Compare commits

...

38 Commits

Author SHA1 Message Date
Jim Liu 宝玉 93e54a7b86 chore: release v1.69.1 2026-03-16 12:59:35 -05:00
Jim Liu 宝玉 c1f8a9ad07 chore: sync vendored baoyu-chrome-cdp copies 2026-03-16 12:57:39 -05:00
Jim Liu 宝玉 8b8ecf61a6 fix(baoyu-chrome-cdp): tighten chrome auto-connect 2026-03-16 12:55:29 -05:00
Jim Liu 宝玉 4be6f3682a chore: sync vendored baoyu-chrome-cdp across all skills 2026-03-16 12:54:36 -05:00
Jim Liu 宝玉 b89ef02221 chore(baoyu-post-to-wechat): sync vendored baoyu-chrome-cdp 2026-03-16 12:53:51 -05:00
Jim Liu 宝玉 55356c8820 chore: release v1.69.0 2026-03-16 12:53:25 -05:00
Jim Liu 宝玉 f23d4eebc3 docs(baoyu-cover-image): clarify people reference image workflow and interactive confirmation 2026-03-16 12:52:16 -05:00
Jim Liu 宝玉 3b795b6ef3 Merge pull request #92 from bviews/main
feat(baoyu-chrome-cdp): support Chrome 146 auto-connect
2026-03-16 12:40:22 -05:00
Jim Liu 宝玉 c62d9d5a1b Merge pull request #94 from cfh-7598/fix/wechat-article-reliability
fix(baoyu-post-to-wechat): improve browser publishing reliability
2026-03-16 12:32:49 -05:00
cfh 84c56b0da3 fix(baoyu-post-to-wechat): improve browser publishing reliability
- Add retry logic (5 attempts with progressive backoff) to clickMenuByText
  to handle slow-loading home page menus
- Increase post-login wait from 2s to 5s and menu timeout from 20s to 40s
- Replace fixed 3s sleep after editor tab opens with waitForElement polling
  for #title (30s) and .ProseMirror (15s) to reliably wait for full load
- Improve title/author filling with focus() and change event dispatch
  for more reliable value setting

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 00:43:39 +08:00
Alec Jiang 462d080a0e fix(gemini-web): also respect BAOYU_CHROME_PROFILE_DIR in auto-discovery skip
Both GEMINI_WEB_CHROME_PROFILE_DIR and BAOYU_CHROME_PROFILE_DIR are
valid profile overrides (see resolveGeminiWebChromeProfileDir). Skip
existing Chrome auto-discovery when either is set.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:02:58 +08:00
Alec Jiang bd01c370c9 fix(gemini-web): respect explicit profile config over auto-discovery
Skip existing Chrome auto-discovery when GEMINI_WEB_CHROME_PROFILE_DIR
is explicitly set, to avoid binding to the wrong browser profile/account.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 18:39:53 +08:00
Alec Jiang b7bcc8c094 fix(baoyu-chrome-cdp): keep HTTP validation in findExistingChromeDebugPort
findExistingChromeDebugPort callers (fetch_google_cookies_via_cdp) depend
on /json/version being available. TCP-only check could misclassify
non-CDP listeners as reusable, causing waitForChromeDebugPort to timeout
instead of falling back to launching a new Chrome. Restore isDebugPortReady
(HTTP) as the validator for this function; TCP-only check remains in
discoverRunningChromeDebugPort for Chrome 146 approval mode.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 18:11:37 +08:00
Alec Jiang d9f9da639d fix(baoyu-chrome-cdp): support Chrome 146 native remote debugging (approval mode)
Chrome 146+ blocks all HTTP endpoints (/json/version) in approval mode.
Read DevToolsActivePort ws path directly and use TCP port check instead
of HTTP discovery. Add WebSocket connect retry loop for approval dialog.
Unify findExistingChromeDebugPort to use the same mechanism.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 18:00:58 +08:00
bviews 126b3040e6 fix(gemini-web): reuse openPageSession and fix orphaned tab leak
- Replace manual CDP target orchestration with openPageSession, keeping
  behavior consistent with fetch_google_cookies_via_cdp
- Move created-tab cleanup into finally block so tabs are always closed
  even when Target.attachToTarget or Network.enable throws

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 16:44:53 +08:00
bviews 682888cc95 feat(baoyu-chrome-cdp): support connecting to existing Chrome session
Add ability to discover and connect to an already-running Chrome browser
(v144+) for cookie extraction, avoiding the need to launch a new window
and re-login. Uses Chrome's DevToolsActivePort from default user data
directories and process scanning as discovery mechanisms.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 15:51:57 +08:00
Jim Liu 宝玉 e31294415d chore: release v1.68.0 2026-03-14 23:08:00 -05:00
Jim Liu 宝玉 926f74e9c9 feat(baoyu-cover-image): add character preservation from reference images 2026-03-14 23:07:56 -05:00
Jim Liu 宝玉 339990e87e feat(baoyu-article-illustrator): add configurable output directory support 2026-03-14 23:07:56 -05:00
Jim Liu 宝玉 3c5c3e006d Merge pull request #89 from shixy96/fix/markdown-to-html-inline-code-in-emphasis
fix(markdown-to-html): preserve inline code inside bold/emphasis
2026-03-14 22:27:14 -05:00
shixy 2aa9790789 fix: preserve inline code in cjk emphasis 2026-03-14 17:12:03 +08:00
shixy 38fc733b99 fix(markdown-to-html): preserve inline code inside bold/emphasis
The `extractText()` helper in `preprocessCjkEmphasis()` only handled
`text` nodes and nodes with `children`. `inlineCode` AST nodes (which
have a `value` but no `children`) fell through to the default empty-
string return, silently dropping their content.

For example `**算出 \`logits\`**` rendered as `<strong>算出 </strong>`
with the code span completely lost.

Add an `inlineCode` branch that wraps the node value in backticks so
the downstream `marked` pass can turn it into a proper `<code>` element.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 16:13:02 +08:00
Jim Liu 宝玉 4d2b95d1d1 chore: release v1.67.0 2026-03-13 19:12:47 -05:00
JianJang2017 ac2ce0b8b6 Add qwen-image-2.0-pro support for baoyu-image-gen 2026-03-13 19:09:54 -05:00
Jim Liu 宝玉 de7dc85361 chore: sync shared skill package vendor test files 2026-03-13 17:56:53 -05:00
Jim Liu 宝玉 0c02b81885 chore: release v1.66.1 2026-03-13 17:56:30 -05:00
Jim Liu 宝玉 774ad784d8 test: migrate tests from centralized mjs to colocated TypeScript
Move test files from tests/ directory to colocate with source code,
convert from .mjs to .ts using tsx runner, add workspaces and npm
cache to CI workflow.
2026-03-13 16:36:06 -05:00
Jim Liu 宝玉 484b00109f chore: release v1.66.0 2026-03-13 16:20:38 -05:00
Jim Liu 宝玉 ac217d5402 test: add test infrastructure with CI workflow and image-gen unit tests 2026-03-13 16:17:01 -05:00
Jim Liu 宝玉 70d9f63727 docs(baoyu-image-gen): add Jimeng and Seedream provider documentation 2026-03-13 16:16:57 -05:00
Jim Liu 宝玉 3398509d9e refactor(baoyu-image-gen): export functions for testability and add module entry guard 2026-03-13 16:16:50 -05:00
Jim Liu 宝玉 a11613c11b Merge pull request #88 from JimLiu/lindaifeng/main
fix(image-gen): tighten Jimeng provider behavior
2026-03-13 15:58:07 -05:00
Jim Liu 宝玉 cb17cb9cca fix(image-gen): tighten Jimeng provider behavior 2026-03-13 15:39:46 -05:00
Jim Liu 宝玉 88d6e09472 Merge pull request #87 from lindaifeng/main
Integrate DreamGraph and DoubaoGraph
2026-03-13 15:35:15 -05:00
Jim Liu 宝玉 004236682d chore: release v1.65.1 2026-03-13 15:29:52 -05:00
Jim Liu 宝玉 7e07c1bb84 refactor(baoyu-translate): replace remark/unified with markdown-it for chunk parsing
Simplifies dependencies and adds main.ts CLI entry point with exported
functions for programmatic reuse.
2026-03-13 15:27:25 -05:00
lindaifeng c151f33775 Merge branch 'JimLiu:main' into main 2026-03-14 00:39:44 +08:00
ldf 32003da694 集成即梦生图和豆包生图 2026-03-14 00:37:46 +08:00
80 changed files with 9730 additions and 527 deletions
+1 -1
View File
@@ -6,7 +6,7 @@
},
"metadata": {
"description": "Skills shared by Baoyu for improving daily work efficiency",
"version": "1.65.0"
"version": "1.69.1"
},
"plugins": [
{
+25
View File
@@ -0,0 +1,25 @@
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
cache: npm
- name: Install dependencies
run: npm ci
- name: Run tests
run: npm test
+61
View File
@@ -2,6 +2,67 @@
English | [中文](./CHANGELOG.zh.md)
## 1.69.1 - 2026-03-16
### Fixes
- `baoyu-chrome-cdp`: tighten chrome auto-connect logic to reduce false positives
## 1.69.0 - 2026-03-16
### Features
- `baoyu-chrome-cdp`: support connecting to existing Chrome session (by @bviews)
### Fixes
- `baoyu-chrome-cdp`: support Chrome 146 native remote debugging in approval mode (by @bviews)
- `baoyu-chrome-cdp`: keep HTTP validation in findExistingChromeDebugPort (by @bviews)
- `baoyu-danger-gemini-web`: reuse openPageSession and fix orphaned tab leak (by @bviews)
- `baoyu-danger-gemini-web`: respect explicit profile config over auto-discovery (by @bviews)
- `baoyu-danger-gemini-web`: respect BAOYU_CHROME_PROFILE_DIR in auto-discovery skip (by @bviews)
- `baoyu-post-to-wechat`: improve browser publishing reliability (by @cfh-7598)
### Documentation
- `baoyu-cover-image`: clarify people reference image workflow and interactive confirmation
## 1.68.0 - 2026-03-14
### Features
- `baoyu-article-illustrator`: add configurable output directory (`default_output_dir`) with 4 options — `imgs-subdir`, `same-dir`, `illustrations-subdir`, `independent`
- `baoyu-cover-image`: add character preservation from reference images — use `usage: direct` to pass people references to model for stylized likeness
## 1.67.0 - 2026-03-13
### Features
- `baoyu-image-gen`: add qwen-image-2.0-pro model support for DashScope provider with free-form sizes and text rendering (by @JianJang2017)
## 1.66.1 - 2026-03-13
### Tests
- Migrate test files from centralized `tests/` directory to colocate with source code
- Convert tests from `.mjs` to TypeScript (`.test.ts`) with `tsx` runner
- Add npm workspaces configuration and npm cache to CI workflow
## 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
- `baoyu-translate`: replace remark/unified with markdown-it for chunk parsing, add main.ts CLI entry point
## 1.65.0 - 2026-03-13
### Features
+61
View File
@@ -2,6 +2,67 @@
[English](./CHANGELOG.md) | 中文
## 1.69.1 - 2026-03-16
### 修复
- `baoyu-chrome-cdp`:收紧 Chrome 自动连接逻辑,减少误连接
## 1.69.0 - 2026-03-16
### 新功能
- `baoyu-chrome-cdp`:支持连接到已有的 Chrome 会话 (by @bviews)
### 修复
- `baoyu-chrome-cdp`:支持 Chrome 146 原生远程调试(审批模式)(by @bviews)
- `baoyu-chrome-cdp`:保留 findExistingChromeDebugPort 中的 HTTP 验证 (by @bviews)
- `baoyu-danger-gemini-web`:复用 openPageSession 并修复孤立标签页泄漏 (by @bviews)
- `baoyu-danger-gemini-web`:显式配置优先于自动发现 (by @bviews)
- `baoyu-danger-gemini-web`:自动发现跳过时也遵循 BAOYU_CHROME_PROFILE_DIR (by @bviews)
- `baoyu-post-to-wechat`:提升浏览器发布可靠性 (by @cfh-7598)
### 文档
- `baoyu-cover-image`:完善人物参考图片工作流和交互式确认说明
## 1.68.0 - 2026-03-14
### 新功能
- `baoyu-article-illustrator`:新增可配置输出目录(`default_output_dir`),支持 4 种选项——`imgs-subdir``same-dir``illustrations-subdir``independent`
- `baoyu-cover-image`:新增参考图片人物保留功能——当参考图包含人物时使用 `usage: direct` 传递给模型,风格化保留人物特征
## 1.67.0 - 2026-03-13
### 新功能
- `baoyu-image-gen`:新增 DashScope qwen-image-2.0-pro 模型支持,支持自由尺寸和文字渲染 (by @JianJang2017)
## 1.66.1 - 2026-03-13
### 测试
- 将测试文件从集中式 `tests/` 目录迁移至与源码同级
- 将测试从 `.mjs` 转换为 TypeScript`.test.ts`),使用 `tsx` 运行器
- 新增 npm workspaces 配置,CI 工作流添加 npm 缓存
## 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
- `baoyu-translate`:将 chunk 解析从 remark/unified 替换为 markdown-it,新增 main.ts CLI 入口
## 1.65.0 - 2026-03-13
### 新功能
+1 -1
View File
@@ -1,6 +1,6 @@
# CLAUDE.md
Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.65.0**.
Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.69.1**.
## Architecture
+30 -4
View File
@@ -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` |
| `DASHSCOPE_IMAGE_MODEL` | DashScope model | `qwen-image-2.0-pro` |
| `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
@@ -982,13 +996,25 @@ GOOGLE_IMAGE_MODEL=gemini-3-pro-image-preview
# DashScope (Aliyun Tongyi Wanxiang)
DASHSCOPE_API_KEY=sk-xxx
DASHSCOPE_IMAGE_MODEL=z-image-turbo
DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
# DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
# Replicate
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
```
+30 -4
View File
@@ -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``replicate`(默认:自动检测,优先 google) |
| `--provider` | `google``openai``openrouter``dashscope``jimeng``seedream``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` |
| `DASHSCOPE_IMAGE_MODEL` | DashScope 模型 | `qwen-image-2.0-pro` |
| `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
@@ -982,13 +996,25 @@ GOOGLE_IMAGE_MODEL=gemini-3-pro-image-preview
# DashScope(阿里通义万相)
DASHSCOPE_API_KEY=sk-xxx
DASHSCOPE_IMAGE_MODEL=z-image-turbo
DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
# DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
# Replicate
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
```
+73
View File
@@ -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`
+1958
View File
File diff suppressed because it is too large Load Diff
+15
View File
@@ -0,0 +1,15 @@
{
"name": "baoyu-skills",
"private": true,
"type": "module",
"workspaces": [
"packages/*"
],
"scripts": {
"test": "node --import tsx --test",
"test:coverage": "node --import tsx --experimental-test-coverage --test"
},
"devDependencies": {
"tsx": "^4.20.5"
}
}
+307
View File
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
+120 -8
View File
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}
+93
View File
@@ -0,0 +1,93 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
extractSummaryFromBody,
extractTitleFromMarkdown,
parseFrontmatter,
pickFirstString,
serializeFrontmatter,
stripWrappingQuotes,
toFrontmatterString,
} from "./content.ts";
test("parseFrontmatter extracts YAML fields and strips wrapping quotes", () => {
const input = `---
title: "Hello World"
author: Baoyu
summary: plain text
---
# Heading
Body`;
const result = parseFrontmatter(input);
assert.deepEqual(result.frontmatter, {
title: "Hello World",
author: "Baoyu",
summary: "plain text",
});
assert.match(result.body, /^# Heading/);
});
test("parseFrontmatter returns original content when no frontmatter exists", () => {
const input = "# No frontmatter";
assert.deepEqual(parseFrontmatter(input), {
frontmatter: {},
body: input,
});
});
test("serializeFrontmatter renders YAML only when fields exist", () => {
assert.equal(serializeFrontmatter({}), "");
assert.equal(
serializeFrontmatter({ title: "Hello", author: "Baoyu" }),
"---\ntitle: Hello\nauthor: Baoyu\n---\n",
);
});
test("quote and frontmatter string helpers normalize mixed scalar values", () => {
assert.equal(stripWrappingQuotes(`" quoted "`), "quoted");
assert.equal(stripWrappingQuotes("“ 中文标题 ”"), "中文标题");
assert.equal(stripWrappingQuotes("plain"), "plain");
assert.equal(toFrontmatterString("'hello'"), "hello");
assert.equal(toFrontmatterString(42), "42");
assert.equal(toFrontmatterString(false), "false");
assert.equal(toFrontmatterString({}), undefined);
assert.equal(
pickFirstString({ summary: 123, title: "" }, ["title", "summary"]),
"123",
);
});
test("markdown title and summary extraction skip non-body content and clean formatting", () => {
const markdown = `
![cover](cover.png)
## My Title
Body paragraph
`;
assert.equal(extractTitleFromMarkdown(markdown), "My Title");
const summary = extractSummaryFromBody(
`
# Heading
> quote
- list
1. ordered
\`\`\`
code
\`\`\`
This is **the first paragraph** with [a link](https://example.com) and \`inline code\` that should be summarized cleanly.
