feat(provider): add support for azure openai provider

README.fr.md

@@ -987,6 +987,7 @@ Cette conception permet également le **support multi-agent** avec une sélectio
 | **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)              |
+| **Azure OpenAI**    | `azure/`          | `https://{resource}.openai.azure.com`               | Azure     | [Obtenir Clé](https://portal.azure.com)                          |
 | **Antigravity** | `antigravity/` | Google Cloud | Custom | OAuth uniquement |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 

README.ja.md

@@ -928,6 +928,7 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 | **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)                 |
+| **Azure OpenAI**    | `azure/`          | `https://{resource}.openai.azure.com`               | Azure     | [キーを取得](https://portal.azure.com)                            |
 | **Antigravity** | `antigravity/` | Google Cloud | カスタム | OAuthのみ |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 

README.md

@@ -1005,6 +1005,7 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
 | `groq`       | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com)                 |
 | `cerebras`   | LLM (Cerebras direct)                   | [cerebras.ai](https://cerebras.ai)                           |
 | `vivgrid`    | LLM (Vivgrid direct)                    | [vivgrid.com](https://vivgrid.com)                           |
+| `azure`      | LLM (Azure OpenAI)                      | [portal.azure.com](https://portal.azure.com)                 |
 
 ### Model Configuration (model_list)
 
@@ -1041,6 +1042,7 @@ This design also enables **multi-agent support** with flexible provider selectio
 | **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)                     |
+| **Azure OpenAI**    | `azure/`          | `https://{resource}.openai.azure.com`               | Azure     | [Get Key](https://portal.azure.com)                              |
 | **Antigravity**     | `antigravity/`    | Google Cloud                                        | Custom    | OAuth only                                                       |
 | **GitHub Copilot**  | `github-copilot/` | `localhost:4321`                                    | gRPC      | -                                                                |
 

README.pt-br.md

@@ -983,6 +983,7 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
 | **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)                   |
+| **Azure OpenAI**    | `azure/`          | `https://{resource}.openai.azure.com`               | Azure     | [Obter Chave](https://portal.azure.com)                          |
 | **Antigravity** | `antigravity/` | Google Cloud | Custom | Apenas OAuth |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 

README.vi.md

@@ -952,6 +952,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 | **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)                    |
+| **Azure OpenAI**    | `azure/`          | `https://{resource}.openai.azure.com`               | Azure     | [Lấy Khóa](https://portal.azure.com)                             |
 | **Antigravity** | `antigravity/` | Google Cloud | Tùy chỉnh | Chỉ OAuth |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 

README.zh.md

@@ -524,6 +524,7 @@ Agent 读取 HEARTBEAT.md
 | **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)                    |
+| **Azure OpenAI**    | `azure/`          | `https://{resource}.openai.azure.com`               | Azure     | [获取密钥](https://portal.azure.com)                              |
 | **Antigravity**     | `antigravity/`    | Google Cloud                                        | 自定义    | 仅 OAuth                                                          |
 | **GitHub Copilot**  | `github-copilot/` | `localhost:4321`                                    | gRPC      | -                                                                 |
 

config/config.example.json

@@ -53,6 +53,12 @@
       "api_key": "your-modelscope-access-token",
       "api_base": "https://api-inference.modelscope.cn/v1"
     },
+    {
+      "model_name": "azure-gpt5",
+      "model": "azure/my-gpt5-deployment",
+      "api_key": "your-azure-api-key",
+      "api_base": "https://your-resource.openai.azure.com"
+    },
     {
       "model_name": "loadbalanced-gpt-5.4",
       "model": "openai/gpt-5.4",

pkg/config/defaults.go

@@ -384,6 +384,15 @@ func DefaultConfig() *Config {
 				APIBase:   "http://localhost:8000/v1",
 				APIKey:    "",
 			},
+
+			// Azure OpenAI - https://portal.azure.com
+			// model_name is a user-friendly alias; the model field's path after "azure/" is your deployment name
+			{
+				ModelName: "azure-gpt5",
+				Model:     "azure/my-gpt5-deployment",
+				APIBase:   "https://your-resource.openai.azure.com",
+				APIKey:    "",
+			},
 		},
 		Gateway: GatewayConfig{
 			Host: "127.0.0.1",

