chore: release v1.66.0

fix(image-gen): tighten Jimeng provider behavior

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.65.1"
+    "version": "1.66.0"
   },
   "plugins": [
     {

.github/workflows/test.yml

@@ -0,0 +1,21 @@
+name: Test
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  node-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Run tests
+        run: npm test

CHANGELOG.md

@@ -2,6 +2,23 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.66.0 - 2026-03-13
+
+### Features
+- `baoyu-image-gen`: add Jimeng (即梦) and Seedream (豆包) image generation providers (by @lindaifeng)
+
+### Fixes
+- `baoyu-image-gen`: tighten Jimeng provider behavior
+
+### Refactor
+- `baoyu-image-gen`: export functions for testability and add module entry guard
+
+### Documentation
+- `baoyu-image-gen`: add Jimeng and Seedream provider documentation to SKILL.md and READMEs
+
+### Tests
+- Add test infrastructure with CI workflow and image-gen unit tests
+
 ## 1.65.1 - 2026-03-13
 
 ### Refactor

CHANGELOG.zh.md

@@ -2,6 +2,23 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.66.0 - 2026-03-13
+
+### 新功能
+- `baoyu-image-gen`：新增即梦（Jimeng）和豆包（Seedream）图像生成服务商 (by @lindaifeng)
+
+### 修复
+- `baoyu-image-gen`：收紧即梦服务商行为
+
+### 重构
+- `baoyu-image-gen`：导出函数以支持测试，新增模块入口守卫
+
+### 文档
+- `baoyu-image-gen`：在 SKILL.md 和 README 中添加即梦和豆包服务商文档
+
+### 测试
+- 新增测试基础设施，包含 CI 工作流和 image-gen 单元测试
+
 ## 1.65.1 - 2026-03-13
 
 ### 重构

CLAUDE.md

@@ -1,6 +1,6 @@
 # CLAUDE.md
 
-Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.65.1**.
+Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.66.0**.
 
 ## Architecture
 

README.md

@@ -665,7 +665,7 @@ AI-powered generation backends.
 
 #### baoyu-image-gen
 
-AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyun Tongyi Wanxiang), and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.
+AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyun Tongyi Wanxiang), Jimeng (即梦), Seedream (豆包), and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.
 
 ```bash
 # Basic generation (auto-detect provider)
@@ -689,6 +689,12 @@ AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyu
 # Replicate
 /baoyu-image-gen --prompt "A cat" --image cat.png --provider replicate
 
+# Jimeng (即梦)
+/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
+
+# Seedream (豆包)
+/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
+
 # With reference images (Google, OpenAI, OpenRouter, or Replicate)
 /baoyu-image-gen --prompt "Make it blue" --image out.png --ref source.png
 ```
@@ -699,7 +705,7 @@ AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyu
 | `--prompt`, `-p` | Prompt text |
 | `--promptfiles` | Read prompt from files (concatenated) |
 | `--image` | Output image path (required) |
-| `--provider` | `google`, `openai`, `openrouter`, `dashscope` or `replicate` (default: auto-detect; prefers google) |
+| `--provider` | `google`, `openai`, `openrouter`, `dashscope`, `jimeng`, `seedream` or `replicate` (default: auto-detect; prefers google) |
 | `--model`, `-m` | Model ID |
 | `--ar` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
 | `--size` | Size (e.g., `1024x1024`) |
@@ -714,16 +720,24 @@ AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyu
 | `GOOGLE_API_KEY` | Google API key | - |
 | `DASHSCOPE_API_KEY` | DashScope API key (Aliyun) | - |
 | `REPLICATE_API_TOKEN` | Replicate API token | - |
+| `JIMENG_ACCESS_KEY_ID` | Jimeng Volcengine access key | - |
+| `JIMENG_SECRET_ACCESS_KEY` | Jimeng Volcengine secret key | - |
+| `ARK_API_KEY` | Seedream Volcengine ARK API key | - |
 | `OPENAI_IMAGE_MODEL` | OpenAI model | `gpt-image-1.5` |
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter model | `google/gemini-3.1-flash-image-preview` |
 | `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image-preview` |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope model | `z-image-turbo` |
 | `REPLICATE_IMAGE_MODEL` | Replicate model | `google/nano-banana-pro` |
+| `JIMENG_IMAGE_MODEL` | Jimeng model | `jimeng_t2i_v40` |
+| `SEEDREAM_IMAGE_MODEL` | Seedream model | `doubao-seedream-5-0-260128` |
 | `OPENAI_BASE_URL` | Custom OpenAI endpoint | - |
 | `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint | `https://openrouter.ai/api/v1` |
 | `GOOGLE_BASE_URL` | Custom Google endpoint | - |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint | - |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint | - |
+| `JIMENG_BASE_URL` | Custom Jimeng endpoint | `https://visual.volcengineapi.com` |
+| `JIMENG_REGION` | Jimeng region | `cn-north-1` |
+| `SEEDREAM_BASE_URL` | Custom Seedream endpoint | `https://ark.cn-beijing.volces.com/api/v3` |
 
 **Provider Auto-Selection**:
 1. If `--provider` specified → use it
@@ -989,6 +1003,18 @@ DASHSCOPE_IMAGE_MODEL=z-image-turbo
 REPLICATE_API_TOKEN=r8_xxx
 REPLICATE_IMAGE_MODEL=google/nano-banana-pro
 # REPLICATE_BASE_URL=https://api.replicate.com
+
+# Jimeng (即梦)
+JIMENG_ACCESS_KEY_ID=xxx
+JIMENG_SECRET_ACCESS_KEY=xxx
+JIMENG_IMAGE_MODEL=jimeng_t2i_v40
+# JIMENG_BASE_URL=https://visual.volcengineapi.com
+# JIMENG_REGION=cn-north-1
+
+# Seedream (豆包)
+ARK_API_KEY=xxx
+SEEDREAM_IMAGE_MODEL=doubao-seedream-5-0-260128
+# SEEDREAM_BASE_URL=https://ark.cn-beijing.volces.com/api/v3
 EOF
 ```
 

README.zh.md

@@ -665,7 +665,7 @@ AI 驱动的生成后端。
 
 #### baoyu-image-gen
 
-基于 AI SDK 的图像生成，支持 OpenAI、Google、OpenRouter、DashScope（阿里通义万相）和 Replicate API。支持文生图、参考图、宽高比和质量预设。
+基于 AI SDK 的图像生成，支持 OpenAI、Google、OpenRouter、DashScope（阿里通义万相）、即梦（Jimeng）、豆包（Seedream）和 Replicate API。支持文生图、参考图、宽高比和质量预设。
 
 ```bash
 # 基础生成（自动检测服务商）
@@ -689,6 +689,12 @@ AI 驱动的生成后端。
 # Replicate
 /baoyu-image-gen --prompt "一只猫" --image cat.png --provider replicate
 
+# 即梦（Jimeng）
+/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
+
+# 豆包（Seedream）
+/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
+
 # 带参考图（Google、OpenAI、OpenRouter 或 Replicate）
 /baoyu-image-gen --prompt "把它变成蓝色" --image out.png --ref source.png
 ```
@@ -699,7 +705,7 @@ AI 驱动的生成后端。
 | `--prompt`, `-p` | 提示词文本 |
 | `--promptfiles` | 从文件读取提示词（多文件拼接） |
 | `--image` | 输出图片路径（必需） |
-| `--provider` | `google`、`openai`、`openrouter`、`dashscope` 或 `replicate`（默认：自动检测，优先 google） |
+| `--provider` | `google`、`openai`、`openrouter`、`dashscope`、`jimeng`、`seedream` 或 `replicate`（默认：自动检测，优先 google） |
 | `--model`, `-m` | 模型 ID |
 | `--ar` | 宽高比（如 `16:9`、`1:1`、`4:3`） |
 | `--size` | 尺寸（如 `1024x1024`） |
@@ -714,16 +720,24 @@ AI 驱动的生成后端。
 | `GOOGLE_API_KEY` | Google API 密钥 | - |
 | `DASHSCOPE_API_KEY` | DashScope API 密钥（阿里云） | - |
 | `REPLICATE_API_TOKEN` | Replicate API Token | - |
+| `JIMENG_ACCESS_KEY_ID` | 即梦火山引擎 Access Key | - |
+| `JIMENG_SECRET_ACCESS_KEY` | 即梦火山引擎 Secret Key | - |
+| `ARK_API_KEY` | 豆包火山引擎 ARK API 密钥 | - |
 | `OPENAI_IMAGE_MODEL` | OpenAI 模型 | `gpt-image-1.5` |
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter 模型 | `google/gemini-3.1-flash-image-preview` |
 | `GOOGLE_IMAGE_MODEL` | Google 模型 | `gemini-3-pro-image-preview` |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope 模型 | `z-image-turbo` |
 | `REPLICATE_IMAGE_MODEL` | Replicate 模型 | `google/nano-banana-pro` |
+| `JIMENG_IMAGE_MODEL` | 即梦模型 | `jimeng_t2i_v40` |
+| `SEEDREAM_IMAGE_MODEL` | 豆包模型 | `doubao-seedream-5-0-260128` |
 | `OPENAI_BASE_URL` | 自定义 OpenAI 端点 | - |
 | `OPENROUTER_BASE_URL` | 自定义 OpenRouter 端点 | `https://openrouter.ai/api/v1` |
 | `GOOGLE_BASE_URL` | 自定义 Google 端点 | - |
 | `DASHSCOPE_BASE_URL` | 自定义 DashScope 端点 | - |
 | `REPLICATE_BASE_URL` | 自定义 Replicate 端点 | - |
+| `JIMENG_BASE_URL` | 自定义即梦端点 | `https://visual.volcengineapi.com` |
+| `JIMENG_REGION` | 即梦区域 | `cn-north-1` |
+| `SEEDREAM_BASE_URL` | 自定义豆包端点 | `https://ark.cn-beijing.volces.com/api/v3` |
 
 **服务商自动选择**：
 1. 如果指定了 `--provider` → 使用指定的
@@ -989,6 +1003,18 @@ DASHSCOPE_IMAGE_MODEL=z-image-turbo
 REPLICATE_API_TOKEN=r8_xxx
 REPLICATE_IMAGE_MODEL=google/nano-banana-pro
 # REPLICATE_BASE_URL=https://api.replicate.com
+
+# 即梦（Jimeng）
+JIMENG_ACCESS_KEY_ID=xxx
+JIMENG_SECRET_ACCESS_KEY=xxx
+JIMENG_IMAGE_MODEL=jimeng_t2i_v40
+# JIMENG_BASE_URL=https://visual.volcengineapi.com
+# JIMENG_REGION=cn-north-1
+
+# 豆包（Seedream）
+ARK_API_KEY=xxx
+SEEDREAM_IMAGE_MODEL=doubao-seedream-5-0-260128
+# SEEDREAM_BASE_URL=https://ark.cn-beijing.volces.com/api/v3
 EOF
 ```
 