`,
70,
);
assert.equal(
summary,
"This is the first paragraph with a link and inline code that should...",
);
});
+140
View File
@@ -0,0 +1,140 @@
import assert from "node:assert/strict";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import { COLOR_PRESETS, FONT_FAMILY_MAP } from "./constants.ts";
import {
buildMarkdownDocumentMeta,
formatTimestamp,
resolveColorToken,
resolveFontFamilyToken,
resolveMarkdownStyle,
resolveRenderOptions,
} from "./document.ts";
function useCwd(t: TestContext, cwd: string): void {
const previous = process.cwd();
process.chdir(cwd);
t.after(() => {
process.chdir(previous);
});
}
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("document token resolvers map known presets and allow passthrough values", () => {
assert.equal(resolveColorToken("green"), COLOR_PRESETS.green);
assert.equal(resolveColorToken("#123456"), "#123456");
assert.equal(resolveColorToken(), undefined);
assert.equal(resolveFontFamilyToken("mono"), FONT_FAMILY_MAP.mono);
assert.equal(resolveFontFamilyToken("Custom Font"), "Custom Font");
assert.equal(resolveFontFamilyToken(), undefined);
});
test("formatTimestamp uses compact sortable datetime output", () => {
const date = new Date("2026-03-13T21:04:05.000Z");
const pad = (value: number) => String(value).padStart(2, "0");
const expected = `${date.getFullYear()}${pad(date.getMonth() + 1)}${pad(
date.getDate(),
)}${pad(date.getHours())}${pad(date.getMinutes())}${pad(date.getSeconds())}`;
assert.equal(formatTimestamp(date), expected);
});
test("buildMarkdownDocumentMeta prefers frontmatter and falls back to markdown title and summary", () => {
const metaFromYaml = buildMarkdownDocumentMeta(
"# Markdown Title\n\nBody summary paragraph that should be ignored.",
{
title: `" YAML Title "`,
author: "'Baoyu'",
summary: `" YAML Summary "`,
},
"fallback",
);
assert.deepEqual(metaFromYaml, {
title: "YAML Title",
author: "Baoyu",
description: "YAML Summary",
});
const metaFromMarkdown = buildMarkdownDocumentMeta(
`## “Markdown Title”\n\nThis is the first body paragraph that should become the summary because it is long enough.`,
{},
"fallback",
);
assert.equal(metaFromMarkdown.title, "Markdown Title");
assert.match(metaFromMarkdown.description ?? "", /^This is the first body paragraph/);
});
test("resolveMarkdownStyle merges theme defaults with explicit overrides", () => {
const style = resolveMarkdownStyle({
theme: "modern",
primaryColor: "#112233",
fontFamily: "Custom Sans",
});
assert.equal(style.primaryColor, "#112233");
assert.equal(style.fontFamily, "Custom Sans");
assert.equal(style.fontSize, "15px");
assert.equal(style.containerBg, "rgba(250, 249, 245, 1)");
});
test("resolveRenderOptions loads workspace EXTEND settings and lets explicit options win", async (t) => {
const root = await makeTempDir("baoyu-md-render-options-");
useCwd(t, root);
const extendPath = path.join(
root,
".baoyu-skills",
"baoyu-markdown-to-html",
"EXTEND.md",
);
await fs.mkdir(path.dirname(extendPath), { recursive: true });
await fs.writeFile(
extendPath,
`---
default_theme: modern
default_color: green
default_font_family: mono
default_font_size: 17
default_code_theme: nord
mac_code_block: false
show_line_number: true
cite: true
count: true
legend: title-alt
keep_title: true
---
`,
);
const fromExtend = resolveRenderOptions();
assert.equal(fromExtend.theme, "modern");
assert.equal(fromExtend.primaryColor, COLOR_PRESETS.green);
assert.equal(fromExtend.fontFamily, FONT_FAMILY_MAP.mono);
assert.equal(fromExtend.fontSize, "17px");
assert.equal(fromExtend.codeTheme, "nord");
assert.equal(fromExtend.isMacCodeBlock, false);
assert.equal(fromExtend.isShowLineNumber, true);
assert.equal(fromExtend.citeStatus, true);
assert.equal(fromExtend.countStatus, true);
assert.equal(fromExtend.legend, "title-alt");
assert.equal(fromExtend.keepTitle, true);
const explicit = resolveRenderOptions({
theme: "simple",
fontSize: "18px",
keepTitle: false,
});
assert.equal(explicit.theme, "simple");
assert.equal(explicit.fontSize, "18px");
assert.equal(explicit.keepTitle, false);
});
@@ -0,0 +1,71 @@
import assert from "node:assert/strict";
import test from "node:test";
import { DEFAULT_STYLE } from "./constants.ts";
import {
buildCss,
buildHtmlDocument,
modifyHtmlStructure,
normalizeCssText,
normalizeInlineCss,
removeFirstHeading,
} from "./html-builder.ts";
test("buildCss injects style variables and concatenates base and theme CSS", () => {
const css = buildCss("body { color: red; }", ".theme { color: blue; }");
assert.match(css, /--md-primary-color: #0F4C81;/);
assert.match(css, /body \{ color: red; \}/);
assert.match(css, /\.theme \{ color: blue; \}/);
});
test("buildHtmlDocument includes optional meta tags and code theme CSS", () => {
const html = buildHtmlDocument(
{
title: "Doc",
author: "Baoyu",
description: "Summary",
},
"body { color: red; }",
"<article>Hello</article>",
".hljs { color: blue; }",
);
assert.match(html, /<title>Doc<\/title>/);
assert.match(html, /meta name="author" content="Baoyu"/);
assert.match(html, /meta name="description" content="Summary"/);
assert.match(html, /<style>body \{ color: red; \}<\/style>/);
assert.match(html, /<style>\.hljs \{ color: blue; \}<\/style>/);
assert.match(html, /<article>Hello<\/article>/);
});
test("normalizeCssText and normalizeInlineCss replace variables and strip declarations", () => {
const rawCss = `
:root { --md-primary-color: #000; --md-font-size: 12px; --foreground: 0 0% 5%; }
.box { color: var(--md-primary-color); font-size: var(--md-font-size); background: hsl(var(--foreground)); }
`;
const normalizedCss = normalizeCssText(rawCss, DEFAULT_STYLE);
assert.match(normalizedCss, /color: #0F4C81/);
assert.match(normalizedCss, /font-size: 16px/);
assert.match(normalizedCss, /background: #3f3f3f/);
assert.doesNotMatch(normalizedCss, /--md-primary-color/);
const normalizedHtml = normalizeInlineCss(
`<style>${rawCss}</style><div style="color: var(--md-primary-color)"></div>`,
DEFAULT_STYLE,
);
assert.match(normalizedHtml, /color: #0F4C81/);
assert.doesNotMatch(normalizedHtml, /var\(--md-primary-color\)/);
});
test("HTML structure helpers hoist nested lists and remove the first heading", () => {
const nestedList = `<ul><li>Parent<ul><li>Child</li></ul></li></ul>`;
assert.equal(
modifyHtmlStructure(nestedList),
`<ul><li>Parent</li><ul><li>Child</li></ul></ul>`,
);
const html = `<h1>Title</h1><p>Intro</p><h2>Sub</h2>`;
assert.equal(removeFirstHeading(html), `<p>Intro</p><h2>Sub</h2>`);
});
+79
View File
@@ -0,0 +1,79 @@
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 {
getImageExtension,
replaceMarkdownImagesWithPlaceholders,
resolveContentImages,
resolveImagePath,
} from "./images.ts";
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("replaceMarkdownImagesWithPlaceholders rewrites markdown and tracks image metadata", () => {
const result = replaceMarkdownImagesWithPlaceholders(
`![cover](images/cover.png)\n\nText\n\n![diagram](images/diagram.webp)`,
"IMG_",
);
assert.equal(result.markdown, `IMG_1\n\nText\n\nIMG_2`);
assert.deepEqual(result.images, [
{ alt: "cover", originalPath: "images/cover.png", placeholder: "IMG_1" },
{ alt: "diagram", originalPath: "images/diagram.webp", placeholder: "IMG_2" },
]);
});
test("image extension and local fallback resolution handle common path variants", async (t) => {
assert.equal(getImageExtension("https://example.com/a.jpeg?x=1"), "jpeg");
assert.equal(getImageExtension("/tmp/figure"), "png");
const root = await makeTempDir("baoyu-md-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "figure.webp"), "webp");
const resolved = await resolveImagePath("figure.png", baseDir, tempDir, "test");
assert.equal(resolved, path.join(baseDir, "figure.webp"));
});
test("resolveContentImages resolves image placeholders against the content directory", async (t) => {
const root = await makeTempDir("baoyu-md-content-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "cover.png"), "png");
const resolved = await resolveContentImages(
[
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
},
],
baseDir,
tempDir,
"test",
);
assert.deepEqual(resolved, [
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
localPath: path.join(baseDir, "cover.png"),
},
]);
});
+64
View File
@@ -0,0 +1,64 @@
import assert from "node:assert/strict";
import test from "node:test";
import { initRenderer, renderMarkdown } from "./renderer.ts";
const render = (md: string) => {
const r = initRenderer();
return renderMarkdown(md, r).html;
};
test("bold with inline code (no underscore)", () => {
const html = render("**算出 `logits`,算出 `loss`。**");
assert.match(html, /<code[^>]*>logits<\/code>/);
assert.match(html, /<code[^>]*>loss<\/code>/);
});
test("bold with inline code (contains underscore)", () => {
const html = render("**变成 `input_ids`。**");
assert.match(html, /<code[^>]*>input_ids<\/code>/);
});
test("emphasis with inline code", () => {
const html = render("*查看 `hidden_states`*");
assert.match(html, /<code[^>]*>hidden_states<\/code>/);
});
test("plain inline code (regression)", () => {
const html = render("`lm_head`");
assert.match(html, /<code[^>]*>lm_head<\/code>/);
});
test("bold without code (regression)", () => {
const html = render("**纯粗体文本**");
assert.match(html, /<strong[^>]*>纯粗体文本<\/strong>/);
assert.doesNotMatch(html, /<code/);
});
test("bold with inline code containing backticks", () => {
const html = render("**``a`b``**");
assert.match(html, /<code[^>]*>a&#96;b<\/code>/);
});
test("emphasis with inline code containing backticks", () => {
const html = render("*``a`b``*");
assert.match(html, /<em[^>]*><code[^>]*>a&#96;b<\/code><\/em>/);
});
test("bold with inline code containing consecutive backticks", () => {
const html = render("**```a``b```**");
assert.match(html, /<code[^>]*>a&#96;&#96;b<\/code>/);
});
test("bold with inline code containing only backticks", () => {
const html = render("**```` `` ````**");
assert.match(html, /<code[^>]*>&#96;&#96;<\/code>/);
});
test("bold with inline code containing only spaces", () => {
const oneSpace = render("**`` ``**");
assert.match(oneSpace, /<code[^>]*> <\/code>/);
const twoSpaces = render("**`` ``**");
assert.match(twoSpaces, /<code[^>]*> <\/code>/);
});
+8
View File
@@ -109,6 +109,13 @@ function parseFrontMatterAndContent(markdownText: string): ParseResult {
}
}
function wrapInlineCode(value: string): string {
const runs = value.match(/`+/g);
const fence = "`".repeat(Math.max(...(runs?.map((run) => run.length) ?? [0])) + 1);
const padding = /^ *$/.test(value) ? "" : " ";
return `${fence}${padding}${value}${padding}${fence}`;
}
export function initRenderer(opts: IOpts = {}): RendererAPI {
const footnotes: [number, string, string][] = [];
let footnoteIndex = 0;
@@ -369,6 +376,7 @@ function preprocessCjkEmphasis(markdown: string): string {
const tree = processor.parse(markdown);
const extractText = (node: any): string => {
if (node.type === "text") return node.value;
if (node.type === "inlineCode") return wrapInlineCode(node.value);
if (node.children) return node.children.map(extractText).join("");
return "";
};
+110
View File
@@ -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 "./release-files.mjs";
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function writeFile(filePath: string, contents = ""): Promise<void> {
await fs.mkdir(path.dirname(filePath), { recursive: true });
await fs.writeFile(filePath, contents);
}
async function writeJson(filePath: string, value: unknown): Promise<void> {
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/,
);
});
+70
View File
@@ -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 "./shared-skill-packages.mjs";
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function writeFile(filePath: string, contents = ""): Promise<void> {
await fs.mkdir(path.dirname(filePath), { recursive: true });
await fs.writeFile(filePath, contents);
}
async function writeJson(filePath: string, value: unknown): Promise<void> {
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"),
) as { dependencies: Record<string, string> };
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"),
) as { name: string };
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/);
});
+16 -4
View File
@@ -133,7 +133,7 @@ Full procedures: [references/workflow.md](references/workflow.md#step-5-generate
### Step 6: Finalize
Insert `![description](path/NN-{type}-{slug}.png)` after paragraphs.
Insert `![description]({relative-path}/NN-{type}-{slug}.png)` after paragraphs. Path computed relative to article file based on output directory setting.
```
Article Illustration Complete!
@@ -143,15 +143,27 @@ Images: X/N generated
## Output Directory
Output directory is determined by `default_output_dir` in EXTEND.md (set during first-time setup):
| `default_output_dir` | Output Path | Markdown Insert Path |
|----------------------|-------------|----------------------|
| `imgs-subdir` (default) | `{article-dir}/imgs/` | `imgs/NN-{type}-{slug}.png` |
| `same-dir` | `{article-dir}/` | `NN-{type}-{slug}.png` |
| `illustrations-subdir` | `{article-dir}/illustrations/` | `illustrations/NN-{type}-{slug}.png` |
| `independent` | `illustrations/{topic-slug}/` | `illustrations/{topic-slug}/NN-{type}-{slug}.png` (relative to cwd) |
All auxiliary files (outline, prompts) are saved inside the output directory:
```
illustrations/{topic-slug}/
├── source-{slug}.{ext}
├── references/ # if provided
{output-dir}/
├── outline.md
├── prompts/
│ └── NN-{type}-{slug}.md
└── NN-{type}-{slug}.png
```
When input is **pasted content** (no file path), always uses `illustrations/{topic-slug}/` with `source-{slug}.{ext}` saved alongside.
**Slug**: 2-4 words, kebab-case. **Conflict**: append `-YYYYMMDD-HHMMSS`.
## Modification
@@ -69,7 +69,23 @@ options:
description: "Friendly, approachable, personal"
```
### Question 3: Save Location
### Question 3: Output Directory
```
header: "Output Directory"
question: "Where to save generated illustrations when illustrating a file?"
options:
- label: "imgs-subdir (Recommended)"
description: "{article-dir}/imgs/ — images in a subdirectory next to the article"
- label: "same-dir"
description: "{article-dir}/ — images alongside the article file"
- label: "illustrations-subdir"
description: "{article-dir}/illustrations/ — separate illustrations subdirectory"
- label: "independent"
description: "illustrations/{topic-slug}/ — standalone directory in cwd"
```
### Question 4: Save Location
```
header: "Save"
@@ -108,6 +124,7 @@ watermark:
preferred_style:
name: [selected style or null]
description: ""
default_output_dir: imgs-subdir # same-dir | imgs-subdir | illustrations-subdir | independent
language: null
custom_styles: []
---
@@ -55,7 +55,7 @@ Reference Style Extracted (no file):
| Input | Output Directory | Next |
|-------|------------------|------|
| File path | Ask user (1.2) | → 1.2 |
| File path | EXTEND.md `default_output_dir` (default: `imgs-subdir`). If not configured, confirm in 1.2. | → 1.2 |
| Pasted content | `illustrations/{topic-slug}/` | → 1.4 |
**Backup rule for pasted content**: If `source.md` exists in target directory, rename to `source-backup-YYYYMMDD-HHMMSS.md` before saving.
@@ -68,7 +68,7 @@ Check preferences and existing state, then ask ALL needed questions in ONE AskUs
| Question | When to Ask | Options |
|----------|-------------|---------|
| Output directory | No `default_output_dir` in EXTEND.md | `{article-dir}/`, `{article-dir}/imgs/` (Recommended), `{article-dir}/illustrations/`, `illustrations/{topic-slug}/` |
| Output directory | No `default_output_dir` in EXTEND.md | `{article-dir}/imgs/` (Recommended), `{article-dir}/`, `{article-dir}/illustrations/`, `illustrations/{topic-slug}/` |
| Existing images | Target dir has `.png/.jpg/.webp` files | `supplement`, `overwrite`, `regenerate` |
| Article update | Always (file path input) | `update`, `copy` |
@@ -237,7 +237,7 @@ Reference Images:
## Step 4: Generate Outline
Save as `outline.md`:
Save as `{output-dir}/outline.md` (all paths below are relative to the output directory determined in Step 1.1/1.2):
```yaml
---
@@ -285,7 +285,7 @@ references: # Only if references provided
For each illustration in the outline:
1. **Create prompt file**: `prompts/NN-{type}-{slug}.md`
1. **Create prompt file**: `{output-dir}/prompts/NN-{type}-{slug}.md`
2. **Include YAML frontmatter**:
```yaml
---
@@ -381,10 +381,14 @@ Add: `Include a subtle watermark "[content]" at [position].`
### 6.1 Update Article
Insert after corresponding paragraph:
```markdown
![description](illustrations/{slug}/NN-{type}-{slug}.png)
```
Insert after corresponding paragraph, using path relative to article file:
| `default_output_dir` | Insert Path |
|----------------------|-------------|
| `imgs-subdir` | `![description](imgs/NN-{type}-{slug}.png)` |
| `same-dir` | `![description](NN-{type}-{slug}.png)` |
| `illustrations-subdir` | `![description](illustrations/NN-{type}-{slug}.png)` |
| `independent` | `![description](illustrations/{topic-slug}/NN-{type}-{slug}.png)` (relative to cwd) |
Alt text: concise description in article's language.
+13 -1
View File
@@ -162,9 +162,21 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }
5. **Detect language**: Compare source, user input, EXTEND.md preference
6. **Determine output directory**: Per File Structure rules
**⚠️ People in Reference Images — MUST follow all 3 rules:**
If reference images contain **people** who should appear in the cover:
1. **`usage: direct`** — MUST set in refs description file. NEVER use `style` or `palette` when people need to appear
2. **Per-character description** — MUST describe each person's distinctive features (hair, glasses, skin tone, clothing) in `refs/ref-NN-{slug}.md`. Vague descriptions like "a man" will fail
3. **`--ref` flag** — MUST pass reference image via `--ref` in Step 4 so the model sees actual faces
See [reference-images.md § Character Analysis](references/workflow/reference-images.md) for description format.
### Step 2: Confirm Options ⚠️
Full confirmation flow: [references/workflow/confirm-options.md](references/workflow/confirm-options.md)
**MUST use `AskUserQuestion` tool** to present options as interactive selection — NOT plain text tables. Present up to 4 questions in a single `AskUserQuestion` call (Type, Palette, Rendering, Font + Settings). Each question shows the recommended option first with reason, followed by alternatives.
Full confirmation flow and question format: [references/workflow/confirm-options.md](references/workflow/confirm-options.md)
| Condition | Skipped | Still Asked |
|-----------|---------|-------------|
@@ -83,12 +83,17 @@ Full library: [references/visual-elements.md](visual-elements.md)
### Character Handling
When people are needed:
**Default (no reference with people)**:
- Use simplified silhouettes or abstract stick figures
- Symbolic representations (head + shoulders outline)
- NO realistic faces, detailed anatomy, or photographic representations
- Cartoon/icon style consistent with rendering choice
**When reference images contain people**:
- Reference image is passed to model (`usage: direct`) — model must visually reference it to preserve character likeness
- Stylize to match chosen rendering (cartoon/vector), preserving distinctive features (hair, clothing, pose)
- NEVER photorealistic
## Mood Application
Apply mood adjustments to the base palette:
@@ -201,6 +201,12 @@ CRITICAL: The generated cover MUST visually reference the provided images. The c
- [Typography]: [Specific treatment, e.g., "Uppercase text with wide letter-spacing"]
- [Layout element]: [Specific spatial element, e.g., "Bottom banner strip in dark color"]
## From Ref 1 ([filename]) — Characters (if people present):
- **Character 1**: [Appearance, e.g., "Woman, long wavy blonde hair"] → MUST stylize: [e.g., "flat-vector, simplified face, keep blonde hair, label: 'Nicole Forsgren'"]
- **Character 2**: [Appearance, e.g., "Man, short dark hair, stubble"] → MUST stylize: [e.g., "flat-vector, simplified face, keep dark hair, label: 'Gergely Orosz'"]
- **Placement**: [e.g., "Right third, side by side, facing left toward main visual"]
- **Style**: Match rendering style, NOT photorealistic
## From Ref 2 ([filename]) — REQUIRED elements:
[Same detailed breakdown]
@@ -31,8 +31,8 @@ usage: direct | style | palette
| Usage | When to Use |
|-------|-------------|
| `direct` | Reference matches desired output closely |
| `style` | Extract visual style characteristics only |
| `direct` | Model sees reference image directly; required if people must appear in output |
| `style` | Extract visual style only (not for people who must appear) |
| `palette` | Extract color scheme only |
## Verbal Extraction (No File)
@@ -59,6 +59,19 @@ References are high-priority inputs. Extract **specific, concrete, reproducible*
**Output format**: List each element as bullet that can be copy-pasted into prompt as mandatory instruction.
### Character Analysis ⚠️ If Reference Contains People
Use `usage: direct` so model sees the reference image. Additionally describe per character: **appearance**, **pose**, **clothing** → with **transformation rules** (stylize to match rendering).
| Extract | Good | Bad |
|---------|------|-----|
| Appearance | "Woman: long wavy blonde hair, friendly smile" | "A woman" |
| Pose | "Standing, facing camera, confident posture" | "Standing" |
| Clothing | "Dark T-shirt, business casual" | "Formal" |
| Transform | "Flat-vector cartoon, keep hair color & clothing" | "Make cartoon" |
Use `usage: direct`. Output each character as MUST/REQUIRED prompt instruction.
