feat(baoyu-image-gen): add Azure OpenAI as independent image generation provider (#111)

Azure OpenAI differs from standard OpenAI in two ways:
1. Auth via api-key header instead of Authorization: Bearer
2. URL requires ?api-version query param with deployment path

Changes:
- New file: scripts/providers/azure.ts (generations + edits, reuses openai utilities)
- types.ts: add "azure" to Provider type and default_model
- main.ts: register azure across rate limits, CLI args, auto-detection,
  provider loading, model resolution, help text, ref validation,
  EXTEND.md parsing, and batch logging

Env vars: AZURE_OPENAI_API_KEY, AZURE_OPENAI_BASE_URL (required),
AZURE_API_VERSION, AZURE_OPENAI_IMAGE_MODEL (optional)

Co-authored-by: CatFly <zw.catfly@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

skills/baoyu-image-gen/scripts/main.ts

@@ -60,6 +60,7 @@ const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
   dashscope: { concurrency: 3, startIntervalMs: 1100 },
   jimeng: { concurrency: 3, startIntervalMs: 1100 },
   seedream: { concurrency: 3, startIntervalMs: 1100 },
+  azure: { concurrency: 3, startIntervalMs: 1100 },
 };
 
 function printUsage(): void {
@@ -74,13 +75,13 @@ Options:
   --image <path>            Output image path (required in single-image mode)
   --batchfile <path>        JSON batch file for multi-image generation
   --jobs <count>            Worker count for batch mode (default: auto, max from config, built-in default 10)
-  --provider google|openai|openrouter|dashscope|replicate|jimeng|seedream  Force provider (auto-detect by default)
+  --provider google|openai|openrouter|dashscope|replicate|jimeng|seedream|azure  Force provider (auto-detect by default)
   -m, --model <id>          Model ID
   --ar <ratio>              Aspect ratio (e.g., 16:9, 1:1, 4:3)
   --size <WxH>              Size (e.g., 1024x1024)
   --quality normal|2k       Quality preset (default: 2k)
   --imageSize 1K|2K|4K      Image size for Google/OpenRouter (default: from quality)
-  --ref <files...>          Reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0)
+  --ref <files...>          Reference images (Google, OpenAI, Azure, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0)
   --n <count>               Number of images for the current task (default: 1)
   --json                    JSON output
   -h, --help                Show help
@@ -131,6 +132,10 @@ Environment variables:
   DASHSCOPE_BASE_URL        Custom DashScope endpoint
   REPLICATE_BASE_URL        Custom Replicate endpoint
   JIMENG_BASE_URL           Custom Jimeng endpoint
+  AZURE_OPENAI_API_KEY      Azure OpenAI API key
+  AZURE_OPENAI_BASE_URL     Azure OpenAI deployment endpoint
+  AZURE_API_VERSION         Azure API version (default: 2024-02-01)
+  AZURE_OPENAI_IMAGE_MODEL  Default Azure model (gpt-image-1.5)
   SEEDREAM_BASE_URL         Custom Seedream endpoint
   BAOYU_IMAGE_GEN_MAX_WORKERS  Override batch worker cap
   BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY  Override provider concurrency
@@ -231,7 +236,8 @@ export function parseArgs(argv: string[]): CliArgs {
         v !== "dashscope" &&
         v !== "replicate" &&
         v !== "jimeng" &&
-        v !== "seedream"
+        v !== "seedream" &&
+        v !== "azure"
       ) {
         throw new Error(`Invalid provider: ${v}`);
       }
@@ -386,6 +392,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           replicate: null,
           jimeng: null,
           seedream: null,
+          azure: null,
         };
         currentKey = "default_model";
         currentProvider = null;
@@ -411,7 +418,8 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "dashscope" ||
           key === "replicate" ||
           key === "jimeng" ||
-          key === "seedream"
+          key === "seedream" ||
+          key === "azure"
         )
       ) {
         config.batch ??= {};
@@ -427,7 +435,8 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "dashscope" ||
           key === "replicate" ||
           key === "jimeng" ||
-          key === "seedream"
+          key === "seedream" ||
+          key === "azure"
         )
       ) {
         const cleaned = value.replace(/['"]/g, "");
@@ -520,9 +529,10 @@ export function getConfiguredProviderRateLimits(
     dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
     jimeng: { ...DEFAULT_PROVIDER_RATE_LIMITS.jimeng },
     seedream: { ...DEFAULT_PROVIDER_RATE_LIMITS.seedream },
+    azure: { ...DEFAULT_PROVIDER_RATE_LIMITS.azure },
   };
 