docs/testing.md

@@ -0,0 +1,73 @@
+# Testing Strategy
+
+This repository has many scripts, but they do not share a single runtime or dependency graph. The lowest-risk testing strategy is to start from stable Node-based library code, then expand outward to CLI and skill-specific smoke tests.
+
+## Current Baseline
+
+- Root test runner: `node:test`
+- Entry point: `npm test`
+- Coverage command: `npm run test:coverage`
+- CI trigger: GitHub Actions on `push`, `pull_request`, and manual dispatch
+
+This avoids introducing Jest/Vitest across a repo that already mixes plain Node scripts, Bun-based skill packages, vendored code, and browser automation.
+
+## Rollout Plan
+
+### Phase 1: Stable library coverage
+
+Focus on pure functions under `scripts/lib/` first.
+
+- `scripts/lib/release-files.mjs`
+- `scripts/lib/shared-skill-packages.mjs`
+
+Goals:
+
+- Validate file filtering and release packaging rules
+- Catch regressions in package vendoring and dependency rewriting
+- Keep tests deterministic and free of network, Bun, or browser requirements
+
+### Phase 2: Root CLI integration tests
+
+Add temp-directory integration tests for root CLIs that already support dry-run or local-only flows.
+
+- `scripts/sync-shared-skill-packages.mjs`
+- `scripts/publish-skill.mjs --dry-run`
+- `scripts/sync-clawhub.mjs` argument handling and local skill discovery
+
+Goals:
+
+- Assert exit codes and stdout for common flows
+- Cover CLI argument parsing without hitting external services
+
+### Phase 3: Skill script smoke tests
+
+Add opt-in smoke tests for selected `skills/*/scripts/` packages, starting with those that:
+
+- accept local input files
+- have deterministic output
+- do not require authenticated browser sessions
+
+Examples:
+
+- markdown transforms
+- file conversion helpers
+- local content analyzers
+
+Keep browser automation, login flows, and live API publishing scripts outside the default CI path unless they are explicitly mocked.
+
+### Phase 4: Coverage gates
+
+After the stable Node path has enough breadth, add coverage thresholds in CI for the tested root modules.
+
+Recommended order:
+
+1. Start with reporting only
+2. Add line/function thresholds for `scripts/lib/**`
+3. Expand include patterns once skill-level smoke tests are reliable
+
+## Conventions For New Tests
+
+- Prefer temp directories over committed fixtures unless the fixture is reused heavily
+- Test exported functions before testing CLI wrappers
+- Avoid network, browser, and credential dependencies in default CI
+- Keep tests isolated so they can run with plain `node --test`

package.json

@@ -0,0 +1,9 @@
+{
+  "name": "baoyu-skills",
+  "private": true,
+  "type": "module",
+  "scripts": {
+    "test": "node --test",
+    "test:coverage": "node --experimental-test-coverage --test"
+  }
+}

skills/baoyu-image-gen/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: baoyu-image-gen
-description: AI image generation with OpenAI, Google, OpenRouter, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
+description: AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
 version: 1.56.2
 metadata:
   openclaw:
@@ -13,7 +13,7 @@ metadata:
 
 # Image Generation (AI SDK)
 
-Official API-based image generation. Supports OpenAI, Google, OpenRouter, DashScope (阿里通义万象) and Replicate providers.
+Official API-based image generation. Supports OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Jimeng (即梦), Seedream (豆包) and Replicate providers.
 
 ## Script Directory
 
@@ -141,13 +141,13 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `--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` | Force provider (default: auto-detect) |
+| `--provider google\|openai\|openrouter\|dashscope\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
 | `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; OpenRouter: `google/gemini-3.1-flash-image-preview`) |
 | `--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. Supported by Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal models, and Replicate |
+| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal models, and Replicate. Not supported by Jimeng or Seedream |
 | `--n <count>` | Number of images |
 | `--json` | JSON output |
 
@@ -160,11 +160,16 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `GOOGLE_API_KEY` | Google API key |
 | `DASHSCOPE_API_KEY` | DashScope API key (阿里云) |
 | `REPLICATE_API_TOKEN` | Replicate API token |
+| `JIMENG_ACCESS_KEY_ID` | Jimeng (即梦) Volcengine access key |
+| `JIMENG_SECRET_ACCESS_KEY` | Jimeng (即梦) Volcengine secret key |
+| `ARK_API_KEY` | Seedream (豆包) Volcengine ARK API key |
 | `OPENAI_IMAGE_MODEL` | OpenAI model override |
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter model override (default: `google/gemini-3.1-flash-image-preview`) |
 | `GOOGLE_IMAGE_MODEL` | Google model override |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: z-image-turbo) |
 | `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-pro) |
+| `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
+| `SEEDREAM_IMAGE_MODEL` | Seedream model override (default: doubao-seedream-5-0-260128) |
 | `OPENAI_BASE_URL` | Custom OpenAI endpoint |
 | `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint (default: `https://openrouter.ai/api/v1`) |
 | `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution |
@@ -172,6 +177,9 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `GOOGLE_BASE_URL` | Custom Google endpoint |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint |
+| `JIMENG_BASE_URL` | Custom Jimeng endpoint (default: `https://visual.volcengineapi.com`) |
+| `JIMENG_REGION` | Jimeng region (default: `cn-north-1`) |
+| `SEEDREAM_BASE_URL` | Custom Seedream endpoint (default: `https://ark.cn-beijing.volces.com/api/v3`) |
 | `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
 | `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
 | `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |
@@ -227,7 +235,7 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 
 ## Provider Selection
 
-1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI, then OpenRouter, then Replicate
+1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI, then OpenRouter, then Replicate (Jimeng and Seedream do not support reference images)
 2. `--provider` specified → use it (if `--ref`, must be `google`, `openai`, `openrouter`, or `replicate`)
 3. Only one API key available → use that provider
 4. Multiple available → default to Google

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

@@ -1,6 +1,7 @@
 import path from "node:path";
 import process from "node:process";
 import { homedir } from "node:os";
+import { fileURLToPath } from "node:url";
 import { access, mkdir, readFile, writeFile } from "node:fs/promises";
 import type {
   BatchFile,
@@ -55,6 +56,8 @@ const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
   openai: { concurrency: 3, startIntervalMs: 1100 },
   openrouter: { concurrency: 3, startIntervalMs: 1100 },
   dashscope: { concurrency: 3, startIntervalMs: 1100 },
+  jimeng: { concurrency: 3, startIntervalMs: 1100 },
+  seedream: { concurrency: 3, startIntervalMs: 1100 },
 };
 
 function printUsage(): void {
@@ -69,7 +72,7 @@ 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  Force provider (auto-detect by default)
+  --provider google|openai|openrouter|dashscope|replicate|jimeng|seedream  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)
@@ -107,11 +110,16 @@ Environment variables:
   GEMINI_API_KEY            Gemini API key (alias for GOOGLE_API_KEY)
   DASHSCOPE_API_KEY         DashScope API key
   REPLICATE_API_TOKEN       Replicate API token
+  JIMENG_ACCESS_KEY_ID      Jimeng Access Key ID
+  JIMENG_SECRET_ACCESS_KEY  Jimeng Secret Access Key
+  ARK_API_KEY               Seedream/Ark API key
   OPENAI_IMAGE_MODEL        Default OpenAI model (gpt-image-1.5)
   OPENROUTER_IMAGE_MODEL    Default OpenRouter model (google/gemini-3.1-flash-image-preview)
   GOOGLE_IMAGE_MODEL        Default Google model (gemini-3-pro-image-preview)
   DASHSCOPE_IMAGE_MODEL     Default DashScope model (z-image-turbo)
   REPLICATE_IMAGE_MODEL     Default Replicate model (google/nano-banana-pro)
+  JIMENG_IMAGE_MODEL        Default Jimeng model (jimeng_t2i_v40)
+  SEEDREAM_IMAGE_MODEL      Default Seedream model (doubao-seedream-5-0-260128)
   OPENAI_BASE_URL           Custom OpenAI endpoint
   OPENAI_IMAGE_USE_CHAT     Use /chat/completions instead of /images/generations (true|false)
   OPENROUTER_BASE_URL       Custom OpenRouter endpoint
@@ -120,6 +128,8 @@ Environment variables:
   GOOGLE_BASE_URL           Custom Google endpoint
   DASHSCOPE_BASE_URL        Custom DashScope endpoint
   REPLICATE_BASE_URL        Custom Replicate endpoint
+  JIMENG_BASE_URL           Custom Jimeng endpoint
+  SEEDREAM_BASE_URL         Custom Seedream endpoint
   BAOYU_IMAGE_GEN_MAX_WORKERS  Override batch worker cap
   BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY  Override provider concurrency
   BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS  Override provider start gap in ms
@@ -127,7 +137,7 @@ Environment variables:
 Env file load order: CLI args > EXTEND.md > process.env > <cwd>/.baoyu-skills/.env > ~/.baoyu-skills/.env`);
 }
 