## Verification Output
**For saved files**:
@@ -2,6 +2,7 @@ import process from 'node:process';
import {
CdpConnection,
discoverRunningChromeDebugPort,
findChromeExecutable as findChromeExecutableBase,
findExistingChromeDebugPort,
getFreePort,
@@ -97,6 +98,87 @@ async function is_gemini_session_ready(cookies: CookieMap, verbose: boolean): Pr
}
}
async function fetch_cookies_from_existing_chrome(
timeoutMs: number,
verbose: boolean,
): Promise<CookieMap | null> {
const discovered = await discoverRunningChromeDebugPort();
if (discovered === null) return null;
if (verbose) logger.info(`Found existing Chrome on port ${discovered.port}. Connecting via WebSocket...`);
let cdp: CdpConnection | null = null;
let targetId: string | null = null;
let createdTarget = false;
try {
const connectStart = Date.now();
const connectTimeout = 30_000;
let lastConnErr: unknown = null;
while (Date.now() - connectStart < connectTimeout) {
try {
cdp = await CdpConnection.connect(discovered.wsUrl, 5_000);
break;
} catch (e) {
lastConnErr = e;
if (verbose) logger.debug(`WebSocket connect attempt failed: ${e instanceof Error ? e.message : String(e)}, retrying...`);
await sleep(1000);
}
}
if (!cdp) {
if (verbose) logger.debug(`Could not connect to Chrome after ${connectTimeout / 1000}s: ${lastConnErr instanceof Error ? lastConnErr.message : String(lastConnErr)}`);
return null;
}
const page = await openPageSession({
cdp,
reusing: false,
url: GEMINI_APP_URL,
matchTarget: (target) => target.type === 'page' && target.url.includes('gemini.google.com'),
enableNetwork: true,
activateTarget: false,
});
const { sessionId } = page;
targetId = page.targetId;
createdTarget = page.createdTarget;
if (verbose) logger.debug(createdTarget ? 'No Gemini tab found, creating new tab...' : 'Found existing Gemini tab, attaching...');
const start = Date.now();
let last: CookieMap = {};
while (Date.now() - start < timeoutMs) {
const { cookies } = await cdp.send<{ cookies: Array<{ name: string; value: string }> }>(
'Network.getCookies',
{ urls: ['https://gemini.google.com/', 'https://accounts.google.com/', 'https://www.google.com/'] },
{ sessionId, timeoutMs: 10_000 },
);
const cookieMap: CookieMap = {};
for (const cookie of cookies) {
if (cookie?.name && typeof cookie.value === 'string') cookieMap[cookie.name] = cookie.value;
}
last = cookieMap;
if (await is_gemini_session_ready(cookieMap, verbose)) return cookieMap;
await sleep(1000);
}
if (verbose) logger.debug(`Existing Chrome did not yield valid cookies. Last keys: ${Object.keys(last).join(', ')}`);
return null;
} catch (e) {
if (verbose) logger.debug(`Failed to connect to existing Chrome: ${e instanceof Error ? e.message : String(e)}`);
return null;
} finally {
if (cdp) {
if (createdTarget && targetId) {
try { await cdp.send('Target.closeTarget', { targetId }, { timeoutMs: 5_000 }); } catch {}
}
cdp.close();
}
}
}
async function fetch_google_cookies_via_cdp(
profileDir: string,
timeoutMs: number,
@@ -178,6 +260,19 @@ export async function load_browser_cookies(domain_name: string = '', verbose: bo
if (cached) return { chrome: cached };
}
const hasExplicitProfile = !!(process.env.GEMINI_WEB_CHROME_PROFILE_DIR?.trim() || process.env.BAOYU_CHROME_PROFILE_DIR?.trim());
const existingCookies = hasExplicitProfile ? null : await fetch_cookies_from_existing_chrome(30_000, verbose);
if (existingCookies) {
const filtered: CookieMap = {};
for (const [key, value] of Object.entries(existingCookies)) {
if (typeof value === 'string' && value.length > 0) filtered[key] = value;
}
await write_cookie_file(filtered, resolveGeminiWebCookiePath(), 'cdp-existing');
void domain_name;
return { chrome: filtered };
}
const profileDir = process.env.GEMINI_WEB_CHROME_PROFILE_DIR?.trim() || resolveGeminiWebChromeProfileDir();
const cookies = await fetch_google_cookies_via_cdp(profileDir, 120_000, verbose);
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}
+67 -7
View File
@@ -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
@@ -92,6 +92,12 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider o
# DashScope (阿里通义万象)
${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
# DashScope Qwen-Image 2.0 Pro (recommended for custom sizes and text rendering)
${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9 横幅海报,包含清晰中文标题" --image out.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
# DashScope legacy Qwen fixed-size model
${BUN_X} {baseDir}/scripts/main.ts --prompt "一张电影感海报" --image out.png --provider dashscope --model qwen-image-max --size 1664x928
# Replicate (google/nano-banana-pro)
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
@@ -141,13 +147,13 @@ 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) |
| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; OpenRouter: `google/gemini-3.1-flash-image-preview`) |
| `--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`; DashScope: `qwen-image-2.0-pro`) |
| `--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 +166,16 @@ 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) |
| `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: `qwen-image-2.0-pro`) |
| `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 +183,9 @@ 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` |
@@ -193,6 +207,52 @@ Model priority (highest → lowest), applies to all providers:
- Show: `Using [provider] / [model]`
- Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
### DashScope Models
Use `--model qwen-image-2.0-pro` or set `default_model.dashscope` / `DASHSCOPE_IMAGE_MODEL` when the user wants official Qwen-Image behavior.
Official DashScope model families:
- `qwen-image-2.0-pro`, `qwen-image-2.0-pro-2026-03-03`, `qwen-image-2.0`, `qwen-image-2.0-2026-03-03`
- Free-form `size` in `宽*高` format
- Total pixels must stay between `512*512` and `2048*2048`
- Default size is approximately `1024*1024`
- Best choice for custom ratios such as `21:9` and text-heavy Chinese/English layouts
- `qwen-image-max`, `qwen-image-max-2025-12-30`, `qwen-image-plus`, `qwen-image-plus-2026-01-09`, `qwen-image`
- Fixed sizes only: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`
- Default size is `1664*928`
- `qwen-image` currently has the same capability as `qwen-image-plus`
- Legacy DashScope models such as `z-image-turbo`, `z-image-ultra`, `wanx-v1`
- Keep using them only when the user explicitly asks for legacy behavior or compatibility
When translating CLI args into DashScope behavior:
- `--size` wins over `--ar`
- For `qwen-image-2.0*`, prefer explicit `--size`; otherwise infer from `--ar` and use the official recommended resolutions below
- For `qwen-image-max/plus/image`, only use the five official fixed sizes; if the requested ratio is not covered, switch to `qwen-image-2.0-pro`
- `--quality` is a baoyu-image-gen compatibility preset, not a native DashScope API field. Mapping `normal` / `2k` onto the `qwen-image-2.0*` table below is an implementation inference, not an official API guarantee
Recommended `qwen-image-2.0*` sizes for common aspect ratios:
| Ratio | `normal` | `2k` |
|-------|----------|------|
| `1:1` | `1024*1024` | `1536*1536` |
| `2:3` | `768*1152` | `1024*1536` |
| `3:2` | `1152*768` | `1536*1024` |
| `3:4` | `960*1280` | `1080*1440` |
| `4:3` | `1280*960` | `1440*1080` |
| `9:16` | `720*1280` | `1080*1920` |
| `16:9` | `1280*720` | `1920*1080` |
| `21:9` | `1344*576` | `2048*872` |
DashScope official APIs also expose `negative_prompt`, `prompt_extend`, and `watermark`, but `baoyu-image-gen` does not expose them as dedicated CLI flags today.
Official references:
- [Qwen-Image API](https://help.aliyun.com/zh/model-studio/qwen-image-api)
- [Text-to-image guide](https://help.aliyun.com/zh/model-studio/text-to-image)
- [Qwen-Image Edit API](https://help.aliyun.com/zh/model-studio/qwen-image-edit-api)
### OpenRouter Models
Use full OpenRouter model IDs, e.g.:
@@ -227,7 +287,7 @@ ${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
@@ -50,7 +50,7 @@ options:
- label: "OpenRouter"
description: "Router for Gemini/FLUX/OpenAI-compatible image models"
- label: "DashScope"
description: "Alibaba Cloud - z-image-turbo, good for Chinese content"
description: "Alibaba Cloud - Qwen-Image, strong Chinese/English text rendering"
- label: "Replicate"
description: "Community models - nano-banana-pro, flexible model selection"
```
@@ -186,12 +186,26 @@ options:
header: "DashScope Model"
question: "Choose a default DashScope image generation model?"
options:
- label: "z-image-turbo (Recommended)"
description: "Fast generation, good quality"
- label: "qwen-image-2.0-pro (Recommended)"
description: "Best DashScope model for text rendering and custom sizes"
- label: "qwen-image-2.0"
description: "Faster 2.0 variant with flexible output size"
- label: "qwen-image-max"
description: "Legacy Qwen model with five fixed output sizes"
- label: "qwen-image-plus"
description: "Legacy Qwen model, same current capability as qwen-image"
- label: "z-image-turbo"
description: "Legacy DashScope model for compatibility"
- label: "z-image-ultra"
description: "Higher quality, slower generation"
description: "Legacy DashScope model, higher quality but slower"
```
Notes for DashScope setup:
- Prefer `qwen-image-2.0-pro` when the user needs custom `--size`, uncommon ratios like `21:9`, or strong Chinese/English text rendering.
- `qwen-image-max` / `qwen-image-plus` / `qwen-image` only support five fixed sizes: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`.
- In `baoyu-image-gen`, `quality` is a compatibility preset. It is not a native DashScope parameter.
### Replicate Model Selection
```yaml
@@ -23,7 +23,7 @@ default_model:
google: null # e.g., "gemini-3-pro-image-preview", "gemini-3.1-flash-image-preview"
openai: null # e.g., "gpt-image-1.5", "gpt-image-1"
openrouter: null # e.g., "google/gemini-3.1-flash-image-preview"
dashscope: null # e.g., "z-image-turbo"
dashscope: null # e.g., "qwen-image-2.0-pro"
replicate: null # e.g., "google/nano-banana-pro"
batch:
@@ -88,7 +88,7 @@ default_model:
google: "gemini-3-pro-image-preview"
openai: "gpt-image-1.5"
openrouter: "google/gemini-3.1-flash-image-preview"
dashscope: "z-image-turbo"
dashscope: "qwen-image-2.0-pro"
replicate: "google/nano-banana-pro"
batch:
max_workers: 10
+305
View File
@@ -0,0 +1,305 @@
import assert from "node:assert/strict";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import test, { type TestContext } from "node:test";
import type { CliArgs, ExtendConfig } from "./types.ts";
import {
createTaskArgs,
detectProvider,
getConfiguredMaxWorkers,
getConfiguredProviderRateLimits,
getWorkerCount,
isRetryableGenerationError,
loadBatchTasks,
mergeConfig,
normalizeOutputImagePath,
parseArgs,
parseSimpleYaml,
} from "./main.ts";
function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
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: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
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",
} satisfies Partial<ExtendConfig>,
);
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: Partial<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);
});
+71 -30
View File
@@ -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)
DASHSCOPE_IMAGE_MODEL Default DashScope model (qwen-image-2.0-pro)
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);
});
}
@@ -0,0 +1,148 @@
import assert from "node:assert/strict";
import test, { type TestContext } from "node:test";
import {
getDefaultModel,
getModelFamily,
getQwen2SizeFromAspectRatio,
getSizeFromAspectRatio,
normalizeSize,
parseAspectRatio,
parseSize,
resolveSizeForModel,
} from "./dashscope.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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("DashScope default model prefers env override and otherwise uses qwen-image-2.0-pro", (t) => {
useEnv(t, { DASHSCOPE_IMAGE_MODEL: null });
assert.equal(getDefaultModel(), "qwen-image-2.0-pro");
process.env.DASHSCOPE_IMAGE_MODEL = "qwen-image-max";
assert.equal(getDefaultModel(), "qwen-image-max");
});
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 model family routing distinguishes qwen-2.0, fixed-size qwen, and legacy models", () => {
assert.equal(getModelFamily("qwen-image-2.0-pro"), "qwen2");
assert.equal(getModelFamily("qwen-image"), "qwenFixed");
assert.equal(getModelFamily("z-image-turbo"), "legacy");
assert.equal(getModelFamily("wanx-v1"), "legacy");
});
test("Legacy DashScope size selection keeps the previous quality-based heuristic", () => {
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("Qwen 2.0 recommended sizes follow the official common-ratio table", () => {
assert.equal(getQwen2SizeFromAspectRatio(null, "normal"), "1024*1024");
assert.equal(getQwen2SizeFromAspectRatio(null, "2k"), "1536*1536");
assert.equal(getQwen2SizeFromAspectRatio("16:9", "normal"), "1280*720");
assert.equal(getQwen2SizeFromAspectRatio("21:9", "2k"), "2048*872");
});
test("Qwen 2.0 derives free-form sizes within pixel budget for uncommon ratios", () => {
const size = getQwen2SizeFromAspectRatio("5:2", "normal");
const parsed = parseSize(size);
assert.ok(parsed);
assert.ok(parsed.width * parsed.height >= 512 * 512);
assert.ok(parsed.width * parsed.height <= 2048 * 2048);
assert.ok(Math.abs(parsed.width / parsed.height - 2.5) < 0.08);
});
test("resolveSizeForModel validates explicit qwen-image-2.0 sizes by total pixels", () => {
assert.equal(
resolveSizeForModel("qwen-image-2.0-pro", {
size: "2048x872",
aspectRatio: null,
quality: "2k",
}),
"2048*872",
);
assert.throws(
() =>
resolveSizeForModel("qwen-image-2.0-pro", {
size: "4096x4096",
aspectRatio: null,
quality: "2k",
}),
/total pixels between/,
);
});
test("resolveSizeForModel enforces fixed sizes for qwen-image-max/plus/image", () => {
assert.equal(
resolveSizeForModel("qwen-image-max", {
size: null,
aspectRatio: "1:1",
quality: "2k",
}),
"1328*1328",
);
assert.equal(
resolveSizeForModel("qwen-image", {
size: "1664x928",
aspectRatio: "9:16",
quality: "normal",
}),
"1664*928",
);
assert.throws(
() =>
resolveSizeForModel("qwen-image-max", {
size: null,
aspectRatio: "21:9",
quality: "2k",
}),
/supports only fixed ratios/,
);
assert.throws(
() =>
resolveSizeForModel("qwen-image-plus", {
size: "1024x1024",
aspectRatio: null,
quality: "2k",
}),
/support only these sizes/,
);
});
test("DashScope size normalization converts WxH into provider format", () => {
assert.equal(normalizeSize("1024x1024"), "1024*1024");
assert.equal(normalizeSize("2048*1152"), "2048*1152");
});
@@ -1,28 +1,46 @@
import type { CliArgs } from "../types";
import type { CliArgs, Quality } from "../types";
export function getDefaultModel(): string {
return process.env.DASHSCOPE_IMAGE_MODEL || "z-image-turbo";
}
type DashScopeModelFamily = "qwen2" | "qwenFixed" | "legacy";
function getApiKey(): string | null {
return process.env.DASHSCOPE_API_KEY || null;
}
type DashScopeModelSpec = {
family: DashScopeModelFamily;
defaultSize: string;
};
function getBaseUrl(): string {
const base = process.env.DASHSCOPE_BASE_URL || "https://dashscope.aliyuncs.com";
return base.replace(/\/+$/g, "");
}
const DEFAULT_MODEL = "qwen-image-2.0-pro";
const MIN_QWEN_2_TOTAL_PIXELS = 512 * 512;
const MAX_QWEN_2_TOTAL_PIXELS = 2048 * 2048;
const SIZE_STEP = 16;
const QWEN_NEGATIVE_PROMPT =
"低分辨率,低画质,肢体畸形,手指畸形,画面过饱和,蜡像感,人脸无细节,过度光滑,画面具有AI感,构图混乱,文字模糊,扭曲";
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 };
}
const QWEN_2_TARGET_PIXELS: Record<Quality, number> = {
normal: 1024 * 1024,
"2k": 1536 * 1536,
};
const STANDARD_SIZES: [number, number][] = [
const QWEN_2_RECOMMENDED: Record<string, Record<Quality, string>> = {
"1:1": { normal: "1024*1024", "2k": "1536*1536" },
"2:3": { normal: "768*1152", "2k": "1024*1536" },
"3:2": { normal: "1152*768", "2k": "1536*1024" },
"3:4": { normal: "960*1280", "2k": "1080*1440" },
"4:3": { normal: "1280*960", "2k": "1440*1080" },
"9:16": { normal: "720*1280", "2k": "1080*1920" },
"16:9": { normal: "1280*720", "2k": "1920*1080" },
"21:9": { normal: "1344*576", "2k": "2048*872" },
};
const QWEN_FIXED_SIZES_BY_RATIO: Record<string, string> = {
"16:9": "1664*928",
"4:3": "1472*1104",
"1:1": "1328*1328",
"3:4": "1104*1472",
"9:16": "928*1664",
};
const QWEN_FIXED_SIZES = Object.values(QWEN_FIXED_SIZES_BY_RATIO);
const LEGACY_STANDARD_SIZES: [number, number][] = [
[1024, 1024],
[1280, 720],
[720, 1280],
@@ -34,7 +52,7 @@ const STANDARD_SIZES: [number, number][] = [
[864, 1536],
];
const STANDARD_SIZES_2K: [number, number][] = [
const LEGACY_STANDARD_SIZES_2K: [number, number][] = [
[1536, 1536],
[2048, 1152],
[1152, 2048],
@@ -45,9 +63,167 @@ const STANDARD_SIZES_2K: [number, number][] = [
[2048, 2048],
];
function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
const is2k = quality === "2k";
const defaultSize = is2k ? "1536*1536" : "1024*1024";
const QWEN_2_SPEC: DashScopeModelSpec = {
family: "qwen2",
defaultSize: "1024*1024",
};
const QWEN_FIXED_SPEC: DashScopeModelSpec = {
family: "qwenFixed",
defaultSize: QWEN_FIXED_SIZES_BY_RATIO["16:9"],
};
const LEGACY_SPEC: DashScopeModelSpec = {
family: "legacy",
defaultSize: "1536*1536",
};