pkg/providers/azure/provider.go

@@ -0,0 +1,150 @@
+package azure
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/url"
+	"strings"
+	"time"
+
+	"github.com/sipeed/picoclaw/pkg/providers/common"
+	"github.com/sipeed/picoclaw/pkg/providers/protocoltypes"
+)
+
+type (
+	LLMResponse    = protocoltypes.LLMResponse
+	Message        = protocoltypes.Message
+	ToolDefinition = protocoltypes.ToolDefinition
+)
+
+const (
+	// azureAPIVersion is the Azure OpenAI API version used for all requests.
+	azureAPIVersion       = "2024-10-21"
+	defaultRequestTimeout = common.DefaultRequestTimeout
+)
+
+// Provider implements the LLM provider interface for Azure OpenAI endpoints.
+// It handles Azure-specific authentication (api-key header), URL construction
+// (deployment-based), and request body formatting (max_completion_tokens, no model field).
+type Provider struct {
+	apiKey     string
+	apiBase    string
+	httpClient *http.Client
+}
+
+// Option configures the Azure Provider.
+type Option func(*Provider)
+
+// WithRequestTimeout sets the HTTP request timeout.
+func WithRequestTimeout(timeout time.Duration) Option {
+	return func(p *Provider) {
+		if timeout > 0 {
+			p.httpClient.Timeout = timeout
+		}
+	}
+}
+
+// NewProvider creates a new Azure OpenAI provider.
+func NewProvider(apiKey, apiBase, proxy string, opts ...Option) *Provider {
+	p := &Provider{
+		apiKey:     apiKey,
+		apiBase:    strings.TrimRight(apiBase, "/"),
+		httpClient: common.NewHTTPClient(proxy),
+	}
+
+	for _, opt := range opts {
+		if opt != nil {
+			opt(p)
+		}
+	}
+
+	return p
+}
+
+// NewProviderWithTimeout creates a new Azure OpenAI provider with a custom request timeout in seconds.
+func NewProviderWithTimeout(apiKey, apiBase, proxy string, requestTimeoutSeconds int) *Provider {
+	return NewProvider(
+		apiKey, apiBase, proxy,
+		WithRequestTimeout(time.Duration(requestTimeoutSeconds)*time.Second),
+	)
+}
+
+// Chat sends a chat completion request to the Azure OpenAI endpoint.
+// The model parameter is used as the Azure deployment name in the URL.
+func (p *Provider) Chat(
+	ctx context.Context,
+	messages []Message,
+	tools []ToolDefinition,
+	model string,
+	options map[string]any,
+) (*LLMResponse, error) {
+	if p.apiBase == "" {
+		return nil, fmt.Errorf("Azure API base not configured")
+	}
+
+	// model is the deployment name for Azure OpenAI
+	deployment := model
+
+	// Build Azure-specific URL safely using url.JoinPath and query encoding
+	// to prevent path traversal or query injection via deployment names.
+	base, err := url.JoinPath(p.apiBase, "openai/deployments", deployment, "chat/completions")
+	if err != nil {
+		return nil, fmt.Errorf("failed to build Azure request URL: %w", err)
+	}
+	requestURL := base + "?api-version=" + azureAPIVersion
+
+	// Build request body — no "model" field (Azure infers from deployment URL)
+	requestBody := map[string]any{
+		"messages": common.SerializeMessages(messages),
+	}
+
+	if len(tools) > 0 {
+		requestBody["tools"] = tools
+		requestBody["tool_choice"] = "auto"
+	}
+
+	// Azure OpenAI always uses max_completion_tokens
+	if maxTokens, ok := common.AsInt(options["max_tokens"]); ok {
+		requestBody["max_completion_tokens"] = maxTokens
+	}
+
+	if temperature, ok := common.AsFloat(options["temperature"]); ok {
+		requestBody["temperature"] = temperature
+	}
+
+	jsonData, err := json.Marshal(requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("failed to marshal request: %w", err)
+	}
+
+	req, err := http.NewRequestWithContext(ctx, "POST", requestURL, bytes.NewReader(jsonData))
+	if err != nil {
+		return nil, fmt.Errorf("failed to create request: %w", err)
+	}
+
+	// Azure uses api-key header instead of Authorization: Bearer
+	req.Header.Set("Content-Type", "application/json")
+	if p.apiKey != "" {
+		req.Header.Set("api-key", p.apiKey)
+	}
+
+	resp, err := p.httpClient.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("failed to send request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return nil, common.HandleErrorResponse(resp, p.apiBase)
+	}
+
+	return common.ReadAndParseResponse(resp, p.apiBase)
+}
+
+// GetDefaultModel returns an empty string as Azure deployments are user-configured.
+func (p *Provider) GetDefaultModel() string {
+	return ""
+}