-function parseArgs(argv: string[]): CliArgs {
+export function parseArgs(argv: string[]): CliArgs {
   const out: CliArgs = {
     prompt: null,
     promptFiles: [],
@@ -217,7 +227,9 @@ function parseArgs(argv: string[]): CliArgs {
         v !== "openai" &&
         v !== "openrouter" &&
         v !== "dashscope" &&
-        v !== "replicate"
+        v !== "replicate" &&
+        v !== "jimeng" &&
+        v !== "seedream"
       ) {
         throw new Error(`Invalid provider: ${v}`);
       }
@@ -327,12 +339,12 @@ async function loadEnv(): Promise<void> {
   }
 }
 
-function extractYamlFrontMatter(content: string): string | null {
+export function extractYamlFrontMatter(content: string): string | null {
   const match = content.match(/^---\s*\n([\s\S]*?)\n---\s*$/m);
   return match ? match[1] : null;
 }
 
-function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
+export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
   const config: Partial<ExtendConfig> = {};
   const lines = yaml.split("\n");
   let currentKey: string | null = null;
@@ -370,6 +382,8 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           openrouter: null,
           dashscope: null,
           replicate: null,
+          jimeng: null,
+          seedream: null,
         };
         currentKey = "default_model";
         currentProvider = null;
@@ -393,7 +407,9 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
-          key === "replicate"
+          key === "replicate" ||
+          key === "jimeng" ||
+          key === "seedream"
         )
       ) {
         config.batch ??= {};
@@ -407,7 +423,9 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
-          key === "replicate"
+          key === "replicate" ||
+          key === "jimeng" ||
+          key === "seedream"
         )
       ) {
         const cleaned = value.replace(/['"]/g, "");
@@ -456,7 +474,7 @@ async function loadExtendConfig(): Promise<Partial<ExtendConfig>> {
   return {};
 }
 
-function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
+export function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
   return {
     ...args,
     provider: args.provider ?? extend.default_provider ?? null,
@@ -466,13 +484,13 @@ function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
   };
 }
 
-function parsePositiveInt(value: string | undefined): number | null {
+export function parsePositiveInt(value: string | undefined): number | null {
   if (!value) return null;
   const parsed = parseInt(value, 10);
   return Number.isFinite(parsed) && parsed > 0 ? parsed : null;
 }
 
-function parsePositiveBatchInt(value: unknown): number | null {
+export function parsePositiveBatchInt(value: unknown): number | null {
   if (value === null || value === undefined) return null;
   if (typeof value === "number") {
     return Number.isInteger(value) && value > 0 ? value : null;
@@ -483,13 +501,13 @@ function parsePositiveBatchInt(value: unknown): number | null {
   return null;
 }
 
-function getConfiguredMaxWorkers(extendConfig: Partial<ExtendConfig>): number {
+export function getConfiguredMaxWorkers(extendConfig: Partial<ExtendConfig>): number {
   const envValue = parsePositiveInt(process.env.BAOYU_IMAGE_GEN_MAX_WORKERS);
   const configValue = extendConfig.batch?.max_workers ?? null;
   return Math.max(1, envValue ?? configValue ?? DEFAULT_MAX_WORKERS);
 }
 
-function getConfiguredProviderRateLimits(
+export function getConfiguredProviderRateLimits(
   extendConfig: Partial<ExtendConfig>
 ): Record<Provider, ProviderRateLimit> {
   const configured: Record<Provider, ProviderRateLimit> = {
@@ -498,9 +516,11 @@ function getConfiguredProviderRateLimits(
     openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
     openrouter: { ...DEFAULT_PROVIDER_RATE_LIMITS.openrouter },
     dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
+    jimeng: { ...DEFAULT_PROVIDER_RATE_LIMITS.jimeng },
+    seedream: { ...DEFAULT_PROVIDER_RATE_LIMITS.seedream },
   };
 
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream"] as Provider[]) {
     const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
     const extendLimit = extendConfig.batch?.provider_limits?.[provider];
     configured[provider] = {
@@ -540,14 +560,14 @@ async function readPromptFromStdin(): Promise<string | null> {
   }
 }
 
-function normalizeOutputImagePath(p: string): string {
+export function normalizeOutputImagePath(p: string): string {
   const full = path.resolve(p);
   const ext = path.extname(full);
   if (ext) return full;
   return `${full}.png`;
 }
 
-function detectProvider(args: CliArgs): Provider {
+export function detectProvider(args: CliArgs): Provider {
   if (
     args.referenceImages.length > 0 &&
     args.provider &&
@@ -568,6 +588,8 @@ function detectProvider(args: CliArgs): Provider {
   const hasOpenrouter = !!process.env.OPENROUTER_API_KEY;
   const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
   const hasReplicate = !!process.env.REPLICATE_API_TOKEN;
+  const hasJimeng = !!(process.env.JIMENG_ACCESS_KEY_ID && process.env.JIMENG_SECRET_ACCESS_KEY);
+  const hasSeedream = !!process.env.ARK_API_KEY;
 
   if (args.referenceImages.length > 0) {
     if (hasGoogle) return "google";
@@ -575,7 +597,7 @@ function detectProvider(args: CliArgs): Provider {
     if (hasOpenrouter) return "openrouter";
     if (hasReplicate) return "replicate";
     throw new Error(
-      "Reference images require Google, OpenAI, OpenRouter or Replicate. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, or REPLICATE_API_TOKEN, or remove --ref."
+      "Reference images require Google, OpenAI, OpenRouter, or Replicate. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, or REPLICATE_API_TOKEN, or remove --ref."
     );
   }
 
@@ -585,18 +607,20 @@ function detectProvider(args: CliArgs): Provider {
     hasOpenrouter && "openrouter",
     hasDashscope && "dashscope",
     hasReplicate && "replicate",
+    hasJimeng && "jimeng",
+    hasSeedream && "seedream",
   ].filter(Boolean) as Provider[];
 
   if (available.length === 1) return available[0]!;
   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, or REPLICATE_API_TOKEN.\n" +
+    "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" +
       "Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
   );
 }
 
-async function validateReferenceImages(referenceImages: string[]): Promise<void> {
+export async function validateReferenceImages(referenceImages: string[]): Promise<void> {
   for (const refPath of referenceImages) {
     const fullPath = path.resolve(refPath);
     try {
@@ -607,7 +631,7 @@ async function validateReferenceImages(referenceImages: string[]): Promise<void>
   }
 }
 
-function isRetryableGenerationError(error: unknown): boolean {
+export function isRetryableGenerationError(error: unknown): boolean {
   const msg = error instanceof Error ? error.message : String(error);
   const nonRetryableMarkers = [
     "Reference image",
@@ -632,6 +656,8 @@ async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
   if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
   if (provider === "replicate") return (await import("./providers/replicate")) as 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;
   return (await import("./providers/openai")) as ProviderModule;
 }
 
@@ -658,6 +684,8 @@ function getModelForProvider(
     }
     if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
     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;
   }
   return providerModule.getDefaultModel();
 }
@@ -685,7 +713,7 @@ async function prepareSingleTask(args: CliArgs, extendConfig: Partial<ExtendConf
   };
 }
 
-async function loadBatchTasks(batchFilePath: string): Promise<LoadedBatchTasks> {
+export async function loadBatchTasks(batchFilePath: string): Promise<LoadedBatchTasks> {
   const resolvedBatchFilePath = path.resolve(batchFilePath);
   const content = await readFile(resolvedBatchFilePath, "utf8");
   const parsed = JSON.parse(content.replace(/^\uFEFF/, "")) as BatchFile;
@@ -711,11 +739,11 @@ async function loadBatchTasks(batchFilePath: string): Promise<LoadedBatchTasks>
   throw new Error("Invalid batch file. Expected an array of tasks or an object with a tasks array.");
 }
 
-function resolveBatchPath(batchDir: string, filePath: string): string {
+export function resolveBatchPath(batchDir: string, filePath: string): string {
   return path.isAbsolute(filePath) ? filePath : path.resolve(batchDir, filePath);
 }
 
-function createTaskArgs(baseArgs: CliArgs, task: BatchTaskInput, batchDir: string): CliArgs {
+export function createTaskArgs(baseArgs: CliArgs, task: BatchTaskInput, batchDir: string): CliArgs {
   return {
     ...baseArgs,
     prompt: task.prompt ?? null,
@@ -854,7 +882,7 @@ function createProviderGate(providerRateLimits: Record<Provider, ProviderRateLim
   };
 }
 
-function getWorkerCount(taskCount: number, jobs: number | null, maxWorkers: number): number {
+export function getWorkerCount(taskCount: number, jobs: number | null, maxWorkers: number): number {
   const requested = jobs ?? Math.min(taskCount, maxWorkers);
   return Math.max(1, Math.min(requested, taskCount, maxWorkers));
 }
@@ -873,7 +901,7 @@ 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", "dashscope"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream"] as Provider[]) {
     const limit = providerRateLimits[provider];
     console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
   }
@@ -984,8 +1012,21 @@ async function main(): Promise<void> {
   await runSingleMode(mergedArgs, extendConfig);
 }
 
-main().catch((error) => {
-  const message = error instanceof Error ? error.message : String(error);
-  console.error(message);
-  process.exit(1);
-});
+function isDirectExecution(metaUrl: string): boolean {
+  const entryPath = process.argv[1];
+  if (!entryPath) return false;
+
+  try {
+    return path.resolve(entryPath) === fileURLToPath(metaUrl);
+  } catch {
+    return false;
+  }
+}
+
+if (isDirectExecution(import.meta.url)) {
+  main().catch((error) => {
+    const message = error instanceof Error ? error.message : String(error);
+    console.error(message);
+    process.exit(1);
+  });
+}