const MODEL_SPEC_ALIASES: Record<string, DashScopeModelSpec> = {
"qwen-image-2.0-pro": QWEN_2_SPEC,
"qwen-image-2.0-pro-2026-03-03": QWEN_2_SPEC,
"qwen-image-2.0": QWEN_2_SPEC,
"qwen-image-2.0-2026-03-03": QWEN_2_SPEC,
"qwen-image-max": QWEN_FIXED_SPEC,
"qwen-image-max-2025-12-30": QWEN_FIXED_SPEC,
"qwen-image-plus": QWEN_FIXED_SPEC,
"qwen-image-plus-2026-01-09": QWEN_FIXED_SPEC,
"qwen-image": QWEN_FIXED_SPEC,
};
export function getDefaultModel(): string {
return process.env.DASHSCOPE_IMAGE_MODEL || DEFAULT_MODEL;
}
function getApiKey(): string | null {
return process.env.DASHSCOPE_API_KEY || null;
}
function getBaseUrl(): string {
const base = process.env.DASHSCOPE_BASE_URL || "https://dashscope.aliyuncs.com";
return base.replace(/\/+$/g, "");
}
function getModelSpec(model: string): DashScopeModelSpec {
return MODEL_SPEC_ALIASES[model.trim().toLowerCase()] || LEGACY_SPEC;
}
export function getModelFamily(model: string): DashScopeModelFamily {
return getModelSpec(model).family;
}
function normalizeQuality(quality: CliArgs["quality"]): Quality {
return quality === "normal" ? "normal" : "2k";
}
export function parseAspectRatio(ar: string): { width: number; height: number } | null {
const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
if (!match) return null;
const w = parseFloat(match[1]!);
const h = parseFloat(match[2]!);
if (w <= 0 || h <= 0) return null;
return { width: w, height: h };
}
export function normalizeSize(size: string): string {
return size.replace("x", "*");
}
export function parseSize(size: string): { width: number; height: number } | null {
const match = normalizeSize(size).match(/^(\d+)\*(\d+)$/);
if (!match) return null;
const width = Number(match[1]);
const height = Number(match[2]);
if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
return null;
}
return { width, height };
}
function formatSize(width: number, height: number): string {
return `${width}*${height}`;
}
function getRatioValue(ar: string): number | null {
const parsed = parseAspectRatio(ar);
if (!parsed) return null;
return parsed.width / parsed.height;
}
function findKnownRatioKey(ar: string, candidates: string[], tolerance = 0.02): string | null {
const targetRatio = getRatioValue(ar);
if (targetRatio == null) return null;
let bestKey: string | null = null;
let bestDiff = Infinity;
for (const candidate of candidates) {
const candidateRatio = getRatioValue(candidate);
if (candidateRatio == null) continue;
const diff = Math.abs(candidateRatio - targetRatio);
if (diff < bestDiff) {
bestDiff = diff;
bestKey = candidate;
}
}
return bestDiff <= tolerance ? bestKey : null;
}
function roundToStep(value: number): number {
return Math.max(SIZE_STEP, Math.round(value / SIZE_STEP) * SIZE_STEP);
}
function fitToPixelBudget(
width: number,
height: number,
minPixels: number,
maxPixels: number,
): { width: number; height: number } {
let nextWidth = width;
let nextHeight = height;
let pixels = nextWidth * nextHeight;
if (pixels > maxPixels) {
const scale = Math.sqrt(maxPixels / pixels);
nextWidth *= scale;
nextHeight *= scale;
} else if (pixels < minPixels) {
const scale = Math.sqrt(minPixels / pixels);
nextWidth *= scale;
nextHeight *= scale;
}
let roundedWidth = roundToStep(nextWidth);
let roundedHeight = roundToStep(nextHeight);
pixels = roundedWidth * roundedHeight;
while (pixels > maxPixels && (roundedWidth > SIZE_STEP || roundedHeight > SIZE_STEP)) {
if (roundedWidth >= roundedHeight && roundedWidth > SIZE_STEP) {
roundedWidth -= SIZE_STEP;
} else if (roundedHeight > SIZE_STEP) {
roundedHeight -= SIZE_STEP;
} else {
break;
}
pixels = roundedWidth * roundedHeight;
}
while (pixels < minPixels) {
if (roundedWidth <= roundedHeight) {
roundedWidth += SIZE_STEP;
} else {
roundedHeight += SIZE_STEP;
}
pixels = roundedWidth * roundedHeight;
}
return { width: roundedWidth, height: roundedHeight };
}
export function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
const normalizedQuality = normalizeQuality(quality);
const sizes = normalizedQuality === "2k" ? LEGACY_STANDARD_SIZES_2K : LEGACY_STANDARD_SIZES;
const defaultSize = normalizedQuality === "2k" ? "1536*1536" : "1024*1024";
if (!ar) return defaultSize;
@@ -55,86 +231,157 @@ function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]):
if (!parsed) return defaultSize;
const targetRatio = parsed.width / parsed.height;
const sizes = is2k ? STANDARD_SIZES_2K : STANDARD_SIZES;
let best = defaultSize;
let bestDiff = Infinity;
for (const [w, h] of sizes) {
const diff = Math.abs(w / h - targetRatio);
for (const [width, height] of sizes) {
const diff = Math.abs(width / height - targetRatio);
if (diff < bestDiff) {
bestDiff = diff;
best = `${w}*${h}`;
best = formatSize(width, height);
}
}
return best;
}
function normalizeSize(size: string): string {
return size.replace("x", "*");
export function getQwen2SizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
const normalizedQuality = normalizeQuality(quality);
if (!ar) {
return QWEN_2_RECOMMENDED["1:1"][normalizedQuality];
}
const recommendedRatio = findKnownRatioKey(ar, Object.keys(QWEN_2_RECOMMENDED));
if (recommendedRatio) {
return QWEN_2_RECOMMENDED[recommendedRatio][normalizedQuality];
}
const parsed = parseAspectRatio(ar);
if (!parsed) {
return QWEN_2_RECOMMENDED["1:1"][normalizedQuality];
}
const targetRatio = parsed.width / parsed.height;
const targetPixels = QWEN_2_TARGET_PIXELS[normalizedQuality];
const rawWidth = Math.sqrt(targetPixels * targetRatio);
const rawHeight = Math.sqrt(targetPixels / targetRatio);
const fitted = fitToPixelBudget(
rawWidth,
rawHeight,
MIN_QWEN_2_TOTAL_PIXELS,
MAX_QWEN_2_TOTAL_PIXELS,
);
return formatSize(fitted.width, fitted.height);
}
export async function generateImage(
prompt: string,
model: string,
args: CliArgs
): Promise<Uint8Array> {
const apiKey = getApiKey();
if (!apiKey) throw new Error("DASHSCOPE_API_KEY is required");
if (args.referenceImages.length > 0) {
throw new Error(
"Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
function getQwenFixedSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
if (quality === "normal") {
console.warn(
"DashScope qwen-image-max/plus/image models use fixed output sizes; --quality normal does not change the generated resolution."
);
}
const size = args.size ? normalizeSize(args.size) : getSizeFromAspectRatio(args.aspectRatio, args.quality);
const url = `${getBaseUrl()}/api/v1/services/aigc/multimodal-generation/generation`;
if (!ar) return QWEN_FIXED_SPEC.defaultSize;
const body = {
model,
input: {
messages: [
{
role: "user",
content: [{ text: prompt }],
},
],
},
parameters: {
prompt_extend: false,
size,
},
};
console.log(`Generating image with DashScope (${model})...`, { size });
const res = await fetch(url, {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${apiKey}`,
},
body: JSON.stringify(body),
});
if (!res.ok) {
const err = await res.text();
throw new Error(`DashScope API error (${res.status}): ${err}`);
const ratioKey = findKnownRatioKey(ar, Object.keys(QWEN_FIXED_SIZES_BY_RATIO));
if (!ratioKey) {
throw new Error(
`DashScope model supports only fixed ratios ${Object.keys(QWEN_FIXED_SIZES_BY_RATIO).join(", ")}. ` +
`For custom ratios like "${ar}", use --model qwen-image-2.0-pro.`
);
}
const result = await res.json() as {
output?: {
result_image?: string;
choices?: Array<{
message?: {
content?: Array<{ image?: string }>;
};
}>;
};
return QWEN_FIXED_SIZES_BY_RATIO[ratioKey]!;
}
function validateSizeFormat(size: string): { width: number; height: number } {
const parsed = parseSize(size);
if (!parsed) {
throw new Error(`Invalid DashScope size "${size}". Expected <width>x<height> or <width>*<height>.`);
}
return parsed;
}
function validateQwen2Size(size: string): string {
const normalized = normalizeSize(size);
const parsed = validateSizeFormat(normalized);
const totalPixels = parsed.width * parsed.height;
if (totalPixels < MIN_QWEN_2_TOTAL_PIXELS || totalPixels > MAX_QWEN_2_TOTAL_PIXELS) {
throw new Error(
`DashScope qwen-image-2.0* models require total pixels between ${MIN_QWEN_2_TOTAL_PIXELS} ` +
`and ${MAX_QWEN_2_TOTAL_PIXELS}. Received ${normalized} (${totalPixels} pixels).`
);
}
return normalized;
}
function validateQwenFixedSize(size: string): string {
const normalized = normalizeSize(size);
validateSizeFormat(normalized);
if (!QWEN_FIXED_SIZES.includes(normalized)) {
throw new Error(
`DashScope qwen-image-max/plus/image models support only these sizes: ${QWEN_FIXED_SIZES.join(", ")}. ` +
`Received ${normalized}.`
);
}
return normalized;
}
export function resolveSizeForModel(
model: string,
args: Pick<CliArgs, "size" | "aspectRatio" | "quality">,
): string {
const spec = getModelSpec(model);
if (args.size) {
if (spec.family === "qwen2") return validateQwen2Size(args.size);
if (spec.family === "qwenFixed") return validateQwenFixedSize(args.size);
validateSizeFormat(args.size);
return normalizeSize(args.size);
}
if (spec.family === "qwen2") {
return getQwen2SizeFromAspectRatio(args.aspectRatio, args.quality);
}
if (spec.family === "qwenFixed") {
return getQwenFixedSizeFromAspectRatio(args.aspectRatio, args.quality);
}
return getSizeFromAspectRatio(args.aspectRatio, args.quality);
}
function buildParameters(
family: DashScopeModelFamily,
size: string,
): Record<string, unknown> {
const parameters: Record<string, unknown> = {
prompt_extend: false,
size,
};
if (family === "qwen2" || family === "qwenFixed") {
parameters.watermark = false;
parameters.negative_prompt = QWEN_NEGATIVE_PROMPT;
}
return parameters;
}
type DashScopeResponse = {
output?: {
result_image?: string;
choices?: Array<{
message?: {
content?: Array<{ image?: string }>;
};
}>;
};
};
async function extractImageFromResponse(result: DashScopeResponse): Promise<Uint8Array> {
let imageData: string | null = null;
if (result.output?.result_image) {
@@ -163,3 +410,54 @@ export async function generateImage(
return Uint8Array.from(Buffer.from(imageData, "base64"));
}
export async function generateImage(
prompt: string,
model: string,
args: CliArgs
): Promise<Uint8Array> {
const apiKey = getApiKey();
if (!apiKey) throw new Error("DASHSCOPE_API_KEY is required");
if (args.referenceImages.length > 0) {
throw new Error(
"Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
);
}
const spec = getModelSpec(model);
const size = resolveSizeForModel(model, args);
const url = `${getBaseUrl()}/api/v1/services/aigc/multimodal-generation/generation`;
const body = {
model,
input: {
messages: [
{
role: "user",
content: [{ text: prompt }],
},
],
},
parameters: buildParameters(spec.family, size),
};
console.log(`Generating image with DashScope (${model})...`, { family: spec.family, size });
const res = await fetch(url, {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${apiKey}`,
},
body: JSON.stringify(body),
});
if (!res.ok) {
const err = await res.text();
throw new Error(`DashScope API error (${res.status}): ${err}`);
}
const result = await res.json() as DashScopeResponse;
return extractImageFromResponse(result);
}
@@ -0,0 +1,126 @@
import assert from "node:assert/strict";
import test, { type TestContext } from "node:test";
import type { CliArgs } from "../types.ts";
import {
addAspectRatioToPrompt,
buildGoogleUrl,
buildPromptWithAspect,
extractInlineImageData,
extractPredictedImageData,
getGoogleImageSize,
isGoogleImagen,
isGoogleMultimodal,
normalizeGoogleModelId,
} from "./google.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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;
}
}
});
}
function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
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,
};
}
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(makeArgs({ imageSize: null, quality: "2k" })), "2K");
assert.equal(getGoogleImageSize(makeArgs({ 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",
);
});
@@ -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 {
@@ -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;
}
@@ -0,0 +1,56 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
extractImageFromResponse,
getMimeType,
getOpenAISize,
parseAspectRatio,
} from "./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/,
);
});
@@ -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) {
@@ -0,0 +1,101 @@
import assert from "node:assert/strict";
import test from "node:test";
import type { CliArgs } from "../types.ts";
import {
buildInput,
extractOutputUrl,
parseModelId,
} from "./replicate.ts";
function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
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,
};
}
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" } as never),
"https://example.com/a.png",
);
assert.equal(
extractOutputUrl({ output: ["https://example.com/b.png"] } as never),
"https://example.com/b.png",
);
assert.equal(
extractOutputUrl({ output: { url: "https://example.com/c.png" } } as never),
"https://example.com/c.png",
);
assert.throws(
() => extractOutputUrl({ output: { invalid: true } } as never),
/Unexpected Replicate output format/,
);
});
@@ -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 ${MAX_POLL_MS / 1000}s`);
}
function extractOutputUrl(prediction: PredictionResponse): string {
export function extractOutputUrl(prediction: PredictionResponse): string {
const output = prediction.output;
if (typeof output === "string") return output;
@@ -0,0 +1,111 @@
import type { CliArgs } from "../types";
export function getDefaultModel(): string {
return process.env.SEEDREAM_IMAGE_MODEL || "doubao-seedream-5-0-260128";
}
function getApiKey(): string | null {
return process.env.ARK_API_KEY || null;
}
function getBaseUrl(): string {
return process.env.SEEDREAM_BASE_URL || "https://ark.cn-beijing.volces.com/api/v3";
}
/**
* Convert aspect ratio to Seedream size format
* Seedream API accepts: "2k" (default), "3k", or WIDTHxHEIGHT format
* Note: API uses lowercase "2k"/"3k", not "2K"/"3K"
*/
function getSeedreamSize(ar: string | null, quality: CliArgs["quality"], imageSize?: string | null): string {
// If explicit size is provided
if (imageSize) {
const upper = imageSize.toUpperCase();
if (upper === "2K" || upper === "3K") {
return upper.toLowerCase(); // API expects "2k" or "3k"
}
// For widthxheight format, pass through as-is
if (imageSize.includes("x")) {
return imageSize;
}
}
// Default to 2k (smallest option supported by API)
return "2k";
}
type SeedreamImageResponse = {
model: string;
created: number;
data: Array<{
url: string;
size: string;
}>;
usage: {
generated_images: number;
output_tokens: number;
total_tokens: number;
};
};
export async function generateImage(
prompt: string,
model: string,
args: CliArgs
): Promise<Uint8Array> {
const apiKey = getApiKey();
if (!apiKey) {
throw new Error(
"ARK_API_KEY is required. " +
"Get your API key from https://console.volcengine.com/ark"
);
}
const baseUrl = getBaseUrl();
const size = getSeedreamSize(args.aspectRatio, args.quality, args.imageSize);
console.error(`Calling Seedream API (${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);
}
+3 -1
View File
@@ -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;
@@ -0,0 +1,93 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
extractSummaryFromBody,
extractTitleFromMarkdown,
parseFrontmatter,
pickFirstString,
serializeFrontmatter,
stripWrappingQuotes,
toFrontmatterString,
} from "./content.ts";
test("parseFrontmatter extracts YAML fields and strips wrapping quotes", () => {
const input = `---
title: "Hello World"
author: Baoyu
summary: plain text
---
# Heading
Body`;
const result = parseFrontmatter(input);
assert.deepEqual(result.frontmatter, {
title: "Hello World",
author: "Baoyu",
summary: "plain text",
});
assert.match(result.body, /^# Heading/);
});
test("parseFrontmatter returns original content when no frontmatter exists", () => {
const input = "# No frontmatter";
assert.deepEqual(parseFrontmatter(input), {
frontmatter: {},
body: input,
});
});
test("serializeFrontmatter renders YAML only when fields exist", () => {
assert.equal(serializeFrontmatter({}), "");
assert.equal(
serializeFrontmatter({ title: "Hello", author: "Baoyu" }),
"---\ntitle: Hello\nauthor: Baoyu\n---\n",
);
});
test("quote and frontmatter string helpers normalize mixed scalar values", () => {
assert.equal(stripWrappingQuotes(`" quoted "`), "quoted");
assert.equal(stripWrappingQuotes("“ 中文标题 ”"), "中文标题");
assert.equal(stripWrappingQuotes("plain"), "plain");
assert.equal(toFrontmatterString("'hello'"), "hello");
assert.equal(toFrontmatterString(42), "42");
assert.equal(toFrontmatterString(false), "false");
assert.equal(toFrontmatterString({}), undefined);
assert.equal(
pickFirstString({ summary: 123, title: "" }, ["title", "summary"]),
"123",
);
});
test("markdown title and summary extraction skip non-body content and clean formatting", () => {
const markdown = `
![cover](cover.png)
## My Title
Body paragraph
`;
assert.equal(extractTitleFromMarkdown(markdown), "My Title");
const summary = extractSummaryFromBody(
`
# Heading
> quote
- list
1. ordered
\`\`\`
code
\`\`\`
This is **the first paragraph** with [a link](https://example.com) and \`inline code\` that should be summarized cleanly.