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream", "azure"] as Provider[]) {
     const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
     const extendLimit = extendConfig.batch?.provider_limits?.[provider];
     configured[provider] = {
@@ -581,18 +591,20 @@ export function detectProvider(args: CliArgs): Provider {
     args.provider &&
     args.provider !== "google" &&
     args.provider !== "openai" &&
+    args.provider !== "azure" &&
     args.provider !== "openrouter" &&
     args.provider !== "replicate" &&
     args.provider !== "seedream"
   ) {
     throw new Error(
-      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider openrouter (OpenRouter multimodal), --provider replicate, or --provider seedream for supported Seedream models."
+      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider azure (Azure OpenAI), --provider openrouter (OpenRouter multimodal), --provider replicate, or --provider seedream for supported Seedream models."
     );
   }
 
   if (args.provider) return args.provider;
 
   const hasGoogle = !!(process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY);
+  const hasAzure = !!(process.env.AZURE_OPENAI_API_KEY && process.env.AZURE_OPENAI_BASE_URL);
   const hasOpenai = !!process.env.OPENAI_API_KEY;
   const hasOpenrouter = !!process.env.OPENROUTER_API_KEY;
   const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
@@ -611,17 +623,19 @@ export function detectProvider(args: CliArgs): Provider {
   if (args.referenceImages.length > 0) {
     if (hasGoogle) return "google";
     if (hasOpenai) return "openai";
+    if (hasAzure) return "azure";
     if (hasOpenrouter) return "openrouter";
     if (hasReplicate) return "replicate";
     if (hasSeedream) return "seedream";
     throw new Error(
-      "Reference images require Google, OpenAI, OpenRouter, Replicate, or supported Seedream models. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, or ARK_API_KEY, or remove --ref."
+      "Reference images require Google, OpenAI, Azure, OpenRouter, Replicate, or supported Seedream models. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, or ARK_API_KEY, or remove --ref."
     );
   }
 
   const available = [
     hasGoogle && "google",
     hasOpenai && "openai",
+    hasAzure && "azure",
     hasOpenrouter && "openrouter",
     hasDashscope && "dashscope",
     hasReplicate && "replicate",
@@ -633,7 +647,7 @@ export function detectProvider(args: CliArgs): Provider {
   if (available.length > 1) return available[0]!;
 
   throw new Error(
-    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
+    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
       "Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
   );
 }
@@ -676,6 +690,7 @@ async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
   if (provider === "openrouter") return (await import("./providers/openrouter")) as ProviderModule;
   if (provider === "jimeng") return (await import("./providers/jimeng")) as ProviderModule;
   if (provider === "seedream") return (await import("./providers/seedream")) as ProviderModule;
+  if (provider === "azure") return (await import("./providers/azure")) as ProviderModule;
   return (await import("./providers/openai")) as ProviderModule;
 }
 
@@ -704,6 +719,7 @@ function getModelForProvider(
     if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
     if (provider === "jimeng" && extendConfig.default_model.jimeng) return extendConfig.default_model.jimeng;
     if (provider === "seedream" && extendConfig.default_model.seedream) return extendConfig.default_model.seedream;
+    if (provider === "azure" && extendConfig.default_model.azure) return extendConfig.default_model.azure;
   }
   return providerModule.getDefaultModel();
 }
@@ -923,7 +939,7 @@ async function runBatchTasks(
   const acquireProvider = createProviderGate(providerRateLimits);
   const workerCount = getWorkerCount(tasks.length, jobs, maxWorkers);
   console.error(`Batch mode: ${tasks.length} tasks, ${workerCount} workers, parallel mode enabled.`);
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream", "azure"] as Provider[]) {
     const limit = providerRateLimits[provider];
     console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
   }