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

@@ -13,7 +13,7 @@ function getBaseUrl(): string {
   return base.replace(/\/+$/g, "");
 }
 
-function parseAspectRatio(ar: string): { width: number; height: number } | null {
+export function parseAspectRatio(ar: string): { width: number; height: number } | null {
   const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
   if (!match) return null;
   const w = parseFloat(match[1]!);
@@ -45,7 +45,7 @@ const STANDARD_SIZES_2K: [number, number][] = [
   [2048, 2048],
 ];
 
-function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
+export function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
   const is2k = quality === "2k";
   const defaultSize = is2k ? "1536*1536" : "1024*1024";
 
@@ -71,7 +71,7 @@ function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]):
   return best;
 }
 
-function normalizeSize(size: string): string {
+export function normalizeSize(size: string): string {
   return size.replace("x", "*");
 }
 

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

@@ -17,16 +17,16 @@ export function getDefaultModel(): string {
   return process.env.GOOGLE_IMAGE_MODEL || "gemini-3-pro-image-preview";
 }
 
-function normalizeGoogleModelId(model: string): string {
+export function normalizeGoogleModelId(model: string): string {
   return model.startsWith("models/") ? model.slice("models/".length) : model;
 }
 
-function isGoogleMultimodal(model: string): boolean {
+export function isGoogleMultimodal(model: string): boolean {
   const normalized = normalizeGoogleModelId(model);
   return GOOGLE_MULTIMODAL_MODELS.some((m) => normalized.includes(m));
 }
 
-function isGoogleImagen(model: string): boolean {
+export function isGoogleImagen(model: string): boolean {
   const normalized = normalizeGoogleModelId(model);
   return GOOGLE_IMAGEN_MODELS.some((m) => normalized.includes(m));
 }
@@ -35,7 +35,7 @@ function getGoogleApiKey(): string | null {
   return process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY || null;
 }
 
-function getGoogleImageSize(args: CliArgs): "1K" | "2K" | "4K" {
+export function getGoogleImageSize(args: CliArgs): "1K" | "2K" | "4K" {
   if (args.imageSize) return args.imageSize as "1K" | "2K" | "4K";
   return args.quality === "2k" ? "2K" : "1K";
 }
@@ -46,7 +46,7 @@ function getGoogleBaseUrl(): string {
   return base.replace(/\/+$/g, "");
 }
 
-function buildGoogleUrl(pathname: string): string {
+export function buildGoogleUrl(pathname: string): string {
   const base = getGoogleBaseUrl();
   const cleanedPath = pathname.replace(/^\/+/g, "");
   if (base.endsWith("/v1beta")) return `${base}/${cleanedPath}`;
@@ -162,7 +162,7 @@ async function postGoogleJson<T>(pathname: string, body: unknown): Promise<T> {
   return postGoogleJsonViaFetch<T>(url, apiKey, body);
 }
 
-function buildPromptWithAspect(
+export function buildPromptWithAspect(
   prompt: string,
   ar: string | null,
   quality: CliArgs["quality"],
@@ -177,7 +177,7 @@ function buildPromptWithAspect(
   return result;
 }
 
-function addAspectRatioToPrompt(prompt: string, ar: string | null): string {
+export function addAspectRatioToPrompt(prompt: string, ar: string | null): string {
   if (!ar) return prompt;
   return `${prompt} Aspect ratio: ${ar}.`;
 }
@@ -194,7 +194,7 @@ async function readImageAsBase64(
   return { data: buf.toString("base64"), mimeType };
 }
 
-function extractInlineImageData(response: {
+export function extractInlineImageData(response: {
   candidates?: Array<{
     content?: { parts?: Array<{ inlineData?: { data?: string } }> };
   }>;
@@ -208,7 +208,7 @@ function extractInlineImageData(response: {
   return null;
 }
 
-function extractPredictedImageData(response: {
+export function extractPredictedImageData(response: {
   predictions?: Array<any>;
   generatedImages?: Array<any>;
 }): string | null {