`,
70,
);
assert.equal(
summary,
"This is the first paragraph with a link and inline code that should...",
);
});
@@ -0,0 +1,140 @@
import assert from "node:assert/strict";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import { COLOR_PRESETS, FONT_FAMILY_MAP } from "./constants.ts";
import {
buildMarkdownDocumentMeta,
formatTimestamp,
resolveColorToken,
resolveFontFamilyToken,
resolveMarkdownStyle,
resolveRenderOptions,
} from "./document.ts";
function useCwd(t: TestContext, cwd: string): void {
const previous = process.cwd();
process.chdir(cwd);
t.after(() => {
process.chdir(previous);
});
}
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("document token resolvers map known presets and allow passthrough values", () => {
assert.equal(resolveColorToken("green"), COLOR_PRESETS.green);
assert.equal(resolveColorToken("#123456"), "#123456");
assert.equal(resolveColorToken(), undefined);
assert.equal(resolveFontFamilyToken("mono"), FONT_FAMILY_MAP.mono);
assert.equal(resolveFontFamilyToken("Custom Font"), "Custom Font");
assert.equal(resolveFontFamilyToken(), undefined);
});
test("formatTimestamp uses compact sortable datetime output", () => {
const date = new Date("2026-03-13T21:04:05.000Z");
const pad = (value: number) => String(value).padStart(2, "0");
const expected = `${date.getFullYear()}${pad(date.getMonth() + 1)}${pad(
date.getDate(),
)}${pad(date.getHours())}${pad(date.getMinutes())}${pad(date.getSeconds())}`;
assert.equal(formatTimestamp(date), expected);
});
test("buildMarkdownDocumentMeta prefers frontmatter and falls back to markdown title and summary", () => {
const metaFromYaml = buildMarkdownDocumentMeta(
"# Markdown Title\n\nBody summary paragraph that should be ignored.",
{
title: `" YAML Title "`,
author: "'Baoyu'",
summary: `" YAML Summary "`,
},
"fallback",
);
assert.deepEqual(metaFromYaml, {
title: "YAML Title",
author: "Baoyu",
description: "YAML Summary",
});
const metaFromMarkdown = buildMarkdownDocumentMeta(
`## “Markdown Title”\n\nThis is the first body paragraph that should become the summary because it is long enough.`,
{},
"fallback",
);
assert.equal(metaFromMarkdown.title, "Markdown Title");
assert.match(metaFromMarkdown.description ?? "", /^This is the first body paragraph/);
});
test("resolveMarkdownStyle merges theme defaults with explicit overrides", () => {
const style = resolveMarkdownStyle({
theme: "modern",
primaryColor: "#112233",
fontFamily: "Custom Sans",
});
assert.equal(style.primaryColor, "#112233");
assert.equal(style.fontFamily, "Custom Sans");
assert.equal(style.fontSize, "15px");
assert.equal(style.containerBg, "rgba(250, 249, 245, 1)");
});
test("resolveRenderOptions loads workspace EXTEND settings and lets explicit options win", async (t) => {
const root = await makeTempDir("baoyu-md-render-options-");
useCwd(t, root);
const extendPath = path.join(
root,
".baoyu-skills",
"baoyu-markdown-to-html",
"EXTEND.md",
);
await fs.mkdir(path.dirname(extendPath), { recursive: true });
await fs.writeFile(
extendPath,
`---
default_theme: modern
default_color: green
default_font_family: mono
default_font_size: 17
default_code_theme: nord
mac_code_block: false
show_line_number: true
cite: true
count: true
legend: title-alt
keep_title: true
---
`,
);
const fromExtend = resolveRenderOptions();
assert.equal(fromExtend.theme, "modern");
assert.equal(fromExtend.primaryColor, COLOR_PRESETS.green);
assert.equal(fromExtend.fontFamily, FONT_FAMILY_MAP.mono);
assert.equal(fromExtend.fontSize, "17px");
assert.equal(fromExtend.codeTheme, "nord");
assert.equal(fromExtend.isMacCodeBlock, false);
assert.equal(fromExtend.isShowLineNumber, true);
assert.equal(fromExtend.citeStatus, true);
assert.equal(fromExtend.countStatus, true);
assert.equal(fromExtend.legend, "title-alt");
assert.equal(fromExtend.keepTitle, true);
const explicit = resolveRenderOptions({
theme: "simple",
fontSize: "18px",
keepTitle: false,
});
assert.equal(explicit.theme, "simple");
assert.equal(explicit.fontSize, "18px");
assert.equal(explicit.keepTitle, false);
});
@@ -0,0 +1,71 @@
import assert from "node:assert/strict";
import test from "node:test";
import { DEFAULT_STYLE } from "./constants.ts";
import {
buildCss,
buildHtmlDocument,
modifyHtmlStructure,
normalizeCssText,
normalizeInlineCss,
removeFirstHeading,
} from "./html-builder.ts";
test("buildCss injects style variables and concatenates base and theme CSS", () => {
const css = buildCss("body { color: red; }", ".theme { color: blue; }");
assert.match(css, /--md-primary-color: #0F4C81;/);
assert.match(css, /body \{ color: red; \}/);
assert.match(css, /\.theme \{ color: blue; \}/);
});
test("buildHtmlDocument includes optional meta tags and code theme CSS", () => {
const html = buildHtmlDocument(
{
title: "Doc",
author: "Baoyu",
description: "Summary",
},
"body { color: red; }",
"<article>Hello</article>",
".hljs { color: blue; }",
);
assert.match(html, /<title>Doc<\/title>/);
assert.match(html, /meta name="author" content="Baoyu"/);
assert.match(html, /meta name="description" content="Summary"/);
assert.match(html, /<style>body \{ color: red; \}<\/style>/);
assert.match(html, /<style>\.hljs \{ color: blue; \}<\/style>/);
assert.match(html, /<article>Hello<\/article>/);
});
test("normalizeCssText and normalizeInlineCss replace variables and strip declarations", () => {
const rawCss = `
:root { --md-primary-color: #000; --md-font-size: 12px; --foreground: 0 0% 5%; }
.box { color: var(--md-primary-color); font-size: var(--md-font-size); background: hsl(var(--foreground)); }
`;
const normalizedCss = normalizeCssText(rawCss, DEFAULT_STYLE);
assert.match(normalizedCss, /color: #0F4C81/);
assert.match(normalizedCss, /font-size: 16px/);
assert.match(normalizedCss, /background: #3f3f3f/);
assert.doesNotMatch(normalizedCss, /--md-primary-color/);
const normalizedHtml = normalizeInlineCss(
`<style>${rawCss}</style><div style="color: var(--md-primary-color)"></div>`,
DEFAULT_STYLE,
);
assert.match(normalizedHtml, /color: #0F4C81/);
assert.doesNotMatch(normalizedHtml, /var\(--md-primary-color\)/);
});
test("HTML structure helpers hoist nested lists and remove the first heading", () => {
const nestedList = `<ul><li>Parent<ul><li>Child</li></ul></li></ul>`;
assert.equal(
modifyHtmlStructure(nestedList),
`<ul><li>Parent</li><ul><li>Child</li></ul></ul>`,
);
const html = `<h1>Title</h1><p>Intro</p><h2>Sub</h2>`;
assert.equal(removeFirstHeading(html), `<p>Intro</p><h2>Sub</h2>`);
});
@@ -0,0 +1,79 @@
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 {
getImageExtension,
replaceMarkdownImagesWithPlaceholders,
resolveContentImages,
resolveImagePath,
} from "./images.ts";
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("replaceMarkdownImagesWithPlaceholders rewrites markdown and tracks image metadata", () => {
const result = replaceMarkdownImagesWithPlaceholders(
`![cover](images/cover.png)\n\nText\n\n![diagram](images/diagram.webp)`,
"IMG_",
);
assert.equal(result.markdown, `IMG_1\n\nText\n\nIMG_2`);
assert.deepEqual(result.images, [
{ alt: "cover", originalPath: "images/cover.png", placeholder: "IMG_1" },
{ alt: "diagram", originalPath: "images/diagram.webp", placeholder: "IMG_2" },
]);
});
test("image extension and local fallback resolution handle common path variants", async (t) => {
assert.equal(getImageExtension("https://example.com/a.jpeg?x=1"), "jpeg");
assert.equal(getImageExtension("/tmp/figure"), "png");
const root = await makeTempDir("baoyu-md-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "figure.webp"), "webp");
const resolved = await resolveImagePath("figure.png", baseDir, tempDir, "test");
assert.equal(resolved, path.join(baseDir, "figure.webp"));
});
test("resolveContentImages resolves image placeholders against the content directory", async (t) => {
const root = await makeTempDir("baoyu-md-content-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "cover.png"), "png");
const resolved = await resolveContentImages(
[
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
},
],
baseDir,
tempDir,
"test",
);
assert.deepEqual(resolved, [
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
localPath: path.join(baseDir, "cover.png"),
},
]);
});
@@ -0,0 +1,64 @@
import assert from "node:assert/strict";
import test from "node:test";
import { initRenderer, renderMarkdown } from "./renderer.ts";
const render = (md: string) => {
const r = initRenderer();
return renderMarkdown(md, r).html;
};
test("bold with inline code (no underscore)", () => {
const html = render("**算出 `logits`,算出 `loss`。**");
assert.match(html, /<code[^>]*>logits<\/code>/);
assert.match(html, /<code[^>]*>loss<\/code>/);
});
test("bold with inline code (contains underscore)", () => {
const html = render("**变成 `input_ids`。**");
assert.match(html, /<code[^>]*>input_ids<\/code>/);
});
test("emphasis with inline code", () => {
const html = render("*查看 `hidden_states`*");
assert.match(html, /<code[^>]*>hidden_states<\/code>/);
});
test("plain inline code (regression)", () => {
const html = render("`lm_head`");
assert.match(html, /<code[^>]*>lm_head<\/code>/);
});
test("bold without code (regression)", () => {
const html = render("**纯粗体文本**");
assert.match(html, /<strong[^>]*>纯粗体文本<\/strong>/);
assert.doesNotMatch(html, /<code/);
});
test("bold with inline code containing backticks", () => {
const html = render("**``a`b``**");
assert.match(html, /<code[^>]*>a&#96;b<\/code>/);
});
test("emphasis with inline code containing backticks", () => {
const html = render("*``a`b``*");
assert.match(html, /<em[^>]*><code[^>]*>a&#96;b<\/code><\/em>/);
});
test("bold with inline code containing consecutive backticks", () => {
const html = render("**```a``b```**");
assert.match(html, /<code[^>]*>a&#96;&#96;b<\/code>/);
});
test("bold with inline code containing only backticks", () => {
const html = render("**```` `` ````**");
assert.match(html, /<code[^>]*>&#96;&#96;<\/code>/);
});
test("bold with inline code containing only spaces", () => {
const oneSpace = render("**`` ``**");
assert.match(oneSpace, /<code[^>]*> <\/code>/);
const twoSpaces = render("**`` ``**");
assert.match(twoSpaces, /<code[^>]*> <\/code>/);
});
@@ -109,6 +109,13 @@ function parseFrontMatterAndContent(markdownText: string): ParseResult {
}
}
function wrapInlineCode(value: string): string {
const runs = value.match(/`+/g);
const fence = "`".repeat(Math.max(...(runs?.map((run) => run.length) ?? [0])) + 1);
const padding = /^ *$/.test(value) ? "" : " ";
return `${fence}${padding}${value}${padding}${fence}`;
}
export function initRenderer(opts: IOpts = {}): RendererAPI {
const footnotes: [number, string, string][] = [];
let footnoteIndex = 0;
@@ -369,6 +376,7 @@ function preprocessCjkEmphasis(markdown: string): string {
const tree = processor.parse(markdown);
const extractText = (node: any): string => {
if (node.type === "text") return node.value;
if (node.type === "inlineCode") return wrapInlineCode(node.value);
if (node.children) return node.children.map(extractText).join("");
return "";
};
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}
@@ -0,0 +1,93 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
extractSummaryFromBody,
extractTitleFromMarkdown,
parseFrontmatter,
pickFirstString,
serializeFrontmatter,
stripWrappingQuotes,
toFrontmatterString,
} from "./content.ts";
test("parseFrontmatter extracts YAML fields and strips wrapping quotes", () => {
const input = `---
title: "Hello World"
author: Baoyu
summary: plain text
---
# Heading
Body`;
const result = parseFrontmatter(input);
assert.deepEqual(result.frontmatter, {
title: "Hello World",
author: "Baoyu",
summary: "plain text",
});
assert.match(result.body, /^# Heading/);
});
test("parseFrontmatter returns original content when no frontmatter exists", () => {
const input = "# No frontmatter";
assert.deepEqual(parseFrontmatter(input), {
frontmatter: {},
body: input,
});
});
test("serializeFrontmatter renders YAML only when fields exist", () => {
assert.equal(serializeFrontmatter({}), "");
assert.equal(
serializeFrontmatter({ title: "Hello", author: "Baoyu" }),
"---\ntitle: Hello\nauthor: Baoyu\n---\n",
);
});
test("quote and frontmatter string helpers normalize mixed scalar values", () => {
assert.equal(stripWrappingQuotes(`" quoted "`), "quoted");
assert.equal(stripWrappingQuotes("“ 中文标题 ”"), "中文标题");
assert.equal(stripWrappingQuotes("plain"), "plain");
assert.equal(toFrontmatterString("'hello'"), "hello");
assert.equal(toFrontmatterString(42), "42");
assert.equal(toFrontmatterString(false), "false");
assert.equal(toFrontmatterString({}), undefined);
assert.equal(
pickFirstString({ summary: 123, title: "" }, ["title", "summary"]),
"123",
);
});
test("markdown title and summary extraction skip non-body content and clean formatting", () => {
const markdown = `
![cover](cover.png)
## My Title
Body paragraph
`;
assert.equal(extractTitleFromMarkdown(markdown), "My Title");
const summary = extractSummaryFromBody(
`
# Heading
> quote
- list
1. ordered
\`\`\`
code
\`\`\`
This is **the first paragraph** with [a link](https://example.com) and \`inline code\` that should be summarized cleanly.
`,
70,
);
assert.equal(
summary,
"This is the first paragraph with a link and inline code that should...",
);
});
@@ -0,0 +1,140 @@
import assert from "node:assert/strict";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import { COLOR_PRESETS, FONT_FAMILY_MAP } from "./constants.ts";
import {
buildMarkdownDocumentMeta,
formatTimestamp,
resolveColorToken,
resolveFontFamilyToken,
resolveMarkdownStyle,
resolveRenderOptions,
} from "./document.ts";
function useCwd(t: TestContext, cwd: string): void {
const previous = process.cwd();
process.chdir(cwd);
t.after(() => {
process.chdir(previous);
});
}
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("document token resolvers map known presets and allow passthrough values", () => {
assert.equal(resolveColorToken("green"), COLOR_PRESETS.green);
assert.equal(resolveColorToken("#123456"), "#123456");
assert.equal(resolveColorToken(), undefined);
assert.equal(resolveFontFamilyToken("mono"), FONT_FAMILY_MAP.mono);
assert.equal(resolveFontFamilyToken("Custom Font"), "Custom Font");
assert.equal(resolveFontFamilyToken(), undefined);
});
test("formatTimestamp uses compact sortable datetime output", () => {
const date = new Date("2026-03-13T21:04:05.000Z");
const pad = (value: number) => String(value).padStart(2, "0");
const expected = `${date.getFullYear()}${pad(date.getMonth() + 1)}${pad(
date.getDate(),
)}${pad(date.getHours())}${pad(date.getMinutes())}${pad(date.getSeconds())}`;
assert.equal(formatTimestamp(date), expected);
});
test("buildMarkdownDocumentMeta prefers frontmatter and falls back to markdown title and summary", () => {
const metaFromYaml = buildMarkdownDocumentMeta(
"# Markdown Title\n\nBody summary paragraph that should be ignored.",
{
title: `" YAML Title "`,
author: "'Baoyu'",
summary: `" YAML Summary "`,
},
"fallback",
);
assert.deepEqual(metaFromYaml, {
title: "YAML Title",
author: "Baoyu",
description: "YAML Summary",
});
const metaFromMarkdown = buildMarkdownDocumentMeta(
`## “Markdown Title”\n\nThis is the first body paragraph that should become the summary because it is long enough.`,
{},
"fallback",
);
assert.equal(metaFromMarkdown.title, "Markdown Title");
assert.match(metaFromMarkdown.description ?? "", /^This is the first body paragraph/);
});
test("resolveMarkdownStyle merges theme defaults with explicit overrides", () => {
const style = resolveMarkdownStyle({
theme: "modern",
primaryColor: "#112233",
fontFamily: "Custom Sans",
});
assert.equal(style.primaryColor, "#112233");
assert.equal(style.fontFamily, "Custom Sans");
assert.equal(style.fontSize, "15px");
assert.equal(style.containerBg, "rgba(250, 249, 245, 1)");
});
test("resolveRenderOptions loads workspace EXTEND settings and lets explicit options win", async (t) => {
const root = await makeTempDir("baoyu-md-render-options-");
useCwd(t, root);
const extendPath = path.join(
root,
".baoyu-skills",
"baoyu-markdown-to-html",
"EXTEND.md",
);
await fs.mkdir(path.dirname(extendPath), { recursive: true });
await fs.writeFile(
extendPath,
`---
default_theme: modern
default_color: green
default_font_family: mono
default_font_size: 17
default_code_theme: nord
mac_code_block: false
show_line_number: true
cite: true
count: true
legend: title-alt
keep_title: true
---
`,
);
const fromExtend = resolveRenderOptions();
assert.equal(fromExtend.theme, "modern");
assert.equal(fromExtend.primaryColor, COLOR_PRESETS.green);
assert.equal(fromExtend.fontFamily, FONT_FAMILY_MAP.mono);
assert.equal(fromExtend.fontSize, "17px");
assert.equal(fromExtend.codeTheme, "nord");
assert.equal(fromExtend.isMacCodeBlock, false);
assert.equal(fromExtend.isShowLineNumber, true);
assert.equal(fromExtend.citeStatus, true);
assert.equal(fromExtend.countStatus, true);
assert.equal(fromExtend.legend, "title-alt");
assert.equal(fromExtend.keepTitle, true);
