Merge pull request #523 from aspotton/feature/azure-openai-provider-with-ui

feat: add complete Azure OpenAI provider support

Author: jamiepine

README.md

@@ -195,6 +195,27 @@ api_key = "env:MY_PROVIDER_KEY"
 channel = "my-provider/my-model"
 ```
 
+**Azure OpenAI Service** — configure Azure OpenAI deployments:
+
+```toml
+[llm.provider.azure]
+api_type = "azure"
+base_url = "https://{resource-name}.openai.azure.com"
+api_key = "env:AZURE_API_KEY"
+api_version = "2024-06-01"  # required
+deployment = "gpt-4o"        # required — your deployment name
+
+[defaults.routing]
+channel = "azure/gpt-4o"
+worker = "azure/gpt-4o-mini"
+```
+
+Important notes:
+- `base_url` must end with `.openai.azure.com`
+- `api_version` and `deployment` are required fields
+- API key authentication is handled automatically via the `api-key` header
+- For Azure AI Foundry (accessing Anthropic, Llama, or other models through Azure's model catalog), use `api_type = "openai_chat_completions"` instead and configure the deployment endpoint accordingly
+
 Additional built-in providers include **Kilo Gateway**, **OpenCode Go**, **NVIDIA**, **MiniMax**, **Moonshot AI (Kimi)**, and **Z.AI Coding Plan** — configure with `kilo_key`, `opencode_go_key`, `nvidia_key`, `minimax_key`, `moonshot_key`, or `zai_coding_plan_key` in `[llm]`.
 
 ### Skills

docs/content/docs/(configuration)/config.mdx

@@ -376,6 +376,11 @@ If you define a custom provider with the same ID as a legacy key, your custom co
 | `mistral_key` | string | None | Mistral API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
 | `opencode_zen_key` | string | None | OpenCode Zen API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
 | `opencode_go_key` | string | None | OpenCode Go API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
+| `gemini_key` | string | None | Gemini API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
+| `nvidia_key` | string | None | NVIDIA API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
+| `minimax_key` | string | None | MiniMax API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
+| `moonshot_key` | string | None | Moonshot API key (`secret:NAME`, `env:VAR_NAME`, or literal) |
+| `github_copilot_key` | string | None | GitHub Copilot PAT (`secret:NAME`, `env:VAR_NAME`, or literal) |
 
 #### Custom Providers
 
@@ -391,10 +396,12 @@ name = "My Provider"            # Optional - friendly name for display
 
 | Field | Type | Required | Description |
 |-------|------|----------|-------------|
-| `api_type` | string | Yes | API protocol type. One of: `anthropic`, `openai_completions`, `openai_chat_completions`, `openai_responses`, `gemini`, or `kilo_gateway` |
-| `base_url` | string | Yes | Base URL of the API endpoint. Must be a valid URL (including protocol) |
+| `api_type` | string | Yes | API protocol type. One of: `anthropic`, `openai_completions`, `openai_chat_completions`, `openai_responses`, `gemini`, `kilo_gateway`, or `azure` |
+| `base_url` | string | Yes | Base URL of the API endpoint. Must be a valid URL (including protocol). For Azure, must end with `.openai.azure.com` |
 | `api_key` | string | Yes | API key for authentication. Supports `secret:NAME` and `env:VAR_NAME` syntax |
 | `name` | string | No | Optional friendly name for the provider (displayed in logs and UI) |
+| `api_version` | string | Azure only | Azure API version (format: `YYYY-MM-DD` or `YYYY-MM-DD-preview`) |
+| `deployment` | string | Azure only | Azure deployment name (alphanumeric, hyphens, and dots allowed) |
 
 > Note:
 > - For `openai_completions`, `openai_chat_completions`, and `openai_responses`, configure `base_url` as the provider root URL (usually without a trailing `/v1`).
@@ -421,15 +428,23 @@ api_key = "env:CUSTOM_ANTHROPIC_KEY"
 name = "Anthropic EU"
 ```
 
-**OpenAI Chat Completions provider:**
+**Azure OpenAI provider:**
 ```toml
-[llm.provider.azure_openai]
-api_type = "openai_responses"
-base_url = "https://my-azure-openai.openai.azure.com"
-api_key = "env:AZURE_OPENAI_KEY"
-name = "Azure OpenAI GPT-4"
+[llm.provider.azure]
+api_type = "azure"
+base_url = "https://my-resource.openai.azure.com"
+api_key = "env:AZURE_API_KEY"
+api_version = "2024-02-15"  # Required for Azure
+deployment = "gpt-4o"        # Required for Azure (deployment name)
+name = "Azure OpenAI"
 ```
 