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

@@ -0,0 +1,467 @@
+import type { CliArgs } from "../types";
+import * as crypto from "node:crypto";
+
+type JimengSizePreset = "normal" | "2k" | "4k";
+
+export function getDefaultModel(): string {
+  return process.env.JIMENG_IMAGE_MODEL || "jimeng_t2i_v40";
+}
+
+function getAccessKey(): string | null {
+  return process.env.JIMENG_ACCESS_KEY_ID || null;
+}
+
+function getSecretKey(): string | null {
+  return process.env.JIMENG_SECRET_ACCESS_KEY || null;
+}
+
+function getRegion(): string {
+  return process.env.JIMENG_REGION || "cn-north-1";
+}
+
+function getBaseUrl(): string {
+  return process.env.JIMENG_BASE_URL || "https://visual.volcengineapi.com";
+}
+
+function resolveEndpoint(query: Record<string, string>): {
+  url: string;
+  host: string;
+  canonicalUri: string;
+} {
+  let baseUrl: URL;
+  try {
+    baseUrl = new URL(getBaseUrl());
+  } catch {
+    throw new Error(`Invalid JIMENG_BASE_URL: ${getBaseUrl()}`);
+  }
+
+  baseUrl.search = "";
+  for (const [key, value] of Object.entries(query).sort(([a], [b]) => a.localeCompare(b))) {
+    baseUrl.searchParams.set(key, value);
+  }
+
+  return {
+    url: baseUrl.toString(),
+    host: baseUrl.host,
+    canonicalUri: baseUrl.pathname || "/",
+  };
+}
+
+/**
+ * Volcengine HMAC-SHA256 signature generation
+ * Following the official documentation at:
+ * https://www.volcengine.com/docs/85621/1817045
+ */
+function generateSignature(
+  method: string,
+  query: Record<string, string>,
+  headers: Record<string, string>,
+  body: string,
+  accessKey: string,
+  secretKey: string,
+  region: string,
+  service: string,
+  canonicalUri: string
+): string {
+  // 1. Create canonical request
+  // Sort query parameters alphabetically
+  const sortedQuery = Object.entries(query)
+    .sort(([a], [b]) => a.localeCompare(b))
+    .map(([k, v]) => `${encodeURIComponent(k)}=${encodeURIComponent(v)}`)
+    .join("&");
+
+  // Sort headers alphabetically and create canonical headers
+  const sortedHeaders = Object.entries(headers)
+    .sort(([a], [b]) => a.localeCompare(b))
+    .map(([k, v]) => `${k.toLowerCase()}:${v.trim()}\n`)
+    .join("");
+
+  const signedHeaders = Object.keys(headers)
+    .sort()
+    .map(k => k.toLowerCase())
+    .join(";");
+
+  const hashedPayload = crypto.createHash("sha256").update(body, "utf8").digest("hex");
+
+  const canonicalRequest = [
+    method,
+    canonicalUri,
+    sortedQuery,
+    sortedHeaders,
+    signedHeaders,
+    hashedPayload,
+  ].join("\n");
+
+  const hashedCanonicalRequest = crypto
+    .createHash("sha256")
+    .update(canonicalRequest, "utf8")
+    .digest("hex");
+
+  // 2. Create string to sign
+  const algorithm = "HMAC-SHA256";
+  const timestamp = headers["X-Date"] || headers["x-date"];
+  if (!timestamp) {
+    throw new Error("Jimeng signature generation requires an X-Date header.");
+  }
+  const dateStamp = timestamp.slice(0, 8);
+
+  const credentialScope = `${dateStamp}/${region}/${service}/request`;
+
+  const stringToSign = [
+    algorithm,
+    timestamp,
+    credentialScope,
+    hashedCanonicalRequest,
+  ].join("\n");
+
+  // 3. Calculate signature
+  const kDate = crypto
+    .createHmac("sha256", secretKey)
+    .update(dateStamp)
+    .digest();
+
+  const kRegion = crypto.createHmac("sha256", kDate).update(region).digest();
+  const kService = crypto.createHmac("sha256", kRegion).update(service).digest();
+  const kSigning = crypto.createHmac("sha256", kService).update("request").digest();
+
+  const signature = crypto
+    .createHmac("sha256", kSigning)
+    .update(stringToSign)
+    .digest("hex");
+
+  // 4. Create authorization header
+  return `${algorithm} Credential=${accessKey}/${credentialScope}, SignedHeaders=${signedHeaders}, Signature=${signature}`;
+}
+
+/**
+ * Parse aspect ratio string like "16:9", "1:1", "4:3" into width and height
+ */
+function parseAspectRatio(ar: string): { width: number; height: number } | null {
+  const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
+  if (!match) return null;
+  const w = parseFloat(match[1]!);
+  const h = parseFloat(match[2]!);
+  if (w <= 0 || h <= 0) return null;
+  return { width: w, height: h };
+}
+
+/**
+ * Supported size presets for different quality levels
+ * Based on Volcengine Jimeng documentation
+ */
+const SIZE_PRESETS: Record<string, Record<string, string>> = {
+  normal: {
+    "1:1": "1024x1024",
+    "4:3": "1360x1020",
+    "16:9": "1536x864",
+    "3:2": "1440x960",
+    "21:9": "1920x824",
+  },
+  "2k": {
+    "1:1": "2048x2048",
+    "4:3": "2304x1728",
+    "16:9": "2560x1440",
+    "3:2": "2496x1664",
+    "21:9": "3024x1296",
+  },
+  "4k": {
+    "1:1": "4096x4096",
+    "4:3": "4694x3520",
+    "16:9": "5404x3040",
+    "3:2": "4992x3328",
+    "21:9": "6198x2656",
+  },
+};
+
+function normalizeDimensions(value: string): string | null {
+  const match = value.trim().match(/^(\d+)\s*[xX*]\s*(\d+)$/);
+  if (!match) return null;
+  return `${match[1]}x${match[2]}`;
+}
+
+function getClosestPresetSize(ar: string | null, qualityLevel: JimengSizePreset): string {
+  const presets = SIZE_PRESETS[qualityLevel];
+  const defaultSize = presets["1:1"]!;
+
+  if (!ar) return defaultSize;
+
+  const parsed = parseAspectRatio(ar);
+  if (!parsed) return defaultSize;
+
+  const targetRatio = parsed.width / parsed.height;
+  let bestMatch = defaultSize;
+  let bestDiff = Infinity;
+
+  for (const [ratio, size] of Object.entries(presets)) {
+    const [w, h] = ratio.split(":").map(Number);
+    const presetRatio = w / h;
+    const diff = Math.abs(presetRatio - targetRatio);
+    if (diff < bestDiff) {
+      bestDiff = diff;
+      bestMatch = size;
+    }
+  }
+
+  return bestMatch;
+}
+
+function normalizeImageSizePreset(imageSize: string, ar: string | null): string | null {
+  const preset = imageSize.trim().toUpperCase();
+  if (preset === "1K") return getClosestPresetSize(ar, "normal");
+  if (preset === "2K") return getClosestPresetSize(ar, "2k");
+  if (preset === "4K") return getClosestPresetSize(ar, "4k");
+  return normalizeDimensions(imageSize);
+}
+
+function getImageSize(ar: string | null, quality: CliArgs["quality"], imageSize?: string | null): string {
+  if (imageSize) {
+    const normalizedSize = normalizeImageSizePreset(imageSize, ar);
+    if (normalizedSize) return normalizedSize;
+  }
+
+  // Default to 2K quality if not specified
+  const qualityLevel: JimengSizePreset = quality === "normal" ? "normal" : "2k";
+  return getClosestPresetSize(ar, qualityLevel);
+}
+
+/**
+ * Step 1: Submit async task to Volcengine Jimeng API
+ */
+async function submitTask(
+  prompt: string,
+  model: string,
+  size: string,
+  accessKey: string,
+  secretKey: string,
+  region: string
+): Promise<string> {
+  // Query parameters for submit endpoint
+  const query = {
+    Action: "CVSync2AsyncSubmitTask",
+    Version: "2022-08-31",
+  };
+  const endpoint = resolveEndpoint(query);
+
+  // Request body - Jimeng API expects width/height as separate integers
+  const [width, height] = size.split("x").map(Number);
+  const bodyObj = {
+    req_key: model,
+    prompt_text: prompt,
+    // Use separate width and height parameters instead of size string
+    width: width,
+    height: height,
+    // Optional: seed for reproducibility
+    // seed: Math.floor(Math.random() * 999999),
+  };
+
+  const body = JSON.stringify(bodyObj);
+
+  // Headers
+  const timestampHeader = new Date().toISOString().replace(/[:\-]|\.\d{3}/g, "");
+  const headers = {
+    "Content-Type": "application/json",
+    "X-Date": timestampHeader,
+    "Host": endpoint.host,
+  };
+
+  // Generate signature
+  const authorization = generateSignature(
+    "POST",
+    query,
+    headers,
+    body,
+    accessKey,
+    secretKey,
+    region,
+    "cv",
+    endpoint.canonicalUri
+  );
+
+  console.error(`Submitting task to Jimeng (${model})...`, { width, height });
+
+  const res = await fetch(endpoint.url, {
+    method: "POST",
+    headers: {
+      ...headers,
+      "Authorization": authorization,
+    },
+    body,
+  });
+
+  if (!res.ok) {
+    const err = await res.text();
+    throw new Error(`Jimeng API submit error (${res.status}): ${err}`);
+  }
+
+  const result = (await res.json()) as {
+    code?: number;
+    message?: string;
+    data?: {
+      task_id?: string;
+    };
+  };
+
+  // Volcengine API returns code 10000 for success
+  if (result.code !== 10000 || !result.data?.task_id) {
+    console.error("Submit response:", JSON.stringify(result, null, 2));
+    throw new Error(`Failed to submit task: ${result.message || "Unknown error"}`);
+  }
+
+  return result.data.task_id;
+}
+
+/**
+ * Step 2: Poll for task result
+ * Returns image data directly as Uint8Array
+ */
+async function pollForResult(
+  taskId: string,
+  model: string,
+  accessKey: string,
+  secretKey: string,
+  region: string
+): Promise<Uint8Array> {
+  const maxAttempts = 60;
+  const pollIntervalMs = 2000;
+
+  for (let attempt = 0; attempt < maxAttempts; attempt++) {
+    // Query parameters for result endpoint
+    const query = {
+      Action: "CVSync2AsyncGetResult",
+      Version: "2022-08-31",
+    };
+    const endpoint = resolveEndpoint(query);
+
+    // Request body - include req_key and task_id
+    const bodyObj = {
+      req_key: model,
+      task_id: taskId,
+    };
+
+    const body = JSON.stringify(bodyObj);
+
+    // Headers
+    const timestampHeader = new Date().toISOString().replace(/[:\-]|\.\d{3}/g, "");
+    const headers = {
+      "Content-Type": "application/json",
+      "X-Date": timestampHeader,
+      "Host": endpoint.host,
+    };
+
+    // Generate signature
+    const authorization = generateSignature(
+      "POST",
+      query,
+      headers,
+      body,
+      accessKey,
+      secretKey,
+      region,
+      "cv",
+      endpoint.canonicalUri
+    );
+
+    const res = await fetch(endpoint.url, {
+      method: "POST",
+      headers: {
+        ...headers,
+        "Authorization": authorization,
+      },
+      body,
+    });
+
+    if (!res.ok) {
+      const err = await res.text();
+      throw new Error(`Jimeng API poll error (${res.status}): ${err}`);
+    }
+
+    const result = (await res.json()) as {
+      code?: number;
+      message?: string;
+      data?: {
+        status?: string;
+        image_urls?: string[];
+        binary_data_base64?: string[];
+      };
+    };
+
+    // Volcengine API returns code 10000 for success
+    if (result.code === 10000 && result.data) {
+      const { status, image_urls, binary_data_base64 } = result.data;
+
+      // Check for base64 image data (preferred by Jimeng)
+      if (binary_data_base64 && binary_data_base64.length > 0) {
+        console.error("Image received as base64 data");
+        const base64Data = binary_data_base64[0]!;
+        // Convert base64 to Uint8Array
+        const binaryString = Buffer.from(base64Data, "base64").toString("binary");
+        const bytes = new Uint8Array(binaryString.length);
+        for (let i = 0; i < binaryString.length; i++) {
+          bytes[i] = binaryString.charCodeAt(i);
+        }
+        return bytes;
+      }
+
+      // Fallback to URL format
+      if (status === "done" && image_urls && image_urls.length > 0) {
+        // Download from URL
+        console.error(`Downloading image from ${image_urls[0]}...`);
+        const imgRes = await fetch(image_urls[0]!);
+        if (!imgRes.ok) {
+          throw new Error(`Failed to download image from ${image_urls[0]}`);
+        }
+        const buffer = await imgRes.arrayBuffer();
+        return new Uint8Array(buffer);
+      }
+
+      if (status === "in_queue" || status === "generating") {
+        console.error(`Task status: ${status} (${attempt + 1}/${maxAttempts})`);
+        await new Promise(resolve => setTimeout(resolve, pollIntervalMs));
+        continue;
+      }
+
+      if (status === "fail") {
+        throw new Error(`Jimeng task failed: ${result.message || "Generation failed"}`);
+      }
+    }
+
+    console.error("Poll response:", JSON.stringify(result, null, 2));
+    throw new Error(`Unexpected response during polling: ${result.message || "Unknown error"}`);
+  }
+
+  throw new Error("Task timeout: image generation took too long");
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  if (args.referenceImages.length > 0) {
+    throw new Error(
+      "Jimeng does not support reference images. Use --provider google, openai, openrouter, or replicate."
+    );
+  }
+
+  const accessKey = getAccessKey();
+  const secretKey = getSecretKey();
+  const region = getRegion();
+
+  if (!accessKey || !secretKey) {
+    throw new Error(
+      "JIMENG_ACCESS_KEY_ID and JIMENG_SECRET_ACCESS_KEY are required. " +
+      "Get your credentials from https://console.volcengine.com/iam/keymanage"
+    );
+  }
+
+  const size = getImageSize(args.aspectRatio, args.quality, args.imageSize);
+
+  // Step 1: Submit task
+  const taskId = await submitTask(prompt, model, size, accessKey, secretKey, region);
+
+  // Step 2: Poll for result (returns image data directly)
+  const imageData = await pollForResult(taskId, model, accessKey, secretKey, region);
+
+  console.error("Image generation complete!");
+  return imageData;
+}

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

@@ -8,7 +8,7 @@ export function getDefaultModel(): string {
 
 type OpenAIImageResponse = { data: Array<{ url?: string; b64_json?: string }> };
 
-function parseAspectRatio(ar: string): { width: number; height: number } | null {
+export function parseAspectRatio(ar: string): { width: number; height: number } | null {
   const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
   if (!match) return null;
   const w = parseFloat(match[1]!);
@@ -23,7 +23,7 @@ type SizeMapping = {
   portrait: string;
 };
 
-function getOpenAISize(
+export function getOpenAISize(
   model: string,
   ar: string | null,
   quality: CliArgs["quality"]
@@ -201,7 +201,7 @@ async function generateWithOpenAIEdits(
   return extractImageFromResponse(result);
 }
 