const explicit = resolveRenderOptions({
theme: "simple",
fontSize: "18px",
keepTitle: false,
});
assert.equal(explicit.theme, "simple");
assert.equal(explicit.fontSize, "18px");
assert.equal(explicit.keepTitle, false);
});
@@ -0,0 +1,71 @@
import assert from "node:assert/strict";
import test from "node:test";
import { DEFAULT_STYLE } from "./constants.ts";
import {
buildCss,
buildHtmlDocument,
modifyHtmlStructure,
normalizeCssText,
normalizeInlineCss,
removeFirstHeading,
} from "./html-builder.ts";
test("buildCss injects style variables and concatenates base and theme CSS", () => {
const css = buildCss("body { color: red; }", ".theme { color: blue; }");
assert.match(css, /--md-primary-color: #0F4C81;/);
assert.match(css, /body \{ color: red; \}/);
assert.match(css, /\.theme \{ color: blue; \}/);
});
test("buildHtmlDocument includes optional meta tags and code theme CSS", () => {
const html = buildHtmlDocument(
{
title: "Doc",
author: "Baoyu",
description: "Summary",
},
"body { color: red; }",
"<article>Hello</article>",
".hljs { color: blue; }",
);
assert.match(html, /<title>Doc<\/title>/);
assert.match(html, /meta name="author" content="Baoyu"/);
assert.match(html, /meta name="description" content="Summary"/);
assert.match(html, /<style>body \{ color: red; \}<\/style>/);
assert.match(html, /<style>\.hljs \{ color: blue; \}<\/style>/);
assert.match(html, /<article>Hello<\/article>/);
});
test("normalizeCssText and normalizeInlineCss replace variables and strip declarations", () => {
const rawCss = `
:root { --md-primary-color: #000; --md-font-size: 12px; --foreground: 0 0% 5%; }
.box { color: var(--md-primary-color); font-size: var(--md-font-size); background: hsl(var(--foreground)); }
`;
const normalizedCss = normalizeCssText(rawCss, DEFAULT_STYLE);
assert.match(normalizedCss, /color: #0F4C81/);
assert.match(normalizedCss, /font-size: 16px/);
assert.match(normalizedCss, /background: #3f3f3f/);
assert.doesNotMatch(normalizedCss, /--md-primary-color/);
const normalizedHtml = normalizeInlineCss(
`<style>${rawCss}</style><div style="color: var(--md-primary-color)"></div>`,
DEFAULT_STYLE,
);
assert.match(normalizedHtml, /color: #0F4C81/);
assert.doesNotMatch(normalizedHtml, /var\(--md-primary-color\)/);
});
test("HTML structure helpers hoist nested lists and remove the first heading", () => {
const nestedList = `<ul><li>Parent<ul><li>Child</li></ul></li></ul>`;
assert.equal(
modifyHtmlStructure(nestedList),
`<ul><li>Parent</li><ul><li>Child</li></ul></ul>`,
);
const html = `<h1>Title</h1><p>Intro</p><h2>Sub</h2>`;
assert.equal(removeFirstHeading(html), `<p>Intro</p><h2>Sub</h2>`);
});
@@ -0,0 +1,79 @@
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 {
getImageExtension,
replaceMarkdownImagesWithPlaceholders,
resolveContentImages,
resolveImagePath,
} from "./images.ts";
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("replaceMarkdownImagesWithPlaceholders rewrites markdown and tracks image metadata", () => {
const result = replaceMarkdownImagesWithPlaceholders(
`![cover](images/cover.png)\n\nText\n\n![diagram](images/diagram.webp)`,
"IMG_",
);
assert.equal(result.markdown, `IMG_1\n\nText\n\nIMG_2`);
assert.deepEqual(result.images, [
{ alt: "cover", originalPath: "images/cover.png", placeholder: "IMG_1" },
{ alt: "diagram", originalPath: "images/diagram.webp", placeholder: "IMG_2" },
]);
});
test("image extension and local fallback resolution handle common path variants", async (t) => {
assert.equal(getImageExtension("https://example.com/a.jpeg?x=1"), "jpeg");
assert.equal(getImageExtension("/tmp/figure"), "png");
const root = await makeTempDir("baoyu-md-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "figure.webp"), "webp");
const resolved = await resolveImagePath("figure.png", baseDir, tempDir, "test");
assert.equal(resolved, path.join(baseDir, "figure.webp"));
});
test("resolveContentImages resolves image placeholders against the content directory", async (t) => {
const root = await makeTempDir("baoyu-md-content-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "cover.png"), "png");
const resolved = await resolveContentImages(
[
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
},
],
baseDir,
tempDir,
"test",
);
assert.deepEqual(resolved, [
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
localPath: path.join(baseDir, "cover.png"),
},
]);
});
@@ -0,0 +1,64 @@
import assert from "node:assert/strict";
import test from "node:test";
import { initRenderer, renderMarkdown } from "./renderer.ts";
const render = (md: string) => {
const r = initRenderer();
return renderMarkdown(md, r).html;
};
test("bold with inline code (no underscore)", () => {
const html = render("**算出 `logits`,算出 `loss`。**");
assert.match(html, /<code[^>]*>logits<\/code>/);
assert.match(html, /<code[^>]*>loss<\/code>/);
});
test("bold with inline code (contains underscore)", () => {
const html = render("**变成 `input_ids`。**");
assert.match(html, /<code[^>]*>input_ids<\/code>/);
});
test("emphasis with inline code", () => {
const html = render("*查看 `hidden_states`*");
assert.match(html, /<code[^>]*>hidden_states<\/code>/);
});
test("plain inline code (regression)", () => {
const html = render("`lm_head`");
assert.match(html, /<code[^>]*>lm_head<\/code>/);
});
test("bold without code (regression)", () => {
const html = render("**纯粗体文本**");
assert.match(html, /<strong[^>]*>纯粗体文本<\/strong>/);
assert.doesNotMatch(html, /<code/);
});
test("bold with inline code containing backticks", () => {
const html = render("**``a`b``**");
assert.match(html, /<code[^>]*>a&#96;b<\/code>/);
});
test("emphasis with inline code containing backticks", () => {
const html = render("*``a`b``*");
assert.match(html, /<em[^>]*><code[^>]*>a&#96;b<\/code><\/em>/);
});
test("bold with inline code containing consecutive backticks", () => {
const html = render("**```a``b```**");
assert.match(html, /<code[^>]*>a&#96;&#96;b<\/code>/);
});
test("bold with inline code containing only backticks", () => {
const html = render("**```` `` ````**");
assert.match(html, /<code[^>]*>&#96;&#96;<\/code>/);
});
test("bold with inline code containing only spaces", () => {
const oneSpace = render("**`` ``**");
assert.match(oneSpace, /<code[^>]*> <\/code>/);
const twoSpaces = render("**`` ``**");
assert.match(twoSpaces, /<code[^>]*> <\/code>/);
});
@@ -109,6 +109,13 @@ function parseFrontMatterAndContent(markdownText: string): ParseResult {
}
}
function wrapInlineCode(value: string): string {
const runs = value.match(/`+/g);
const fence = "`".repeat(Math.max(...(runs?.map((run) => run.length) ?? [0])) + 1);
const padding = /^ *$/.test(value) ? "" : " ";
return `${fence}${padding}${value}${padding}${fence}`;
}
export function initRenderer(opts: IOpts = {}): RendererAPI {
const footnotes: [number, string, string][] = [];
let footnoteIndex = 0;
@@ -369,6 +376,7 @@ function preprocessCjkEmphasis(markdown: string): string {
const tree = processor.parse(markdown);
const extractText = (node: any): string => {
if (node.type === "text") return node.value;
if (node.type === "inlineCode") return wrapInlineCode(node.value);
if (node.children) return node.children.map(extractText).join("");
return "";
};
@@ -51,32 +51,42 @@ async function waitForElement(session: ChromeSession, selector: string, timeoutM
return false;
}
async function clickMenuByText(session: ChromeSession, text: string): Promise<void> {
async function clickMenuByText(session: ChromeSession, text: string, maxRetries = 5): Promise<void> {
console.log(`[wechat] Clicking "${text}" menu...`);
const posResult = await session.cdp.send<{ result: { value: string } }>('Runtime.evaluate', {
expression: `
(function() {
const items = document.querySelectorAll('.new-creation__menu .new-creation__menu-item');
for (const item of items) {
const title = item.querySelector('.new-creation__menu-title');
if (title && title.textContent?.trim() === '${text}') {
item.scrollIntoView({ block: 'center' });
const rect = item.getBoundingClientRect();
return JSON.stringify({ x: rect.x + rect.width / 2, y: rect.y + rect.height / 2 });
for (let attempt = 1; attempt <= maxRetries; attempt++) {
const posResult = await session.cdp.send<{ result: { value: string } }>('Runtime.evaluate', {
expression: `
(function() {
const items = document.querySelectorAll('.new-creation__menu .new-creation__menu-item');
for (const item of items) {
const title = item.querySelector('.new-creation__menu-title');
if (title && title.textContent?.trim() === '${text}') {
item.scrollIntoView({ block: 'center' });
const rect = item.getBoundingClientRect();
return JSON.stringify({ x: rect.x + rect.width / 2, y: rect.y + rect.height / 2 });
}
}
}
return 'null';
})()
`,
returnByValue: true,
}, { sessionId: session.sessionId });
return 'null';
})()
`,
returnByValue: true,
}, { sessionId: session.sessionId });
if (posResult.result.value === 'null') throw new Error(`Menu "${text}" not found`);
const pos = JSON.parse(posResult.result.value);
if (posResult.result.value !== 'null') {
const pos = JSON.parse(posResult.result.value);
await session.cdp.send('Input.dispatchMouseEvent', { type: 'mousePressed', x: pos.x, y: pos.y, button: 'left', clickCount: 1 }, { sessionId: session.sessionId });
await sleep(100);
await session.cdp.send('Input.dispatchMouseEvent', { type: 'mouseReleased', x: pos.x, y: pos.y, button: 'left', clickCount: 1 }, { sessionId: session.sessionId });
return;
}
await session.cdp.send('Input.dispatchMouseEvent', { type: 'mousePressed', x: pos.x, y: pos.y, button: 'left', clickCount: 1 }, { sessionId: session.sessionId });
await sleep(100);
await session.cdp.send('Input.dispatchMouseEvent', { type: 'mouseReleased', x: pos.x, y: pos.y, button: 'left', clickCount: 1 }, { sessionId: session.sessionId });
if (attempt < maxRetries) {
const delay = Math.min(1000 * attempt, 3000);
console.log(`[wechat] Menu "${text}" not found, retrying in ${delay}ms (${attempt}/${maxRetries})...`);
await sleep(delay);
}
}
throw new Error(`Menu "${text}" not found after ${maxRetries} attempts`);
}
async function copyImageToClipboard(imagePath: string): Promise<void> {
@@ -495,10 +505,10 @@ export async function postArticle(options: ArticleOptions): Promise<void> {
if (!loggedIn) throw new Error('Login timeout');
}
console.log('[wechat] Logged in.');
await sleep(2000);
await sleep(5000);
// Wait for menu to be ready
const menuReady = await waitForElement(session, '.new-creation__menu', 20_000);
const menuReady = await waitForElement(session, '.new-creation__menu', 40_000);
if (!menuReady) throw new Error('Home page menu did not load');
const targets = await cdp.send<{ targetInfos: Array<{ targetId: string; url: string; type: string }> }>('Target.getTargets');
@@ -517,16 +527,21 @@ export async function postArticle(options: ArticleOptions): Promise<void> {
await cdp.send('Runtime.enable', {}, { sessionId });
await cdp.send('DOM.enable', {}, { sessionId });
await sleep(3000);
// Wait for editor elements to fully load
console.log('[wechat] Waiting for editor to load...');
const editorLoaded = await waitForElement(session, '#title', 30_000);
if (!editorLoaded) throw new Error('Editor did not load (#title not found)');
await waitForElement(session, '.ProseMirror', 15_000);
await sleep(2000);
if (effectiveTitle) {
console.log('[wechat] Filling title...');
await evaluate(session, `document.querySelector('#title').value = ${JSON.stringify(effectiveTitle)}; document.querySelector('#title').dispatchEvent(new Event('input', { bubbles: true }));`);
await evaluate(session, `(function() { const el = document.querySelector('#title'); el.focus(); el.value = ${JSON.stringify(effectiveTitle)}; el.dispatchEvent(new Event('input', { bubbles: true })); el.dispatchEvent(new Event('change', { bubbles: true })); })()`);
}
if (effectiveAuthor) {
console.log('[wechat] Filling author...');
await evaluate(session, `document.querySelector('#author').value = ${JSON.stringify(effectiveAuthor)}; document.querySelector('#author').dispatchEvent(new Event('input', { bubbles: true }));`);
await evaluate(session, `(function() { const el = document.querySelector('#author'); el.focus(); el.value = ${JSON.stringify(effectiveAuthor)}; el.dispatchEvent(new Event('input', { bubbles: true })); el.dispatchEvent(new Event('change', { bubbles: true })); })()`);
}
await sleep(500);
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
for (const [key, value] of Object.entries(values)) {
previous.set(key, process.env[key]);
if (value == null) {
delete process.env[key];
} else {
process.env[key] = value;
}
}
t.after(() => {
for (const [key, value] of previous.entries()) {
if (value == null) {
delete process.env[key];
} else {
process.env[key] = value;
}
}
});
}
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}
@@ -0,0 +1,93 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
extractSummaryFromBody,
extractTitleFromMarkdown,
parseFrontmatter,
pickFirstString,
serializeFrontmatter,
stripWrappingQuotes,
toFrontmatterString,
} from "./content.ts";
test("parseFrontmatter extracts YAML fields and strips wrapping quotes", () => {
const input = `---
title: "Hello World"
author: Baoyu
summary: plain text
---
# Heading
Body`;
const result = parseFrontmatter(input);
assert.deepEqual(result.frontmatter, {
title: "Hello World",
author: "Baoyu",
summary: "plain text",
});
assert.match(result.body, /^# Heading/);
});
test("parseFrontmatter returns original content when no frontmatter exists", () => {
const input = "# No frontmatter";
assert.deepEqual(parseFrontmatter(input), {
frontmatter: {},
body: input,
});
});
test("serializeFrontmatter renders YAML only when fields exist", () => {
assert.equal(serializeFrontmatter({}), "");
assert.equal(
serializeFrontmatter({ title: "Hello", author: "Baoyu" }),
"---\ntitle: Hello\nauthor: Baoyu\n---\n",
);
});
test("quote and frontmatter string helpers normalize mixed scalar values", () => {
assert.equal(stripWrappingQuotes(`" quoted "`), "quoted");
assert.equal(stripWrappingQuotes("“ 中文标题 ”"), "中文标题");
assert.equal(stripWrappingQuotes("plain"), "plain");
assert.equal(toFrontmatterString("'hello'"), "hello");
assert.equal(toFrontmatterString(42), "42");
assert.equal(toFrontmatterString(false), "false");
assert.equal(toFrontmatterString({}), undefined);
assert.equal(
pickFirstString({ summary: 123, title: "" }, ["title", "summary"]),
"123",
);
});
test("markdown title and summary extraction skip non-body content and clean formatting", () => {
const markdown = `
![cover](cover.png)
## My Title
Body paragraph
`;
assert.equal(extractTitleFromMarkdown(markdown), "My Title");
const summary = extractSummaryFromBody(
`
# Heading
> quote
- list
1. ordered
\`\`\`
code
\`\`\`
This is **the first paragraph** with [a link](https://example.com) and \`inline code\` that should be summarized cleanly.
`,
70,
);
assert.equal(
summary,
"This is the first paragraph with a link and inline code that should...",
);
});
@@ -0,0 +1,140 @@
import assert from "node:assert/strict";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import { COLOR_PRESETS, FONT_FAMILY_MAP } from "./constants.ts";
import {
buildMarkdownDocumentMeta,
formatTimestamp,
resolveColorToken,
resolveFontFamilyToken,
resolveMarkdownStyle,
resolveRenderOptions,
} from "./document.ts";
function useCwd(t: TestContext, cwd: string): void {
const previous = process.cwd();
process.chdir(cwd);
t.after(() => {
process.chdir(previous);
});
}
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("document token resolvers map known presets and allow passthrough values", () => {
assert.equal(resolveColorToken("green"), COLOR_PRESETS.green);
assert.equal(resolveColorToken("#123456"), "#123456");
assert.equal(resolveColorToken(), undefined);
assert.equal(resolveFontFamilyToken("mono"), FONT_FAMILY_MAP.mono);
assert.equal(resolveFontFamilyToken("Custom Font"), "Custom Font");
assert.equal(resolveFontFamilyToken(), undefined);
});
test("formatTimestamp uses compact sortable datetime output", () => {
const date = new Date("2026-03-13T21:04:05.000Z");
const pad = (value: number) => String(value).padStart(2, "0");
const expected = `${date.getFullYear()}${pad(date.getMonth() + 1)}${pad(
date.getDate(),
)}${pad(date.getHours())}${pad(date.getMinutes())}${pad(date.getSeconds())}`;
assert.equal(formatTimestamp(date), expected);
});
test("buildMarkdownDocumentMeta prefers frontmatter and falls back to markdown title and summary", () => {
const metaFromYaml = buildMarkdownDocumentMeta(
"# Markdown Title\n\nBody summary paragraph that should be ignored.",
{
title: `" YAML Title "`,
author: "'Baoyu'",
summary: `" YAML Summary "`,
},
"fallback",
);
assert.deepEqual(metaFromYaml, {
title: "YAML Title",
author: "Baoyu",
description: "YAML Summary",
});
const metaFromMarkdown = buildMarkdownDocumentMeta(
`## “Markdown Title”\n\nThis is the first body paragraph that should become the summary because it is long enough.`,
{},
"fallback",
);
assert.equal(metaFromMarkdown.title, "Markdown Title");