skills/baoyu-image-gen/scripts/providers/azure.ts

@@ -0,0 +1,118 @@
+import path from "node:path";
+import { readFile } from "node:fs/promises";
+import type { CliArgs } from "../types";
+import { getOpenAISize, parseAspectRatio, getMimeType, extractImageFromResponse } from "./openai";
+
+type OpenAIImageResponse = { data: Array<{ url?: string; b64_json?: string }> };
+
+export function getDefaultModel(): string {
+  return process.env.AZURE_OPENAI_IMAGE_MODEL || "gpt-image-1.5";
+}
+
+function getBaseURL(): string {
+  const url = process.env.AZURE_OPENAI_BASE_URL;
+  if (!url) {
+    throw new Error(
+      "AZURE_OPENAI_BASE_URL is required. Set it to your Azure deployment endpoint, e.g.: https://your-resource.openai.azure.com/openai/deployments/your-deployment"
+    );
+  }
+  return url.replace(/\/+$/, "");
+}
+
+function getApiKey(): string {
+  const key = process.env.AZURE_OPENAI_API_KEY;
+  if (!key) {
+    throw new Error(
+      "AZURE_OPENAI_API_KEY is required. Get it from Azure Portal → your OpenAI resource → Keys and Endpoint."
+    );
+  }
+  return key;
+}
+
+function getApiVersion(): string {
+  return process.env.AZURE_API_VERSION || "2024-02-01";
+}
+
+function buildURL(pathSuffix: string): string {
+  return `${getBaseURL()}${pathSuffix}?api-version=${getApiVersion()}`;
+}
+
+function authHeaders(): Record<string, string> {
+  return { "api-key": getApiKey() };
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
+
+  if (args.referenceImages.length > 0) {
+    return generateWithAzureEdits(prompt, model, size, args.referenceImages, args.quality);
+  }
+
+  return generateWithAzureGenerations(prompt, model, size, args.quality);
+}
+
+async function generateWithAzureGenerations(
+  prompt: string,
+  model: string,
+  size: string,
+  quality: CliArgs["quality"]
+): Promise<Uint8Array> {
+  const body: Record<string, any> = { prompt, size, n: 1 };
+
+  const res = await fetch(buildURL("/images/generations"), {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      ...authHeaders(),
+    },
+    body: JSON.stringify(body),
+  });
+
+  if (!res.ok) {
+    const err = await res.text();
+    throw new Error(`Azure OpenAI API error: ${err}`);
+  }
+
+  const result = (await res.json()) as OpenAIImageResponse;
+  return extractImageFromResponse(result);
+}
+
+async function generateWithAzureEdits(
+  prompt: string,
+  model: string,
+  size: string,
+  referenceImages: string[],
+  quality: CliArgs["quality"]
+): Promise<Uint8Array> {
+  const form = new FormData();
+  form.append("prompt", prompt);
+  form.append("size", size);
+
+  for (const refPath of referenceImages) {
+    const bytes = await readFile(refPath);
+    const filename = path.basename(refPath);
+    const mimeType = getMimeType(filename);
+    const blob = new Blob([bytes], { type: mimeType });
+    form.append("image[]", blob, filename);
+  }
+
+  const res = await fetch(buildURL("/images/edits"), {
+    method: "POST",
+    headers: {
+      ...authHeaders(),
+    },
+    body: form,
+  });
+
+  if (!res.ok) {
+    const err = await res.text();
+    throw new Error(`Azure OpenAI edits API error: ${err}`);
+  }
+
+  const result = (await res.json()) as OpenAIImageResponse;
+  return extractImageFromResponse(result);
+}

skills/baoyu-image-gen/scripts/types.ts

@@ -1,4 +1,4 @@
-export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate" | "jimeng" | "seedream";
+export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate" | "jimeng" | "seedream" | "azure";
 export type Quality = "normal" | "2k";
 
 export type CliArgs = {
@@ -55,6 +55,7 @@ export type ExtendConfig = {
     replicate: string | null;
     jimeng: string | null;
     seedream: string | null;
+    azure: string | null;
   };
   batch?: {
     max_workers?: number | null;