-function getMimeType(filename: string): string {
+export function getMimeType(filename: string): string {
   const ext = path.extname(filename).toLowerCase();
   if (ext === ".jpg" || ext === ".jpeg") return "image/jpeg";
   if (ext === ".webp") return "image/webp";
@@ -209,7 +209,7 @@ function getMimeType(filename: string): string {
   return "image/png";
 }
 
-async function extractImageFromResponse(result: OpenAIImageResponse): Promise<Uint8Array> {
+export async function extractImageFromResponse(result: OpenAIImageResponse): Promise<Uint8Array> {
   const img = result.data[0];
 
   if (img?.b64_json) {

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

@@ -20,7 +20,7 @@ function getBaseUrl(): string {
   return base.replace(/\/+$/g, "");
 }
 
-function parseModelId(model: string): { owner: string; name: string; version: string | null } {
+export function parseModelId(model: string): { owner: string; name: string; version: string | null } {
   const [ownerName, version] = model.split(":");
   const parts = ownerName!.split("/");
   if (parts.length !== 2 || !parts[0] || !parts[1]) {
@@ -31,7 +31,7 @@ function parseModelId(model: string): { owner: string; name: string; version: st
   return { owner: parts[0], name: parts[1], version: version || null };
 }
 
-function buildInput(prompt: string, args: CliArgs, referenceImages: string[]): Record<string, unknown> {
+export function buildInput(prompt: string, args: CliArgs, referenceImages: string[]): Record<string, unknown> {
   const input: Record<string, unknown> = { prompt };
 
   if (args.aspectRatio) {
@@ -144,7 +144,7 @@ async function pollPrediction(apiToken: string, getUrl: string): Promise<Predict
   throw new Error(`Replicate prediction timed out after ${MAX_POLL_MS / 1000}s`);
 }
 
-function extractOutputUrl(prediction: PredictionResponse): string {
+export function extractOutputUrl(prediction: PredictionResponse): string {
   const output = prediction.output;
 
   if (typeof output === "string") return output;

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

@@ -0,0 +1,111 @@
+import type { CliArgs } from "../types";
+
+export function getDefaultModel(): string {
+  return process.env.SEEDREAM_IMAGE_MODEL || "doubao-seedream-5-0-260128";
+}
+
+function getApiKey(): string | null {
+  return process.env.ARK_API_KEY || null;
+}
+
+function getBaseUrl(): string {
+  return process.env.SEEDREAM_BASE_URL || "https://ark.cn-beijing.volces.com/api/v3";
+}
+
+/**
+ * Convert aspect ratio to Seedream size format
+ * Seedream API accepts: "2k" (default), "3k", or WIDTHxHEIGHT format
+ * Note: API uses lowercase "2k"/"3k", not "2K"/"3K"
+ */
+function getSeedreamSize(ar: string | null, quality: CliArgs["quality"], imageSize?: string | null): string {
+  // If explicit size is provided
+  if (imageSize) {
+    const upper = imageSize.toUpperCase();
+    if (upper === "2K" || upper === "3K") {
+      return upper.toLowerCase(); // API expects "2k" or "3k"
+    }
+    // For widthxheight format, pass through as-is
+    if (imageSize.includes("x")) {
+      return imageSize;
+    }
+  }
+
+  // Default to 2k (smallest option supported by API)
+  return "2k";
+}
+
+type SeedreamImageResponse = {
+  model: string;
+  created: number;
+  data: Array<{
+    url: string;
+    size: string;
+  }>;
+  usage: {
+    generated_images: number;
+    output_tokens: number;
+    total_tokens: number;
+  };
+};
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  const apiKey = getApiKey();
+  if (!apiKey) {
+    throw new Error(
+      "ARK_API_KEY is required. " +
+        "Get your API key from https://console.volcengine.com/ark"
+    );
+  }
+
+  const baseUrl = getBaseUrl();
+  const size = getSeedreamSize(args.aspectRatio, args.quality, args.imageSize);
+
+  console.error(`Calling Seedream API (${model}) with size: ${size}`);
+
+  const requestBody = {
+    model,
+    prompt,
+    size,
+    output_format: "png",
+    watermark: false,
+  };
+
+  const response = await fetch(`${baseUrl}/images/generations`, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${apiKey}`,
+    },
+    body: JSON.stringify(requestBody),
+  });
+
+  if (!response.ok) {
+    const err = await response.text();
+    throw new Error(`Seedream API error (${response.status}): ${err}`);
+  }
+
+  const result = (await response.json()) as SeedreamImageResponse;
+
+  if (!result.data || result.data.length === 0) {
+    throw new Error("No image data in Seedream response");
+  }
+
+  const imageUrl = result.data[0].url;
+  if (!imageUrl) {
+    throw new Error("No image URL in Seedream response");
+  }
+
+  // Download image from URL
+  console.error(`Downloading image from ${imageUrl}...`);
+  const imgResponse = await fetch(imageUrl);
+  if (!imgResponse.ok) {
+    throw new Error(`Failed to download image from ${imageUrl}`);
+  }
+
+  const buffer = await imgResponse.arrayBuffer();
+  return new Uint8Array(buffer);
+}

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

@@ -1,4 +1,4 @@
-export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate";
+export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate" | "jimeng" | "seedream";
 export type Quality = "normal" | "2k";
 
 export type CliArgs = {
@@ -53,6 +53,8 @@ export type ExtendConfig = {
     openrouter: string | null;
     dashscope: string | null;
     replicate: string | null;
+    jimeng: string | null;
+    seedream: string | null;
   };
   batch?: {
     max_workers?: number | null;

tests/release-files.test.mjs

@@ -0,0 +1,110 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test from "node:test";
+
+import {
+  listReleaseFiles,
+  validateSelfContainedRelease,
+} from "../scripts/lib/release-files.mjs";
+
+async function makeTempDir(prefix) {
+  return fs.mkdtemp(path.join(os.tmpdir(), prefix));
+}
+
+async function writeFile(filePath, contents = "") {
+  await fs.mkdir(path.dirname(filePath), { recursive: true });
+  await fs.writeFile(filePath, contents);
+}
+
+async function writeJson(filePath, value) {
+  await writeFile(filePath, `${JSON.stringify(value, null, 2)}\n`);
+}
+
+test("listReleaseFiles skips generated paths and returns sorted relative paths", async (t) => {
+  const root = await makeTempDir("baoyu-release-files-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  await writeFile(path.join(root, "b.txt"), "b");
+  await writeFile(path.join(root, "a.txt"), "a");
+  await writeFile(path.join(root, "nested", "keep.txt"), "keep");
+  await writeFile(path.join(root, "node_modules", "skip.js"), "skip");
+  await writeFile(path.join(root, ".git", "config"), "skip");
+  await writeFile(path.join(root, "dist", "artifact.txt"), "skip");
+  await writeFile(path.join(root, "out", "artifact.txt"), "skip");
+  await writeFile(path.join(root, "build", "artifact.txt"), "skip");
+  await writeFile(path.join(root, ".DS_Store"), "skip");
+  await writeFile(path.join(root, "bun.lockb"), "skip");
+
+  const files = await listReleaseFiles(root);
+
+  assert.deepEqual(
+    files.map((file) => file.relPath),
+    ["a.txt", "b.txt", "nested/keep.txt"],
+  );
+});
+
+test("validateSelfContainedRelease accepts file dependencies that stay within the release root", async (t) => {
+  const root = await makeTempDir("baoyu-release-ok-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  await writeJson(path.join(root, "shared", "package.json"), {
+    name: "shared-package",
+    version: "1.0.0",
+  });
+  await writeFile(path.join(root, "shared", "index.js"), "export const shared = true;\n");
+  await writeJson(path.join(root, "skill", "package.json"), {
+    name: "test-skill",
+    version: "1.0.0",
+    dependencies: {
+      "shared-package": "file:../shared",
+    },
+  });
+
+  await assert.doesNotReject(() => validateSelfContainedRelease(root));
+});
+
+test("validateSelfContainedRelease rejects missing local file dependencies", async (t) => {
+  const root = await makeTempDir("baoyu-release-missing-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  await writeJson(path.join(root, "skill", "package.json"), {
+    name: "test-skill",
+    version: "1.0.0",
+    dependencies: {
+      "shared-package": "file:../shared",
+    },
+  });
+
+  await assert.rejects(
+    () => validateSelfContainedRelease(root),
+    /Missing local dependency for release/,
+  );
+});
+
+test("validateSelfContainedRelease rejects file dependencies outside the release root", async (t) => {
+  const root = await makeTempDir("baoyu-release-root-");
+  const outside = await makeTempDir("baoyu-release-outside-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+  t.after(() => fs.rm(outside, { recursive: true, force: true }));
+
+  const skillDir = path.join(root, "skill");
+  const externalSpec = path
+    .relative(skillDir, outside)
+    .split(path.sep)
+    .join("/");
+
+  await writeJson(path.join(skillDir, "package.json"), {
+    name: "test-skill",
+    version: "1.0.0",
+    dependencies: {
+      "outside-package": `file:${externalSpec}`,
+    },
+  });
+
+  await assert.rejects(
+    () => validateSelfContainedRelease(root),
+    /Release target is not self-contained/,
+  );
+});