assert.match(metaFromMarkdown.description ?? "", /^This is the first body paragraph/);
});
test("resolveMarkdownStyle merges theme defaults with explicit overrides", () => {
const style = resolveMarkdownStyle({
theme: "modern",
primaryColor: "#112233",
fontFamily: "Custom Sans",
});
assert.equal(style.primaryColor, "#112233");
assert.equal(style.fontFamily, "Custom Sans");
assert.equal(style.fontSize, "15px");
assert.equal(style.containerBg, "rgba(250, 249, 245, 1)");
});
test("resolveRenderOptions loads workspace EXTEND settings and lets explicit options win", async (t) => {
const root = await makeTempDir("baoyu-md-render-options-");
useCwd(t, root);
const extendPath = path.join(
root,
".baoyu-skills",
"baoyu-markdown-to-html",
"EXTEND.md",
);
await fs.mkdir(path.dirname(extendPath), { recursive: true });
await fs.writeFile(
extendPath,
`---
default_theme: modern
default_color: green
default_font_family: mono
default_font_size: 17
default_code_theme: nord
mac_code_block: false
show_line_number: true
cite: true
count: true
legend: title-alt
keep_title: true
---
`,
);
const fromExtend = resolveRenderOptions();
assert.equal(fromExtend.theme, "modern");
assert.equal(fromExtend.primaryColor, COLOR_PRESETS.green);
assert.equal(fromExtend.fontFamily, FONT_FAMILY_MAP.mono);
assert.equal(fromExtend.fontSize, "17px");
assert.equal(fromExtend.codeTheme, "nord");
assert.equal(fromExtend.isMacCodeBlock, false);
assert.equal(fromExtend.isShowLineNumber, true);
assert.equal(fromExtend.citeStatus, true);
assert.equal(fromExtend.countStatus, true);
assert.equal(fromExtend.legend, "title-alt");
assert.equal(fromExtend.keepTitle, true);
const explicit = resolveRenderOptions({
theme: "simple",
fontSize: "18px",
keepTitle: false,
});
assert.equal(explicit.theme, "simple");
assert.equal(explicit.fontSize, "18px");
assert.equal(explicit.keepTitle, false);
});
@@ -0,0 +1,71 @@
import assert from "node:assert/strict";
import test from "node:test";
import { DEFAULT_STYLE } from "./constants.ts";
import {
buildCss,
buildHtmlDocument,
modifyHtmlStructure,
normalizeCssText,
normalizeInlineCss,
removeFirstHeading,
} from "./html-builder.ts";
test("buildCss injects style variables and concatenates base and theme CSS", () => {
const css = buildCss("body { color: red; }", ".theme { color: blue; }");
assert.match(css, /--md-primary-color: #0F4C81;/);
assert.match(css, /body \{ color: red; \}/);
assert.match(css, /\.theme \{ color: blue; \}/);
});
test("buildHtmlDocument includes optional meta tags and code theme CSS", () => {
const html = buildHtmlDocument(
{
title: "Doc",
author: "Baoyu",
description: "Summary",
},
"body { color: red; }",
"<article>Hello</article>",
".hljs { color: blue; }",
);
assert.match(html, /<title>Doc<\/title>/);
assert.match(html, /meta name="author" content="Baoyu"/);
assert.match(html, /meta name="description" content="Summary"/);
assert.match(html, /<style>body \{ color: red; \}<\/style>/);
assert.match(html, /<style>\.hljs \{ color: blue; \}<\/style>/);
assert.match(html, /<article>Hello<\/article>/);
});
test("normalizeCssText and normalizeInlineCss replace variables and strip declarations", () => {
const rawCss = `
:root { --md-primary-color: #000; --md-font-size: 12px; --foreground: 0 0% 5%; }
.box { color: var(--md-primary-color); font-size: var(--md-font-size); background: hsl(var(--foreground)); }
`;
const normalizedCss = normalizeCssText(rawCss, DEFAULT_STYLE);
assert.match(normalizedCss, /color: #0F4C81/);
assert.match(normalizedCss, /font-size: 16px/);
assert.match(normalizedCss, /background: #3f3f3f/);
assert.doesNotMatch(normalizedCss, /--md-primary-color/);
const normalizedHtml = normalizeInlineCss(
`<style>${rawCss}</style><div style="color: var(--md-primary-color)"></div>`,
DEFAULT_STYLE,
);
assert.match(normalizedHtml, /color: #0F4C81/);
assert.doesNotMatch(normalizedHtml, /var\(--md-primary-color\)/);
});
test("HTML structure helpers hoist nested lists and remove the first heading", () => {
const nestedList = `<ul><li>Parent<ul><li>Child</li></ul></li></ul>`;
assert.equal(
modifyHtmlStructure(nestedList),
`<ul><li>Parent</li><ul><li>Child</li></ul></ul>`,
);
const html = `<h1>Title</h1><p>Intro</p><h2>Sub</h2>`;
assert.equal(removeFirstHeading(html), `<p>Intro</p><h2>Sub</h2>`);
});
@@ -0,0 +1,79 @@
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 {
getImageExtension,
replaceMarkdownImagesWithPlaceholders,
resolveContentImages,
resolveImagePath,
} from "./images.ts";
async function makeTempDir(prefix: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
test("replaceMarkdownImagesWithPlaceholders rewrites markdown and tracks image metadata", () => {
const result = replaceMarkdownImagesWithPlaceholders(
`![cover](images/cover.png)\n\nText\n\n![diagram](images/diagram.webp)`,
"IMG_",
);
assert.equal(result.markdown, `IMG_1\n\nText\n\nIMG_2`);
assert.deepEqual(result.images, [
{ alt: "cover", originalPath: "images/cover.png", placeholder: "IMG_1" },
{ alt: "diagram", originalPath: "images/diagram.webp", placeholder: "IMG_2" },
]);
});
test("image extension and local fallback resolution handle common path variants", async (t) => {
assert.equal(getImageExtension("https://example.com/a.jpeg?x=1"), "jpeg");
assert.equal(getImageExtension("/tmp/figure"), "png");
const root = await makeTempDir("baoyu-md-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "figure.webp"), "webp");
const resolved = await resolveImagePath("figure.png", baseDir, tempDir, "test");
assert.equal(resolved, path.join(baseDir, "figure.webp"));
});
test("resolveContentImages resolves image placeholders against the content directory", async (t) => {
const root = await makeTempDir("baoyu-md-content-images-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const baseDir = path.join(root, "article");
const tempDir = path.join(root, "tmp");
await fs.mkdir(baseDir, { recursive: true });
await fs.mkdir(tempDir, { recursive: true });
await fs.writeFile(path.join(baseDir, "cover.png"), "png");
const resolved = await resolveContentImages(
[
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
},
],
baseDir,
tempDir,
"test",
);
assert.deepEqual(resolved, [
{
alt: "cover",
originalPath: "cover.png",
placeholder: "IMG_1",
localPath: path.join(baseDir, "cover.png"),
},
]);
});
@@ -0,0 +1,64 @@
import assert from "node:assert/strict";
import test from "node:test";
import { initRenderer, renderMarkdown } from "./renderer.ts";
const render = (md: string) => {
const r = initRenderer();
return renderMarkdown(md, r).html;
};
test("bold with inline code (no underscore)", () => {
const html = render("**算出 `logits`,算出 `loss`。**");
assert.match(html, /<code[^>]*>logits<\/code>/);
assert.match(html, /<code[^>]*>loss<\/code>/);
});
test("bold with inline code (contains underscore)", () => {
const html = render("**变成 `input_ids`。**");
assert.match(html, /<code[^>]*>input_ids<\/code>/);
});
test("emphasis with inline code", () => {
const html = render("*查看 `hidden_states`*");
assert.match(html, /<code[^>]*>hidden_states<\/code>/);
});
test("plain inline code (regression)", () => {
const html = render("`lm_head`");
assert.match(html, /<code[^>]*>lm_head<\/code>/);
});
test("bold without code (regression)", () => {
const html = render("**纯粗体文本**");
assert.match(html, /<strong[^>]*>纯粗体文本<\/strong>/);
assert.doesNotMatch(html, /<code/);
});
test("bold with inline code containing backticks", () => {
const html = render("**``a`b``**");
assert.match(html, /<code[^>]*>a&#96;b<\/code>/);
});
test("emphasis with inline code containing backticks", () => {
const html = render("*``a`b``*");
assert.match(html, /<em[^>]*><code[^>]*>a&#96;b<\/code><\/em>/);
});
test("bold with inline code containing consecutive backticks", () => {
const html = render("**```a``b```**");
assert.match(html, /<code[^>]*>a&#96;&#96;b<\/code>/);
});
test("bold with inline code containing only backticks", () => {
const html = render("**```` `` ````**");
assert.match(html, /<code[^>]*>&#96;&#96;<\/code>/);
});
test("bold with inline code containing only spaces", () => {
const oneSpace = render("**`` ``**");
assert.match(oneSpace, /<code[^>]*> <\/code>/);
const twoSpaces = render("**`` ``**");
assert.match(twoSpaces, /<code[^>]*> <\/code>/);
});
@@ -109,6 +109,13 @@ function parseFrontMatterAndContent(markdownText: string): ParseResult {
}
}
function wrapInlineCode(value: string): string {
const runs = value.match(/`+/g);
const fence = "`".repeat(Math.max(...(runs?.map((run) => run.length) ?? [0])) + 1);
const padding = /^ *$/.test(value) ? "" : " ";
return `${fence}${padding}${value}${padding}${fence}`;
}
export function initRenderer(opts: IOpts = {}): RendererAPI {
const footnotes: [number, string, string][] = [];
let footnoteIndex = 0;
@@ -369,6 +376,7 @@ function preprocessCjkEmphasis(markdown: string): string {
const tree = processor.parse(markdown);
const extractText = (node: any): string => {
if (node.type === "text") return node.value;
if (node.type === "inlineCode") return wrapInlineCode(node.value);
if (node.children) return node.children.map(extractText).join("");
return "";
};
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}
+4 -3
View File
@@ -21,7 +21,8 @@ Scripts in `scripts/` subdirectory. `{baseDir}` = this SKILL.md's directory path
| Script | Purpose |
|--------|---------|
| `scripts/chunk.ts` | Split markdown into chunks by AST blocks (sections, headings, paragraphs), with line/word fallback for oversized blocks. Use `--output-dir <dir>` to write chunks into `<dir>/chunks/` instead of `<source-dir>/chunks/` |
| `scripts/main.ts` | CLI entry point. Default action splits markdown into chunks; also supports explicit `chunk` subcommand |
| `scripts/chunk.ts` | Markdown chunking implementation used by `main.ts` and kept compatible for direct invocation |
## Preferences (EXTEND.md)
@@ -183,8 +184,8 @@ Before translating chunks:
1. **Extract terminology**: Scan entire document for proper nouns, technical terms, recurring phrases
2. **Build session glossary**: Merge extracted terms with loaded glossaries, establish consistent translations
3. **Split into chunks**: Use `${BUN_X} {baseDir}/scripts/chunk.ts <file> [--max-words <chunk_max_words>] [--output-dir <output-dir>]`
- Parses markdown AST (headings, paragraphs, lists, code blocks, tables, etc.)
3. **Split into chunks**: Use `${BUN_X} {baseDir}/scripts/main.ts <file> [--max-words <chunk_max_words>] [--output-dir <output-dir>]`
- Parses markdown blocks (headings, paragraphs, lists, code blocks, tables, etc.)
- Splits at markdown block boundaries to preserve structure
- If a single block exceeds the threshold, falls back to line splitting, then word splitting
4. **Assemble translation prompt**:
+9 -144
View File
@@ -2,160 +2,25 @@
"lockfileVersion": 1,
"workspaces": {
"": {
"name": "baoyu-translate-chunk",
"dependencies": {
"remark-frontmatter": "^5.0.0",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"remark-stringify": "^11.0.0",
"unified": "^11.0.5",
"markdown-it": "14.1.1",
},
},
},
"packages": {
"@types/debug": ["@types/debug@4.1.12", "", { "dependencies": { "@types/ms": "*" } }, "sha512-vIChWdVG3LG1SMxEvI/AK+FWJthlrqlTu7fbrlywTkkaONwk/UAGaULXRlf8vkzFBLVm0zkMdCquhL5aOjhXPQ=="],
"argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
"@types/mdast": ["@types/mdast@4.0.4", "", { "dependencies": { "@types/unist": "*" } }, "sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA=="],
"entities": ["entities@4.5.0", "", {}, "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw=="],
"@types/ms": ["@types/ms@2.1.0", "", {}, "sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA=="],
"linkify-it": ["linkify-it@5.0.0", "", { "dependencies": { "uc.micro": "^2.0.0" } }, "sha512-5aHCbzQRADcdP+ATqnDuhhJ/MRIqDkZX5pyjFHRRysS8vZ5AbqGEoFIb6pYHPZ+L/OC2Lc+xT8uHVVR5CAK/wQ=="],
"@types/unist": ["@types/unist@3.0.3", "", {}, "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q=="],
"markdown-it": ["markdown-it@14.1.1", "", { "dependencies": { "argparse": "^2.0.1", "entities": "^4.4.0", "linkify-it": "^5.0.0", "mdurl": "^2.0.0", "punycode.js": "^2.3.1", "uc.micro": "^2.1.0" }, "bin": { "markdown-it": "bin/markdown-it.mjs" } }, "sha512-BuU2qnTti9YKgK5N+IeMubp14ZUKUUw7yeJbkjtosvHiP0AZ5c8IAgEMk79D0eC8F23r4Ac/q8cAIFdm2FtyoA=="],
"bail": ["bail@2.0.2", "", {}, "sha512-0xO6mYd7JB2YesxDKplafRpsiOzPt9V02ddPCLbY1xYGPOX24NTyN50qnUxgCPcSoYMhKpAuBTjQoRZCAkUDRw=="],
"mdurl": ["mdurl@2.0.0", "", {}, "sha512-Lf+9+2r+Tdp5wXDXC4PcIBjTDtq4UKjCPMQhKIuzpJNW0b96kVqSwW0bT7FhRSfmAiFYgP+SCRvdrDozfh0U5w=="],
"ccount": ["ccount@2.0.1", "", {}, "sha512-eyrF0jiFpY+3drT6383f1qhkbGsLSifNAjA61IUjZjmLCWjItY6LB9ft9YhoDgwfmclB2zhu51Lc7+95b8NRAg=="],
"punycode.js": ["punycode.js@2.3.1", "", {}, "sha512-uxFIHU0YlHYhDQtV4R9J6a52SLx28BCjT+4ieh7IGbgwVJWO+km431c4yRlREUAsAmt/uMjQUyQHNEPf0M39CA=="],
"character-entities": ["character-entities@2.0.2", "", {}, "sha512-shx7oQ0Awen/BRIdkjkvz54PnEEI/EjwXDSIZp86/KKdbafHh1Df/RYGBhn4hbe2+uKC9FnT5UCEdyPz3ai9hQ=="],
"debug": ["debug@4.4.3", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA=="],
"decode-named-character-reference": ["decode-named-character-reference@1.3.0", "", { "dependencies": { "character-entities": "^2.0.0" } }, "sha512-GtpQYB283KrPp6nRw50q3U9/VfOutZOe103qlN7BPP6Ad27xYnOIWv4lPzo8HCAL+mMZofJ9KEy30fq6MfaK6Q=="],
"dequal": ["dequal@2.0.3", "", {}, "sha512-0je+qPKHEMohvfRTCEo3CrPG6cAzAYgmzKyxRiYSSDkS6eGJdyVJm7WaYA5ECaAD9wLB2T4EEeymA5aFVcYXCA=="],
"devlop": ["devlop@1.1.0", "", { "dependencies": { "dequal": "^2.0.0" } }, "sha512-RWmIqhcFf1lRYBvNmr7qTNuyCt/7/ns2jbpp1+PalgE/rDQcBT0fioSMUpJ93irlUhC5hrg4cYqe6U+0ImW0rA=="],
"escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="],
"extend": ["extend@3.0.2", "", {}, "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g=="],
"fault": ["fault@2.0.1", "", { "dependencies": { "format": "^0.2.0" } }, "sha512-WtySTkS4OKev5JtpHXnib4Gxiurzh5NCGvWrFaZ34m6JehfTUhKZvn9njTfw48t6JumVQOmrKqpmGcdwxnhqBQ=="],
"format": ["format@0.2.2", "", {}, "sha512-wzsgA6WOq+09wrU1tsJ09udeR/YZRaeArL9e1wPbFg3GG2yDnC2ldKpxs4xunpFF9DgqCqOIra3bc1HWrJ37Ww=="],
"is-plain-obj": ["is-plain-obj@4.1.0", "", {}, "sha512-+Pgi+vMuUNkJyExiMBt5IlFoMyKnr5zhJ4Uspz58WOhBF5QoIZkFyNHIbBAtHwzVAgk5RtndVNsDRN61/mmDqg=="],
"longest-streak": ["longest-streak@3.1.0", "", {}, "sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g=="],
"markdown-table": ["markdown-table@3.0.4", "", {}, "sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw=="],
"mdast-util-find-and-replace": ["mdast-util-find-and-replace@3.0.2", "", { "dependencies": { "@types/mdast": "^4.0.0", "escape-string-regexp": "^5.0.0", "unist-util-is": "^6.0.0", "unist-util-visit-parents": "^6.0.0" } }, "sha512-Tmd1Vg/m3Xz43afeNxDIhWRtFZgM2VLyaf4vSTYwudTyeuTneoL3qtWMA5jeLyz/O1vDJmmV4QuScFCA2tBPwg=="],
"mdast-util-from-markdown": ["mdast-util-from-markdown@2.0.3", "", { "dependencies": { "@types/mdast": "^4.0.0", "@types/unist": "^3.0.0", "decode-named-character-reference": "^1.0.0", "devlop": "^1.0.0", "mdast-util-to-string": "^4.0.0", "micromark": "^4.0.0", "micromark-util-decode-numeric-character-reference": "^2.0.0", "micromark-util-decode-string": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0", "unist-util-stringify-position": "^4.0.0" } }, "sha512-W4mAWTvSlKvf8L6J+VN9yLSqQ9AOAAvHuoDAmPkz4dHf553m5gVj2ejadHJhoJmcmxEnOv6Pa8XJhpxE93kb8Q=="],
"mdast-util-frontmatter": ["mdast-util-frontmatter@2.0.1", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.0.0", "escape-string-regexp": "^5.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0", "micromark-extension-frontmatter": "^2.0.0" } }, "sha512-LRqI9+wdgC25P0URIJY9vwocIzCcksduHQ9OF2joxQoyTNVduwLAFUzjoopuRJbJAReaKrNQKAZKL3uCMugWJA=="],
"mdast-util-gfm": ["mdast-util-gfm@3.1.0", "", { "dependencies": { "mdast-util-from-markdown": "^2.0.0", "mdast-util-gfm-autolink-literal": "^2.0.0", "mdast-util-gfm-footnote": "^2.0.0", "mdast-util-gfm-strikethrough": "^2.0.0", "mdast-util-gfm-table": "^2.0.0", "mdast-util-gfm-task-list-item": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-0ulfdQOM3ysHhCJ1p06l0b0VKlhU0wuQs3thxZQagjcjPrlFRqY215uZGHHJan9GEAXd9MbfPjFJz+qMkVR6zQ=="],
"mdast-util-gfm-autolink-literal": ["mdast-util-gfm-autolink-literal@2.0.1", "", { "dependencies": { "@types/mdast": "^4.0.0", "ccount": "^2.0.0", "devlop": "^1.0.0", "mdast-util-find-and-replace": "^3.0.0", "micromark-util-character": "^2.0.0" } }, "sha512-5HVP2MKaP6L+G6YaxPNjuL0BPrq9orG3TsrZ9YXbA3vDw/ACI4MEsnoDpn6ZNm7GnZgtAcONJyPhOP8tNJQavQ=="],
"mdast-util-gfm-footnote": ["mdast-util-gfm-footnote@2.1.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.1.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0" } }, "sha512-sqpDWlsHn7Ac9GNZQMeUzPQSMzR6Wv0WKRNvQRg0KqHh02fpTz69Qc1QSseNX29bhz1ROIyNyxExfawVKTm1GQ=="],
"mdast-util-gfm-strikethrough": ["mdast-util-gfm-strikethrough@2.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-mKKb915TF+OC5ptj5bJ7WFRPdYtuHv0yTRxK2tJvi+BDqbkiG7h7u/9SI89nRAYcmap2xHQL9D+QG/6wSrTtXg=="],
