feat: add MiniMax provider support for PicoOraClaw

apps/picooraclaw/.env.example

@@ -5,6 +5,7 @@
 # ANTHROPIC_API_KEY=sk-ant-xxx
 # OPENAI_API_KEY=sk-xxx
 # GEMINI_API_KEY=xxx
+# MINIMAX_API_KEY=xxx
 
 # ── Chat Channel ──────────────────────────
 # TELEGRAM_BOT_TOKEN=123456:ABC...

apps/picooraclaw/README.md

@@ -691,6 +691,32 @@ Get a key at [openrouter.ai/keys](https://openrouter.ai/keys) (200K free tokens/
 
 </details>
 
+<details>
+<summary><b>MiniMax (high-performance, great value)</b></summary>
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "provider": "minimax",
+      "model": "MiniMax-M2.7"
+    }
+  },
+  "providers": {
+    "minimax": {
+      "api_key": "your-key",
+      "api_base": "https://api.minimax.io/v1"
+    }
+  }
+}
+```
+
+Available models: `MiniMax-M2.7` (default), `MiniMax-M2.7-highspeed` (faster).
+
+Get a key at [platform.minimax.io](https://platform.minimax.io).
+
+</details>
+
 <details>
 <summary><b>Zhipu (best for Chinese users)</b></summary>
 
@@ -728,6 +754,7 @@ Get a key at [bigmodel.cn](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys
 | `gemini` | Gemini models | [aistudio.google.com](https://aistudio.google.com) |
 | `groq` | Fast inference + voice transcription | [console.groq.com](https://console.groq.com) |
 | `deepseek` | DeepSeek models | [platform.deepseek.com](https://platform.deepseek.com) |
+| `minimax` | MiniMax models (M2.7) | [platform.minimax.io](https://platform.minimax.io) |
 | `zhipu` | Zhipu/GLM models | [bigmodel.cn](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
 
 </details>
@@ -1001,7 +1028,7 @@ docker compose run --rm picoclaw-agent -m "What is 2+2?"
 ## Features
 
 - Single static binary (~10MB RAM), runs on RISC-V/ARM64/x86_64
-- Ollama, OpenRouter, Anthropic, OpenAI, Gemini, Zhipu, DeepSeek, Groq providers
+- Ollama, OpenRouter, Anthropic, OpenAI, Gemini, Zhipu, DeepSeek, Groq, MiniMax providers
 - **Default: [Oracle AI Database 26ai Free](https://www.oracle.com/database/free/)** with AI Vector Search (384-dim ONNX embeddings)
 - Chat channels: Telegram, Discord, Slack, QQ, DingTalk, LINE, Feishu, WhatsApp
 - Scheduled tasks via cron expressions

apps/picooraclaw/config/config.example.json

@@ -108,6 +108,10 @@
     "ollama": {
       "api_key": "",
       "api_base": "http://localhost:11434/v1"
+    },
+    "minimax": {
+      "api_key": "",
+      "api_base": "https://api.minimax.io/v1"
     }
   },
   "tools": {

apps/picooraclaw/pkg/config/config.go

@@ -228,6 +228,7 @@ type ProvidersConfig struct {
 	Moonshot      ProviderConfig `json:"moonshot"`
 	DeepSeek      ProviderConfig `json:"deepseek"`
 	GitHubCopilot ProviderConfig `json:"github_copilot"`
+	MiniMax       ProviderConfig `json:"minimax"`
 }
 
 type ProviderConfig struct {
@@ -369,6 +370,7 @@ func DefaultConfig() *Config {
 			Gemini:     ProviderConfig{},
 			Nvidia:     ProviderConfig{},
 			Moonshot:   ProviderConfig{},
+			MiniMax:    ProviderConfig{},
 		},
 		Gateway: GatewayConfig{
 			Host: "0.0.0.0",

apps/picooraclaw/pkg/providers/http_provider.go

@@ -57,7 +57,7 @@ func (p *HTTPProvider) Chat(ctx context.Context, messages []Message, tools []Too
 	// Strip provider prefix from model name (e.g., moonshot/kimi-k2.5 -> kimi-k2.5, groq/openai/gpt-oss-120b -> openai/gpt-oss-120b, ollama/qwen2.5:14b -> qwen2.5:14b)
 	if idx := strings.Index(model, "/"); idx != -1 {
 		prefix := model[:idx]
-		if prefix == "moonshot" || prefix == "nvidia" || prefix == "groq" || prefix == "ollama" {
+		if prefix == "moonshot" || prefix == "nvidia" || prefix == "groq" || prefix == "ollama" || prefix == "minimax" {
 			model = model[idx+1:]
 		}
 	}
@@ -86,6 +86,15 @@ func (p *HTTPProvider) Chat(ctx context.Context, messages []Message, tools []Too
 		// Kimi k2 models only support temperature=1
 		if strings.Contains(lowerModel, "kimi") && strings.Contains(lowerModel, "k2") {
 			requestBody["temperature"] = 1.0
+		} else if strings.Contains(lowerModel, "MiniMax") || strings.Contains(lowerModel, "minimax") {
+			// MiniMax models require temperature in (0.0, 1.0]; 0 is not allowed
+			if temperature <= 0 {
+				requestBody["temperature"] = 1.0
+			} else if temperature > 1.0 {
+				requestBody["temperature"] = 1.0
+			} else {
+				requestBody["temperature"] = temperature
+			}
 		} else {
 			requestBody["temperature"] = temperature
 		}
@@ -467,6 +476,15 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
 					model = "deepseek-chat"
 				}
 			}
+		case "minimax", "MiniMax":
+			if cfg.Providers.MiniMax.APIKey != "" {
+				apiKey = cfg.Providers.MiniMax.APIKey
+				apiBase = cfg.Providers.MiniMax.APIBase
+				if apiBase == "" {
+					apiBase = "https://api.minimax.io/v1"
+				}
+				proxy = cfg.Providers.MiniMax.Proxy
+			}
 		case "github_copilot", "copilot":
 			if cfg.Providers.GitHubCopilot.APIBase != "" {
 				apiBase = cfg.Providers.GitHubCopilot.APIBase
@@ -544,6 +562,13 @@ func CreateProvider(cfg *config.Config) (LLMProvider, error) {
 			if apiBase == "" {
 				apiBase = "https://integrate.api.nvidia.com/v1"
 			}
+		case (strings.Contains(lowerModel, "minimax") || strings.Contains(lowerModel, "MiniMax") || strings.HasPrefix(model, "minimax/")) && cfg.Providers.MiniMax.APIKey != "":
+			apiKey = cfg.Providers.MiniMax.APIKey
+			apiBase = cfg.Providers.MiniMax.APIBase
+			proxy = cfg.Providers.MiniMax.Proxy
+			if apiBase == "" {
+				apiBase = "https://api.minimax.io/v1"
+			}
 		case (strings.Contains(lowerModel, "ollama") || strings.HasPrefix(model, "ollama/")) && cfg.Providers.Ollama.APIBase != "":
 			apiKey = cfg.Providers.Ollama.APIKey
 			if apiKey == "" {