/`     | `https://ark.cn-beijing.volces.com/api/v3`          | OpenAI    | [Get Key](https://console.volcengine.com)                        |
 | **神算云**          | `shengsuanyun/`   | `https://router.shengsuanyun.com/api/v1`            | OpenAI    | -                                                                |
+| **MiniMax**         | `minimax/`        | `https://api.minimax.io/v1`                       | OpenAI    | [Get Key](https://platform.minimax.io)                         |
 | **Antigravity**     | `antigravity/`    | Google Cloud                                        | Custom    | OAuth only                                                       |
 | **GitHub Copilot**  | `github-copilot/` | `localhost:4321`                                    | gRPC      | -                                                                |
 

config/config.example.json

@@ -46,6 +46,12 @@
       "model": "openai/gpt-5.2",
       "api_key": "sk-key2",
       "api_base": "https://api2.example.com/v1"
+    },
+    {
+      "model_name": "minimax-m2.5",
+      "model": "minimax/MiniMax-M2.5",
+      "api_key": "sk-your-minimax-key",
+      "api_base": "https://api.minimax.io/v1"
     }
   ],
   "channels": {

pkg/config/config.go

@@ -432,6 +432,7 @@ type ProvidersConfig struct {
 	Qwen          ProviderConfig       `json:"qwen"`
 	Mistral       ProviderConfig       `json:"mistral"`
 	Avian         ProviderConfig       `json:"avian"`
+	Minimax       ProviderConfig       `json:"minimax"`
 }
 
 // IsEmpty checks if all provider configs are empty (no API keys or API bases set)
@@ -456,7 +457,8 @@ func (p ProvidersConfig) IsEmpty() bool {
 		p.Antigravity.APIKey == "" && p.Antigravity.APIBase == "" &&
 		p.Qwen.APIKey == "" && p.Qwen.APIBase == "" &&
 		p.Mistral.APIKey == "" && p.Mistral.APIBase == "" &&
-		p.Avian.APIKey == "" && p.Avian.APIBase == ""
+		p.Avian.APIKey == "" && p.Avian.APIBase == "" &&
+		p.Minimax.APIKey == "" && p.Minimax.APIBase == ""
 }
 
 // MarshalJSON implements custom JSON marshaling for ProvidersConfig

pkg/config/defaults.go

@@ -277,6 +277,14 @@ func DefaultConfig() *Config {
 				APIKey:    "",
 			},
 
+			// MiniMax - https://platform.minimax.io/
+			{
+				ModelName: "minimax-m2.5",
+				Model:     "minimax/MiniMax-M2.5",
+				APIBase:   "https://api.minimax.io/v1",
+				APIKey:    "",
+			},
+
 			// Antigravity (Google Cloud Code Assist) - OAuth only
 			{
 				ModelName:  "gemini-flash",

pkg/config/migration.go

@@ -390,6 +390,23 @@ func ConvertProvidersToModelList(cfg *Config) []ModelConfig {
 				}, true
 			},
 		},
+		{
+			providerNames: []string{"minimax"},
+			protocol:      "minimax",
+			buildConfig: func(p ProvidersConfig) (ModelConfig, bool) {
+				if p.Minimax.APIKey == "" && p.Minimax.APIBase == "" {
+					return ModelConfig{}, false
+				}
+				return ModelConfig{
+					ModelName:      "minimax",
+					Model:          "minimax/MiniMax-M2.5",
+					APIKey:         p.Minimax.APIKey,
+					APIBase:        p.Minimax.APIBase,
+					Proxy:          p.Minimax.Proxy,
+					RequestTimeout: p.Minimax.RequestTimeout,
+				}, true
+			},
+		},
 	}
 
 	// Process each provider migration

pkg/providers/factory_provider.go

@@ -94,7 +94,7 @@ func CreateProviderFromConfig(cfg *config.ModelConfig) (LLMProvider, string, err
 
 	case "litellm", "openrouter", "groq", "zhipu", "gemini", "nvidia",
 		"ollama", "moonshot", "shengsuanyun", "deepseek", "cerebras",
-		"volcengine", "vllm", "qwen", "mistral", "avian":
+		"volcengine", "vllm", "qwen", "mistral", "avian", "minimax":
 		// 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)
@@ -204,6 +204,8 @@ func getDefaultAPIBase(protocol string) string {
 		return "https://ark.cn-beijing.volces.com/api/v3"
 	case "qwen":
 		return "https://dashscope.aliyuncs.com/compatible-mode/v1"
+	case "minimax":
+		return "https://api.minimax.io/v1"
 	case "vllm":
 		return "http://localhost:8000/v1"
 	case "mistral":

pkg/providers/openai_compat/provider.go

@@ -363,7 +363,7 @@ func normalizeModel(model, apiBase string) string {
 
 	prefix := strings.ToLower(before)
 	switch prefix {
-	case "litellm", "moonshot", "nvidia", "groq", "ollama", "deepseek", "google", "openrouter", "zhipu", "mistral":
+	case "litellm", "moonshot", "nvidia", "groq", "ollama", "deepseek", "google", "openrouter", "zhipu", "mistral", "minimax":
 		return after
 	default:
 		return model