+> **Azure Requirements:**
+> - `base_url` must end with `.openai.azure.com`
+> - `api_version` must match format: `YYYY-MM-DD` or `YYYY-MM-DD-preview`
+> - `deployment` can contain alphanumeric characters, hyphens, and dots (e.g., `gpt-4o`, `gpt-5.2`)
+> - Model names in routing should use the format: `azure/<deployment-name>`
+
 **OpenAI Completions provider:**
 ```toml
 [llm.provider.local_llm]

docs/content/docs/(core)/routing.mdx

@@ -26,6 +26,10 @@ branch = "anthropic/claude-sonnet-4-20250514"
 worker = "anthropic/claude-haiku-4.5-20250514"
 compactor = "anthropic/claude-haiku-4.5-20250514"
 cortex = "anthropic/claude-haiku-4.5-20250514"
+
+# Azure example:
+# channel = "azure/gpt-4o"
+# worker = "azure/gpt-4o-mini"
 ```
 
 | Process | Why this model tier |
@@ -36,6 +40,11 @@ cortex = "anthropic/claude-haiku-4.5-20250514"
 | Compactor | Summarization and memory extraction. Fast and cheap. No personality needed. |
 | Cortex | System-level observation. Small context, simple signal processing. Cheapest tier. |
 
+**Model Format:**
+- Standard providers: `<provider>/<model-name>` (e.g., `anthropic/claude-sonnet-4-20250514`, `openai/gpt-4o`)
+- Azure: `azure/<deployment-name>` (e.g., `azure/gpt-4o`, `azure/gpt-5.2`)
+- Custom providers: `<provider-id>/<model-name>` (e.g., `my_anthropic/claude-3.5-sonnet`)
+
 ### Level 2: Task-Type Overrides
 
 Workers and branches are generic. Different tasks benefit from different models. The channel or branch specifies a task type when spawning, and the routing config maps task types to models.

interface/src/api/client.ts

@@ -1593,28 +1593,44 @@ export const api = {
 
 	// Provider management
 	providers: () => fetchJson<Types.ProvidersResponse>("/providers"),
-	updateProvider: async (provider: string, apiKey: string, model: string) => {
+	updateProvider: async (provider: string, apiKey: string, model: string, baseUrl?: string, apiVersion?: string, deployment?: string) => {
 		const response = await fetch(`${getApiBase()}/providers`, {
-			method: "PUT",
+			method: "POST",
 			headers: { "Content-Type": "application/json" },
-			body: JSON.stringify({ provider, api_key: apiKey, model }),
+			body: JSON.stringify({ provider, api_key: apiKey, model, base_url: baseUrl, api_version: apiVersion, deployment }),
 		});
 		if (!response.ok) {
 			throw new Error(`API error: ${response.status}`);
 		}
 		return response.json() as Promise<Types.ProviderUpdateResponse>;
 	},
-	testProviderModel: async (provider: string, apiKey: string, model: string) => {
-		const response = await fetch(`${getApiBase()}/providers/test`, {
+	testProviderModel: async (provider: string, apiKey: string, model: string, baseUrl?: string, apiVersion?: string, deployment?: string) => {
+		const response = await fetch(`${getApiBase()}/providers/test-model`, {
 			method: "POST",
 			headers: { "Content-Type": "application/json" },
-			body: JSON.stringify({ provider, api_key: apiKey, model }),
+			body: JSON.stringify({ provider, api_key: apiKey, model, base_url: baseUrl, api_version: apiVersion, deployment }),
 		});
 		if (!response.ok) {
 			throw new Error(`API error: ${response.status}`);
 		}
 		return response.json() as Promise<Types.ProviderModelTestResponse>;
 	},
+	getProviderConfig: async (provider: string, options?: { signal?: AbortSignal }) => {
+		const response = await fetch(`${getApiBase()}/providers/${provider}/config`, {
+			method: "GET",
+			signal: options?.signal,
+		});
+		if (!response.ok) {
+			throw new Error(`API error: ${response.status}`);
+		}
+		return response.json() as Promise<{
+			success: boolean;
+			message: string;
+			base_url?: string | null;
+			api_version?: string | null;
+			deployment?: string | null;
+		}>;
+	},
 	startOpenAiOAuthBrowser: async (params: {model: string}) => {
 		const response = await fetch(`${getApiBase()}/providers/openai/oauth/browser/start`, {
 			method: "POST",

interface/src/lib/providerIcons.tsx

@@ -140,6 +140,7 @@ export function ProviderIcon({ provider, className = "text-ink-faint", size = 24
 		"minimax-cn": Minimax,
 		moonshot: Kimi, // Kimi is Moonshot AI's product brand
 		"github-copilot": GithubCopilot,
+		azure: OpenAI,
 	};
 
 	const IconComponent = iconMap[provider.toLowerCase()];