tests/shared-skill-packages.test.mjs

@@ -0,0 +1,70 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test from "node:test";
+
+import { syncSharedSkillPackages } from "../scripts/lib/shared-skill-packages.mjs";
+
+async function makeTempDir(prefix) {
+  return fs.mkdtemp(path.join(os.tmpdir(), prefix));
+}
+
+async function writeFile(filePath, contents = "") {
+  await fs.mkdir(path.dirname(filePath), { recursive: true });
+  await fs.writeFile(filePath, contents);
+}
+
+async function writeJson(filePath, value) {
+  await writeFile(filePath, `${JSON.stringify(value, null, 2)}\n`);
+}
+
+test("syncSharedSkillPackages vendors workspace packages into skill scripts", async (t) => {
+  const root = await makeTempDir("baoyu-sync-shared-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  await writeJson(path.join(root, "packages", "baoyu-md", "package.json"), {
+    name: "baoyu-md",
+    version: "1.0.0",
+  });
+  await writeFile(
+    path.join(root, "packages", "baoyu-md", "src", "index.ts"),
+    "export const markdown = true;\n",
+  );
+
+  const consumerDir = path.join(root, "skills", "demo-skill", "scripts");
+  await writeJson(path.join(consumerDir, "package.json"), {
+    name: "demo-skill-scripts",
+    version: "1.0.0",
+    dependencies: {
+      "baoyu-md": "^1.0.0",
+      kleur: "^4.1.5",
+    },
+  });
+
+  const result = await syncSharedSkillPackages(root, { install: false });
+
+  assert.deepEqual(result.packageDirs, [consumerDir]);
+  assert.deepEqual(result.managedPaths, [
+    "skills/demo-skill/scripts/bun.lock",
+    "skills/demo-skill/scripts/package.json",
+    "skills/demo-skill/scripts/vendor",
+  ]);
+
+  const updatedPackageJson = JSON.parse(
+    await fs.readFile(path.join(consumerDir, "package.json"), "utf8"),
+  );
+  assert.equal(updatedPackageJson.dependencies["baoyu-md"], "file:./vendor/baoyu-md");
+  assert.equal(updatedPackageJson.dependencies.kleur, "^4.1.5");
+
+  const vendoredPackageJson = JSON.parse(
+    await fs.readFile(path.join(consumerDir, "vendor", "baoyu-md", "package.json"), "utf8"),
+  );
+  assert.equal(vendoredPackageJson.name, "baoyu-md");
+
+  const vendoredFile = await fs.readFile(
+    path.join(consumerDir, "vendor", "baoyu-md", "src", "index.ts"),
+    "utf8",
+  );
+  assert.match(vendoredFile, /markdown = true/);
+});

tests/skills/baoyu-image-gen/main.test.mjs

@@ -0,0 +1,301 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test from "node:test";
+
+import {
+  createTaskArgs,
+  detectProvider,
+  getConfiguredMaxWorkers,
+  getConfiguredProviderRateLimits,
+  getWorkerCount,
+  isRetryableGenerationError,
+  loadBatchTasks,
+  mergeConfig,
+  normalizeOutputImagePath,
+  parseArgs,
+  parseSimpleYaml,
+} from "../../../skills/baoyu-image-gen/scripts/main.ts";
+
+function makeArgs(overrides = {}) {
+  return {
+    prompt: null,
+    promptFiles: [],
+    imagePath: null,
+    provider: null,
+    model: null,
+    aspectRatio: null,
+    size: null,
+    quality: null,
+    imageSize: null,
+    referenceImages: [],
+    n: 1,
+    batchFile: null,
+    jobs: null,
+    json: false,
+    help: false,
+    ...overrides,
+  };
+}
+
+function useEnv(t, values) {
+  const previous = new Map();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+async function makeTempDir(prefix) {
+  return fs.mkdtemp(path.join(os.tmpdir(), prefix));
+}
+
+test("parseArgs parses the main image-gen CLI flags", () => {
+  const args = parseArgs([
+    "--promptfiles",
+    "prompts/system.md",
+    "prompts/content.md",
+    "--image",
+    "out/hero",
+    "--provider",
+    "openai",
+    "--quality",
+    "2k",
+    "--imageSize",
+    "4k",
+    "--ref",
+    "ref/one.png",
+    "ref/two.jpg",
+    "--n",
+    "3",
+    "--jobs",
+    "5",
+    "--json",
+  ]);
+
+  assert.deepEqual(args.promptFiles, ["prompts/system.md", "prompts/content.md"]);
+  assert.equal(args.imagePath, "out/hero");
+  assert.equal(args.provider, "openai");
+  assert.equal(args.quality, "2k");
+  assert.equal(args.imageSize, "4K");
+  assert.deepEqual(args.referenceImages, ["ref/one.png", "ref/two.jpg"]);
+  assert.equal(args.n, 3);
+  assert.equal(args.jobs, 5);
+  assert.equal(args.json, true);
+});
+
+test("parseArgs falls back to positional prompt and rejects invalid provider", () => {
+  const positional = parseArgs(["draw", "a", "cat"]);
+  assert.equal(positional.prompt, "draw a cat");
+
+  assert.throws(
+    () => parseArgs(["--provider", "stability"]),
+    /Invalid provider/,
+  );
+});
+
+test("parseSimpleYaml parses nested defaults and provider limits", () => {
+  const yaml = `
+version: 2
+default_provider: openrouter
+default_quality: normal
+default_aspect_ratio: '16:9'
+default_image_size: 2K
+default_model:
+  google: gemini-3-pro-image-preview
+  openai: gpt-image-1.5
+batch:
+  max_workers: 8
+  provider_limits:
+    google:
+      concurrency: 2
+      start_interval_ms: 900
+    openai:
+      concurrency: 4
+`;
+
+  const config = parseSimpleYaml(yaml);
+
+  assert.equal(config.version, 2);
+  assert.equal(config.default_provider, "openrouter");
+  assert.equal(config.default_quality, "normal");
+  assert.equal(config.default_aspect_ratio, "16:9");
+  assert.equal(config.default_image_size, "2K");
+  assert.equal(config.default_model?.google, "gemini-3-pro-image-preview");
+  assert.equal(config.default_model?.openai, "gpt-image-1.5");
+  assert.equal(config.batch?.max_workers, 8);
+  assert.deepEqual(config.batch?.provider_limits?.google, {
+    concurrency: 2,
+    start_interval_ms: 900,
+  });
+  assert.deepEqual(config.batch?.provider_limits?.openai, {
+    concurrency: 4,
+  });
+});
+
+test("mergeConfig only fills values missing from CLI args", () => {
+  const merged = mergeConfig(
+    makeArgs({
+      provider: "openai",
+      quality: null,
+      aspectRatio: null,
+      imageSize: "4K",
+    }),
+    {
+      default_provider: "google",
+      default_quality: "2k",
+      default_aspect_ratio: "3:2",
+      default_image_size: "2K",
+    },
+  );
+
+  assert.equal(merged.provider, "openai");
+  assert.equal(merged.quality, "2k");
+  assert.equal(merged.aspectRatio, "3:2");
+  assert.equal(merged.imageSize, "4K");
+});
+
+test("detectProvider rejects non-ref-capable providers and prefers Google first when multiple keys exist", (t) => {
+  assert.throws(
+    () =>
+      detectProvider(
+        makeArgs({
+          provider: "dashscope",
+          referenceImages: ["ref.png"],
+        }),
+      ),
+    /Reference images require a ref-capable provider/,
+  );
+
+  useEnv(t, {
+    GOOGLE_API_KEY: "google-key",
+    OPENAI_API_KEY: "openai-key",
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: null,
+  });
+  assert.equal(detectProvider(makeArgs()), "google");
+});
+
+test("detectProvider selects an available ref-capable provider for reference-image tasks", (t) => {
+  useEnv(t, {
+    GOOGLE_API_KEY: null,
+    OPENAI_API_KEY: "openai-key",
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: null,
+  });
+  assert.equal(
+    detectProvider(makeArgs({ referenceImages: ["ref.png"] })),
+    "openai",
+  );
+});
+
+test("batch worker and provider-rate-limit configuration prefer env over EXTEND config", (t) => {
+  useEnv(t, {
+    BAOYU_IMAGE_GEN_MAX_WORKERS: "12",
+    BAOYU_IMAGE_GEN_GOOGLE_CONCURRENCY: "5",
+    BAOYU_IMAGE_GEN_GOOGLE_START_INTERVAL_MS: "450",
+  });
+
+  const extendConfig = {
+    batch: {
+      max_workers: 7,
+      provider_limits: {
+        google: {
+          concurrency: 2,
+          start_interval_ms: 900,
+        },
+      },
+    },
+  };
+
+  assert.equal(getConfiguredMaxWorkers(extendConfig), 12);
+  assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).google, {
+    concurrency: 5,
+    startIntervalMs: 450,
+  });
+});
+
+test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t) => {
+  const root = await makeTempDir("baoyu-image-gen-batch-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  const batchFile = path.join(root, "jobs", "batch.json");
+  await fs.mkdir(path.dirname(batchFile), { recursive: true });
+  await fs.writeFile(
+    batchFile,
+    JSON.stringify({
+      jobs: 2,
+      tasks: [
+        {
+          id: "hero",
+          promptFiles: ["prompts/hero.md"],
+          image: "out/hero",
+          ref: ["refs/hero.png"],
+          ar: "16:9",
+        },
+      ],
+    }),
+  );
+
+  const loaded = await loadBatchTasks(batchFile);
+  assert.equal(loaded.jobs, 2);
+  assert.equal(loaded.batchDir, path.dirname(batchFile));
+  assert.equal(loaded.tasks[0].id, "hero");
+
+  const taskArgs = createTaskArgs(
+    makeArgs({
+      provider: "replicate",
+      quality: "2k",
+      json: true,
+    }),
+    loaded.tasks[0],
+    loaded.batchDir,
+  );
+
+  assert.deepEqual(taskArgs.promptFiles, [
+    path.join(loaded.batchDir, "prompts/hero.md"),
+  ]);
+  assert.equal(taskArgs.imagePath, path.join(loaded.batchDir, "out/hero"));
+  assert.deepEqual(taskArgs.referenceImages, [
+    path.join(loaded.batchDir, "refs/hero.png"),
+  ]);
+  assert.equal(taskArgs.provider, "replicate");
+  assert.equal(taskArgs.aspectRatio, "16:9");
+  assert.equal(taskArgs.quality, "2k");
+  assert.equal(taskArgs.json, true);
+});
+
+test("path normalization, worker count, and retry classification follow expected rules", () => {
+  assert.match(normalizeOutputImagePath("out/sample"), /out[\\/]+sample\.png$/);
+  assert.match(normalizeOutputImagePath("out/sample.webp"), /out[\\/]+sample\.webp$/);
+
+  assert.equal(getWorkerCount(8, null, 3), 3);
+  assert.equal(getWorkerCount(2, 6, 5), 2);
+  assert.equal(getWorkerCount(5, 0, 4), 1);
+
+  assert.equal(isRetryableGenerationError(new Error("API error (401): denied")), false);
+  assert.equal(isRetryableGenerationError(new Error("socket hang up")), true);
+});

tests/skills/baoyu-image-gen/providers-dashscope.test.mjs

@@ -0,0 +1,26 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import {
+  getSizeFromAspectRatio,
+  normalizeSize,
+  parseAspectRatio,
+} from "../../../skills/baoyu-image-gen/scripts/providers/dashscope.ts";
+
+test("DashScope aspect-ratio parsing accepts numeric ratios only", () => {
+  assert.deepEqual(parseAspectRatio("3:2"), { width: 3, height: 2 });
+  assert.equal(parseAspectRatio("square"), null);
+  assert.equal(parseAspectRatio("-1:2"), null);
+});
+
+test("DashScope size selection picks the closest supported size per quality preset", () => {
+  assert.equal(getSizeFromAspectRatio(null, "normal"), "1024*1024");
+  assert.equal(getSizeFromAspectRatio("16:9", "normal"), "1280*720");
+  assert.equal(getSizeFromAspectRatio("16:9", "2k"), "2048*1152");
+  assert.equal(getSizeFromAspectRatio("invalid", "2k"), "1536*1536");
+});
+
+test("DashScope size normalization converts WxH into provider format", () => {
+  assert.equal(normalizeSize("1024x1024"), "1024*1024");
+  assert.equal(normalizeSize("2048*1152"), "2048*1152");
+});

tests/skills/baoyu-image-gen/providers-google.test.mjs

@@ -0,0 +1,107 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import {
+  addAspectRatioToPrompt,
+  buildGoogleUrl,
+  buildPromptWithAspect,
+  extractInlineImageData,
+  extractPredictedImageData,
+  getGoogleImageSize,
+  isGoogleImagen,
+  isGoogleMultimodal,
+  normalizeGoogleModelId,
+} from "../../../skills/baoyu-image-gen/scripts/providers/google.ts";
+
+function useEnv(t, values) {
+  const previous = new Map();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+test("Google provider helpers normalize model IDs and select image size defaults", () => {
+  assert.equal(
+    normalizeGoogleModelId("models/gemini-3.1-flash-image-preview"),
+    "gemini-3.1-flash-image-preview",
+  );
+  assert.equal(isGoogleMultimodal("models/gemini-3-pro-image-preview"), true);
+  assert.equal(isGoogleImagen("imagen-3.0-generate-002"), true);
+  assert.equal(
+    getGoogleImageSize({ imageSize: null, quality: "2k" }),
+    "2K",
+  );
+  assert.equal(
+    getGoogleImageSize({ imageSize: "4K", quality: "normal" }),
+    "4K",
+  );
+});
+
+test("Google URL builder appends v1beta when the base URL does not already include it", (t) => {
+  useEnv(t, { GOOGLE_BASE_URL: "https://generativelanguage.googleapis.com" });
+  assert.equal(
+    buildGoogleUrl("models/demo:generateContent"),
+    "https://generativelanguage.googleapis.com/v1beta/models/demo:generateContent",
+  );
+});
+
+test("Google URL and prompt helpers preserve existing v1beta paths and aspect hints", (t) => {
+  useEnv(t, { GOOGLE_BASE_URL: "https://example.com/custom/v1beta/" });
+  assert.equal(
+    buildGoogleUrl("/models/demo:predict"),
+    "https://example.com/custom/v1beta/models/demo:predict",
+  );
+
+  assert.equal(
+    addAspectRatioToPrompt("A city skyline", "16:9"),
+    "A city skyline Aspect ratio: 16:9.",
+  );
+  assert.equal(
+    buildPromptWithAspect("A city skyline", "16:9", "2k"),
+    "A city skyline Aspect ratio: 16:9. High resolution 2048px.",
+  );
+});
+
+test("Google response extractors find inline and predicted image payloads", () => {
+  assert.equal(
+    extractInlineImageData({
+      candidates: [
+        {
+          content: {
+            parts: [{ inlineData: { data: "inline-base64" } }],
+          },
+        },
+      ],
+    }),
+    "inline-base64",
+  );
+
+  assert.equal(
+    extractPredictedImageData({
+      predictions: [{ image: { imageBytes: "predicted-base64" } }],
+    }),
+    "predicted-base64",
+  );
+
+  assert.equal(
+    extractPredictedImageData({
+      generatedImages: [{ bytesBase64Encoded: "generated-base64" }],
+    }),
+    "generated-base64",
+  );
+});

tests/skills/baoyu-image-gen/providers-openai.test.mjs

@@ -0,0 +1,56 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import {
+  extractImageFromResponse,
+  getMimeType,
+  getOpenAISize,
+  parseAspectRatio,
+} from "../../../skills/baoyu-image-gen/scripts/providers/openai.ts";
+
+test("OpenAI aspect-ratio parsing and size selection match model families", () => {
+  assert.deepEqual(parseAspectRatio("16:9"), { width: 16, height: 9 });
+  assert.equal(parseAspectRatio("wide"), null);
+  assert.equal(parseAspectRatio("0:1"), null);
+
+  assert.equal(getOpenAISize("dall-e-3", "16:9", "2k"), "1792x1024");
+  assert.equal(getOpenAISize("dall-e-3", "9:16", "normal"), "1024x1792");
+  assert.equal(getOpenAISize("dall-e-2", "16:9", "2k"), "1024x1024");
+  assert.equal(getOpenAISize("gpt-image-1.5", "16:9", "2k"), "1536x1024");
+  assert.equal(getOpenAISize("gpt-image-1.5", "4:3", "2k"), "1024x1024");
+});
+
+test("OpenAI mime-type detection covers supported reference image extensions", () => {
+  assert.equal(getMimeType("frame.png"), "image/png");
+  assert.equal(getMimeType("frame.jpg"), "image/jpeg");
+  assert.equal(getMimeType("frame.webp"), "image/webp");
+  assert.equal(getMimeType("frame.gif"), "image/gif");
+});
+
+test("OpenAI response extraction supports base64 and URL download flows", async (t) => {
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const fromBase64 = await extractImageFromResponse({
+    data: [{ b64_json: Buffer.from("hello").toString("base64") }],
+  });
+  assert.equal(Buffer.from(fromBase64).toString("utf8"), "hello");
+
+  globalThis.fetch = async () =>
+    new Response(Uint8Array.from([1, 2, 3]), {
+      status: 200,
+      headers: { "Content-Type": "application/octet-stream" },
+    });
+
+  const fromUrl = await extractImageFromResponse({
+    data: [{ url: "https://example.com/image.png" }],
+  });
+  assert.deepEqual([...fromUrl], [1, 2, 3]);
+
+  await assert.rejects(
+    () => extractImageFromResponse({ data: [{}] }),
+    /No image in response/,
+  );
+});

tests/skills/baoyu-image-gen/providers-replicate.test.mjs

@@ -0,0 +1,88 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import {
+  buildInput,
+  extractOutputUrl,
+  parseModelId,
+} from "../../../skills/baoyu-image-gen/scripts/providers/replicate.ts";
+
+function makeArgs(overrides = {}) {
+  return {
+    aspectRatio: null,
+    quality: null,
+    n: 1,
+    ...overrides,
+  };
+}
+
+test("Replicate model parsing accepts official formats and rejects malformed ones", () => {
+  assert.deepEqual(parseModelId("google/nano-banana-pro"), {
+    owner: "google",
+    name: "nano-banana-pro",
+    version: null,
+  });
+  assert.deepEqual(parseModelId("owner/model:abc123"), {
+    owner: "owner",
+    name: "model",
+    version: "abc123",
+  });
+
+  assert.throws(
+    () => parseModelId("just-a-model-name"),
+    /Invalid Replicate model format/,
+  );
+});
+
+test("Replicate input builder maps aspect ratio, image count, quality, and refs", () => {
+  assert.deepEqual(
+    buildInput(
+      "A robot painter",
+      makeArgs({
+        aspectRatio: "16:9",
+        quality: "2k",
+        n: 3,
+      }),
+      ["data:image/png;base64,AAAA"],
+    ),
+    {
+      prompt: "A robot painter",
+      aspect_ratio: "16:9",
+      number_of_images: 3,
+      resolution: "2K",
+      output_format: "png",
+      image_input: ["data:image/png;base64,AAAA"],
+    },
+  );
+
+  assert.deepEqual(
+    buildInput("A robot painter", makeArgs({ quality: "normal" }), ["ref"]),
+    {
+      prompt: "A robot painter",
+      aspect_ratio: "match_input_image",
+      resolution: "1K",
+      output_format: "png",
+      image_input: ["ref"],
+    },
+  );
+});
+
+test("Replicate output extraction supports string, array, and object URLs", () => {
+  assert.equal(
+    extractOutputUrl({ output: "https://example.com/a.png" }),
+    "https://example.com/a.png",
+  );
+  assert.equal(
+    extractOutputUrl({ output: ["https://example.com/b.png"] }),
+    "https://example.com/b.png",
+  );
+  assert.equal(
+    extractOutputUrl({ output: { url: "https://example.com/c.png" } }),
+    "https://example.com/c.png",
+  );
+
+  assert.throws(
+    () => extractOutputUrl({ output: { invalid: true } }),
+    /Unexpected Replicate output format/,
+  );
+});