"mdast-util-gfm-table": ["mdast-util-gfm-table@2.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.0.0", "markdown-table": "^3.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-78UEvebzz/rJIxLvE7ZtDd/vIQ0RHv+3Mh5DR96p7cS7HsBhYIICDBCu8csTNWNO6tBWfqXPWekRuj2FNOGOZg=="],
"mdast-util-gfm-task-list-item": ["mdast-util-gfm-task-list-item@2.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-IrtvNvjxC1o06taBAVJznEnkiHxLFTzgonUdy8hzFVeDun0uTjxxrRGVaNFqkU1wJR3RBPEfsxmU6jDWPofrTQ=="],
"mdast-util-phrasing": ["mdast-util-phrasing@4.1.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "unist-util-is": "^6.0.0" } }, "sha512-TqICwyvJJpBwvGAMZjj4J2n0X8QWp21b9l0o7eXyVJ25YNWYbJDVIyD1bZXE6WtV6RmKJVYmQAKWa0zWOABz2w=="],
"mdast-util-to-markdown": ["mdast-util-to-markdown@2.1.2", "", { "dependencies": { "@types/mdast": "^4.0.0", "@types/unist": "^3.0.0", "longest-streak": "^3.0.0", "mdast-util-phrasing": "^4.0.0", "mdast-util-to-string": "^4.0.0", "micromark-util-classify-character": "^2.0.0", "micromark-util-decode-string": "^2.0.0", "unist-util-visit": "^5.0.0", "zwitch": "^2.0.0" } }, "sha512-xj68wMTvGXVOKonmog6LwyJKrYXZPvlwabaryTjLh9LuvovB/KAH+kvi8Gjj+7rJjsFi23nkUxRQv1KqSroMqA=="],
"mdast-util-to-string": ["mdast-util-to-string@4.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0" } }, "sha512-0H44vDimn51F0YwvxSJSm0eCDOJTRlmN0R1yBh4HLj9wiV1Dn0QoXGbvFAWj2hSItVTlCmBF1hqKlIyUBVFLPg=="],
"micromark": ["micromark@4.0.2", "", { "dependencies": { "@types/debug": "^4.0.0", "debug": "^4.0.0", "decode-named-character-reference": "^1.0.0", "devlop": "^1.0.0", "micromark-core-commonmark": "^2.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-combine-extensions": "^2.0.0", "micromark-util-decode-numeric-character-reference": "^2.0.0", "micromark-util-encode": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-resolve-all": "^2.0.0", "micromark-util-sanitize-uri": "^2.0.0", "micromark-util-subtokenize": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-zpe98Q6kvavpCr1NPVSCMebCKfD7CA2NqZ+rykeNhONIJBpc1tFKt9hucLGwha3jNTNI8lHpctWJWoimVF4PfA=="],
"micromark-core-commonmark": ["micromark-core-commonmark@2.0.3", "", { "dependencies": { "decode-named-character-reference": "^1.0.0", "devlop": "^1.0.0", "micromark-factory-destination": "^2.0.0", "micromark-factory-label": "^2.0.0", "micromark-factory-space": "^2.0.0", "micromark-factory-title": "^2.0.0", "micromark-factory-whitespace": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-classify-character": "^2.0.0", "micromark-util-html-tag-name": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-resolve-all": "^2.0.0", "micromark-util-subtokenize": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-RDBrHEMSxVFLg6xvnXmb1Ayr2WzLAWjeSATAoxwKYJV94TeNavgoIdA0a9ytzDSVzBy2YKFK+emCPOEibLeCrg=="],
"micromark-extension-frontmatter": ["micromark-extension-frontmatter@2.0.0", "", { "dependencies": { "fault": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-C4AkuM3dA58cgZha7zVnuVxBhDsbttIMiytjgsM2XbHAB2faRVaHRle40558FBN+DJcrLNCoqG5mlrpdU4cRtg=="],
"micromark-extension-gfm": ["micromark-extension-gfm@3.0.0", "", { "dependencies": { "micromark-extension-gfm-autolink-literal": "^2.0.0", "micromark-extension-gfm-footnote": "^2.0.0", "micromark-extension-gfm-strikethrough": "^2.0.0", "micromark-extension-gfm-table": "^2.0.0", "micromark-extension-gfm-tagfilter": "^2.0.0", "micromark-extension-gfm-task-list-item": "^2.0.0", "micromark-util-combine-extensions": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-vsKArQsicm7t0z2GugkCKtZehqUm31oeGBV/KVSorWSy8ZlNAv7ytjFhvaryUiCUJYqs+NoE6AFhpQvBTM6Q4w=="],
"micromark-extension-gfm-autolink-literal": ["micromark-extension-gfm-autolink-literal@2.1.0", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-sanitize-uri": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-oOg7knzhicgQ3t4QCjCWgTmfNhvQbDDnJeVu9v81r7NltNCVmhPy1fJRX27pISafdjL+SVc4d3l48Gb6pbRypw=="],
"micromark-extension-gfm-footnote": ["micromark-extension-gfm-footnote@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-core-commonmark": "^2.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-sanitize-uri": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-/yPhxI1ntnDNsiHtzLKYnE3vf9JZ6cAisqVDauhp4CEHxlb4uoOTxOCJ+9s51bIB8U1N1FJ1RXOKTIlD5B/gqw=="],
"micromark-extension-gfm-strikethrough": ["micromark-extension-gfm-strikethrough@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-classify-character": "^2.0.0", "micromark-util-resolve-all": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-ADVjpOOkjz1hhkZLlBiYA9cR2Anf8F4HqZUO6e5eDcPQd0Txw5fxLzzxnEkSkfnD0wziSGiv7sYhk/ktvbf1uw=="],
"micromark-extension-gfm-table": ["micromark-extension-gfm-table@2.1.1", "", { "dependencies": { "devlop": "^1.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-t2OU/dXXioARrC6yWfJ4hqB7rct14e8f7m0cbI5hUmDyyIlwv5vEtooptH8INkbLzOatzKuVbQmAYcbWoyz6Dg=="],
"micromark-extension-gfm-tagfilter": ["micromark-extension-gfm-tagfilter@2.0.0", "", { "dependencies": { "micromark-util-types": "^2.0.0" } }, "sha512-xHlTOmuCSotIA8TW1mDIM6X2O1SiX5P9IuDtqGonFhEK0qgRI4yeC6vMxEV2dgyr2TiD+2PQ10o+cOhdVAcwfg=="],
"micromark-extension-gfm-task-list-item": ["micromark-extension-gfm-task-list-item@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-qIBZhqxqI6fjLDYFTBIa4eivDMnP+OZqsNwmQ3xNLE4Cxwc+zfQEfbs6tzAo2Hjq+bh6q5F+Z8/cksrLFYWQQw=="],
"micromark-factory-destination": ["micromark-factory-destination@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-Xe6rDdJlkmbFRExpTOmRj9N3MaWmbAgdpSrBQvCFqhezUn4AHqJHbaEnfbVYYiexVSs//tqOdY/DxhjdCiJnIA=="],
"micromark-factory-label": ["micromark-factory-label@2.0.1", "", { "dependencies": { "devlop": "^1.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-VFMekyQExqIW7xIChcXn4ok29YE3rnuyveW3wZQWWqF4Nv9Wk5rgJ99KzPvHjkmPXF93FXIbBp6YdW3t71/7Vg=="],
"micromark-factory-space": ["micromark-factory-space@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-zRkxjtBxxLd2Sc0d+fbnEunsTj46SWXgXciZmHq0kDYGnck/ZSGj9/wULTV95uoeYiK5hRXP2mJ98Uo4cq/LQg=="],
"micromark-factory-title": ["micromark-factory-title@2.0.1", "", { "dependencies": { "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-5bZ+3CjhAd9eChYTHsjy6TGxpOFSKgKKJPJxr293jTbfry2KDoWkhBb6TcPVB4NmzaPhMs1Frm9AZH7OD4Cjzw=="],
"micromark-factory-whitespace": ["micromark-factory-whitespace@2.0.1", "", { "dependencies": { "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-Ob0nuZ3PKt/n0hORHyvoD9uZhr+Za8sFoP+OnMcnWK5lngSzALgQYKMr9RJVOWLqQYuyn6ulqGWSXdwf6F80lQ=="],
"micromark-util-character": ["micromark-util-character@2.1.1", "", { "dependencies": { "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-wv8tdUTJ3thSFFFJKtpYKOYiGP2+v96Hvk4Tu8KpCAsTMs6yi+nVmGh1syvSCsaxz45J6Jbw+9DD6g97+NV67Q=="],
"micromark-util-chunked": ["micromark-util-chunked@2.0.1", "", { "dependencies": { "micromark-util-symbol": "^2.0.0" } }, "sha512-QUNFEOPELfmvv+4xiNg2sRYeS/P84pTW0TCgP5zc9FpXetHY0ab7SxKyAQCNCc1eK0459uoLI1y5oO5Vc1dbhA=="],
"micromark-util-classify-character": ["micromark-util-classify-character@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-K0kHzM6afW/MbeWYWLjoHQv1sgg2Q9EccHEDzSkxiP/EaagNzCm7T/WMKZ3rjMbvIpvBiZgwR3dKMygtA4mG1Q=="],
"micromark-util-combine-extensions": ["micromark-util-combine-extensions@2.0.1", "", { "dependencies": { "micromark-util-chunked": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-OnAnH8Ujmy59JcyZw8JSbK9cGpdVY44NKgSM7E9Eh7DiLS2E9RNQf0dONaGDzEG9yjEl5hcqeIsj4hfRkLH/Bg=="],
"micromark-util-decode-numeric-character-reference": ["micromark-util-decode-numeric-character-reference@2.0.2", "", { "dependencies": { "micromark-util-symbol": "^2.0.0" } }, "sha512-ccUbYk6CwVdkmCQMyr64dXz42EfHGkPQlBj5p7YVGzq8I7CtjXZJrubAYezf7Rp+bjPseiROqe7G6foFd+lEuw=="],
"micromark-util-decode-string": ["micromark-util-decode-string@2.0.1", "", { "dependencies": { "decode-named-character-reference": "^1.0.0", "micromark-util-character": "^2.0.0", "micromark-util-decode-numeric-character-reference": "^2.0.0", "micromark-util-symbol": "^2.0.0" } }, "sha512-nDV/77Fj6eH1ynwscYTOsbK7rR//Uj0bZXBwJZRfaLEJ1iGBR6kIfNmlNqaqJf649EP0F3NWNdeJi03elllNUQ=="],
"micromark-util-encode": ["micromark-util-encode@2.0.1", "", {}, "sha512-c3cVx2y4KqUnwopcO9b/SCdo2O67LwJJ/UyqGfbigahfegL9myoEFoDYZgkT7f36T0bLrM9hZTAaAyH+PCAXjw=="],
"micromark-util-html-tag-name": ["micromark-util-html-tag-name@2.0.1", "", {}, "sha512-2cNEiYDhCWKI+Gs9T0Tiysk136SnR13hhO8yW6BGNyhOC4qYFnwF1nKfD3HFAIXA5c45RrIG1ub11GiXeYd1xA=="],
"micromark-util-normalize-identifier": ["micromark-util-normalize-identifier@2.0.1", "", { "dependencies": { "micromark-util-symbol": "^2.0.0" } }, "sha512-sxPqmo70LyARJs0w2UclACPUUEqltCkJ6PhKdMIDuJ3gSf/Q+/GIe3WKl0Ijb/GyH9lOpUkRAO2wp0GVkLvS9Q=="],
"micromark-util-resolve-all": ["micromark-util-resolve-all@2.0.1", "", { "dependencies": { "micromark-util-types": "^2.0.0" } }, "sha512-VdQyxFWFT2/FGJgwQnJYbe1jjQoNTS4RjglmSjTUlpUMa95Htx9NHeYW4rGDJzbjvCsl9eLjMQwGeElsqmzcHg=="],
"micromark-util-sanitize-uri": ["micromark-util-sanitize-uri@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-encode": "^2.0.0", "micromark-util-symbol": "^2.0.0" } }, "sha512-9N9IomZ/YuGGZZmQec1MbgxtlgougxTodVwDzzEouPKo3qFWvymFHWcnDi2vzV1ff6kas9ucW+o3yzJK9YB1AQ=="],
"micromark-util-subtokenize": ["micromark-util-subtokenize@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-XQLu552iSctvnEcgXw6+Sx75GflAPNED1qx7eBJ+wydBb2KCbRZe+NwvIEEMM83uml1+2WSXpBAcp9IUCgCYWA=="],
"micromark-util-symbol": ["micromark-util-symbol@2.0.1", "", {}, "sha512-vs5t8Apaud9N28kgCrRUdEed4UJ+wWNvicHLPxCa9ENlYuAY31M0ETy5y1vA33YoNPDFTghEbnh6efaE8h4x0Q=="],
"micromark-util-types": ["micromark-util-types@2.0.2", "", {}, "sha512-Yw0ECSpJoViF1qTU4DC6NwtC4aWGt1EkzaQB8KPPyCRR8z9TWeV0HbEFGTO+ZY1wB22zmxnJqhPyTpOVCpeHTA=="],
"ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
"remark-frontmatter": ["remark-frontmatter@5.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-frontmatter": "^2.0.0", "micromark-extension-frontmatter": "^2.0.0", "unified": "^11.0.0" } }, "sha512-XTFYvNASMe5iPN0719nPrdItC9aU0ssC4v14mH1BCi1u0n1gAocqcujWUrByftZTbLhRtiKRyjYTSIOcr69UVQ=="],
"remark-gfm": ["remark-gfm@4.0.1", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-gfm": "^3.0.0", "micromark-extension-gfm": "^3.0.0", "remark-parse": "^11.0.0", "remark-stringify": "^11.0.0", "unified": "^11.0.0" } }, "sha512-1quofZ2RQ9EWdeN34S79+KExV1764+wCUGop5CPL1WGdD0ocPpu91lzPGbwWMECpEpd42kJGQwzRfyov9j4yNg=="],
"remark-parse": ["remark-parse@11.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-from-markdown": "^2.0.0", "micromark-util-types": "^2.0.0", "unified": "^11.0.0" } }, "sha512-FCxlKLNGknS5ba/1lmpYijMUzX2esxW5xQqjWxw2eHFfS2MSdaHVINFmhjo+qN1WhZhNimq0dZATN9pH0IDrpA=="],
"remark-stringify": ["remark-stringify@11.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-to-markdown": "^2.0.0", "unified": "^11.0.0" } }, "sha512-1OSmLd3awB/t8qdoEOMazZkNsfVTeY4fTsgzcQFdXNq8ToTN4ZGwrMnlda4K6smTFKD+GRV6O48i6Z4iKgPPpw=="],
"trough": ["trough@2.2.0", "", {}, "sha512-tmMpK00BjZiUyVyvrBK7knerNgmgvcV/KLVyuma/SC+TQN167GrMRciANTz09+k3zW8L8t60jWO1GpfkZdjTaw=="],
"unified": ["unified@11.0.5", "", { "dependencies": { "@types/unist": "^3.0.0", "bail": "^2.0.0", "devlop": "^1.0.0", "extend": "^3.0.0", "is-plain-obj": "^4.0.0", "trough": "^2.0.0", "vfile": "^6.0.0" } }, "sha512-xKvGhPWw3k84Qjh8bI3ZeJjqnyadK+GEFtazSfZv/rKeTkTjOJho6mFqh2SM96iIcZokxiOpg78GazTSg8+KHA=="],
"unist-util-is": ["unist-util-is@6.0.1", "", { "dependencies": { "@types/unist": "^3.0.0" } }, "sha512-LsiILbtBETkDz8I9p1dQ0uyRUWuaQzd/cuEeS1hoRSyW5E5XGmTzlwY1OrNzzakGowI9Dr/I8HVaw4hTtnxy8g=="],
"unist-util-stringify-position": ["unist-util-stringify-position@4.0.0", "", { "dependencies": { "@types/unist": "^3.0.0" } }, "sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ=="],
"unist-util-visit": ["unist-util-visit@5.1.0", "", { "dependencies": { "@types/unist": "^3.0.0", "unist-util-is": "^6.0.0", "unist-util-visit-parents": "^6.0.0" } }, "sha512-m+vIdyeCOpdr/QeQCu2EzxX/ohgS8KbnPDgFni4dQsfSCtpz8UqDyY5GjRru8PDKuYn7Fq19j1CQ+nJSsGKOzg=="],
"unist-util-visit-parents": ["unist-util-visit-parents@6.0.2", "", { "dependencies": { "@types/unist": "^3.0.0", "unist-util-is": "^6.0.0" } }, "sha512-goh1s1TBrqSqukSc8wrjwWhL0hiJxgA8m4kFxGlQ+8FYQ3C/m11FcTs4YYem7V664AhHVvgoQLk890Ssdsr2IQ=="],
"vfile": ["vfile@6.0.3", "", { "dependencies": { "@types/unist": "^3.0.0", "vfile-message": "^4.0.0" } }, "sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q=="],
"vfile-message": ["vfile-message@4.0.3", "", { "dependencies": { "@types/unist": "^3.0.0", "unist-util-stringify-position": "^4.0.0" } }, "sha512-QTHzsGd1EhbZs4AsQ20JX1rC3cOlt/IWJruk893DfLRr57lcnOeMaWG4K0JrRta4mIJZKth2Au3mM3u03/JWKw=="],
"zwitch": ["zwitch@2.0.4", "", {}, "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A=="],
"uc.micro": ["uc.micro@2.1.0", "", {}, "sha512-ARDJmphmdvUk6Glw7y9DQ2bFkKBHwQHLi2lsaH6PPmz/Ka9sFOBsBluozhDltWmnv9u/cF6Rt87znRTPV+yp/A=="],
}
}
+319 -121
View File
@@ -1,137 +1,335 @@
import { readFileSync, writeFileSync, mkdirSync } from "fs"
import { basename, dirname, join } from "path"
import { unified } from "unified"
import remarkParse from "remark-parse"
import remarkGfm from "remark-gfm"
import remarkFrontmatter from "remark-frontmatter"
import remarkStringify from "remark-stringify"
import type { Root, Content } from "mdast"
import { mkdirSync, readFileSync, writeFileSync } from "fs"
import { dirname, join } from "path"
import MarkdownIt from "markdown-it"
const args = process.argv.slice(2)
const file = args.find(a => !a.startsWith("--"))
const maxWords = parseInt(args[args.indexOf("--max-words") + 1] || "5000")
const outputDir = args.indexOf("--output-dir") !== -1 ? args[args.indexOf("--output-dir") + 1] : ""
type BlockKind =
| "heading"
| "thematicBreak"
| "html"
| "code"
| "flow"
if (!file) {
console.error("Usage: chunk.ts <file> [--max-words 5000]")
process.exit(1)
interface Block {
kind: BlockKind
md: string
words: number
}
const content = readFileSync(file, "utf-8")
interface Chunk {
blocks: Block[]
words: number
}
const tree = unified()
.use(remarkParse)
.use(remarkGfm)
.use(remarkFrontmatter, ["yaml"])
.parse(content)
export interface ChunkCliOptions {
file: string
maxWords: number
outputDir: string
}
const stringify = unified()
.use(remarkStringify, { bullet: "-", emphasis: "*", strong: "*" })
.use(remarkGfm)
.use(remarkFrontmatter, ["yaml"])
export interface ChunkResult {
source: string
chunks: number
output_dir: string
frontmatter: boolean
words_per_chunk: number[]
}
function nodeToMd(node: Content): string {
const root: Root = { type: "root", children: [node] }
return stringify.stringify(root).trim()
const parser = new MarkdownIt({ html: true })
export function formatChunkUsage(command: string): string {
return `Usage: ${command} <file> [--max-words 5000] [--output-dir <dir>]`
}
export function runChunkCli(args: string[], command = "chunk.ts"): number {
const parsed = parseChunkCliArgs(args)
if ("help" in parsed) {
console.log(formatChunkUsage(command))
return 0
}
if ("error" in parsed) {
console.error(parsed.error)
console.error(formatChunkUsage(command))
return 1
}
const result = chunkMarkdownFile(parsed.file, {
maxWords: parsed.maxWords,
outputDir: parsed.outputDir,
})
console.log(JSON.stringify(result))
return 0
}
export function chunkMarkdownFile(
file: string,
options: { maxWords?: number; outputDir?: string } = {}
): ChunkResult {
const maxWords = options.maxWords ?? 5000
const outputDir = options.outputDir ?? ""
const rawContent = normalizeNewlines(readFileSync(file, "utf-8"))
const { frontmatter, body } = extractFrontmatter(rawContent)
const chunks = buildChunks(parseMarkdown(body), maxWords)
const dir = outputDir ? join(outputDir, "chunks") : join(dirname(file), "chunks")
mkdirSync(dir, { recursive: true })
if (frontmatter) {
writeFileSync(join(dir, "frontmatter.md"), frontmatter)
}
chunks.forEach((chunk, index) => {
const num = String(index + 1).padStart(2, "0")
writeFileSync(join(dir, `chunk-${num}.md`), chunk.blocks.map(block => block.md).join("\n\n"))
})
return {
source: file,
chunks: chunks.length,
output_dir: dir,
frontmatter: Boolean(frontmatter),
words_per_chunk: chunks.map(chunk => chunk.words),
}
}
function parseChunkCliArgs(args: string[]):
| ChunkCliOptions
| { help: true }
| { error: string } {
let file = ""
let maxWords = 5000
let outputDir = ""
for (let index = 0; index < args.length; index += 1) {
const arg = args[index]
if (arg === "-h" || arg === "--help") {
return { help: true }
}
if (arg === "--max-words") {
const value = args[index + 1]
if (!value) return { error: "Missing value for --max-words" }
maxWords = parsePositiveInt(value, 0)
if (maxWords <= 0) return { error: `Invalid --max-words value: ${value}` }
index += 1
continue
}
if (arg === "--output-dir") {
const value = args[index + 1]
if (!value) return { error: "Missing value for --output-dir" }
outputDir = value
index += 1
continue
}
if (arg.startsWith("-")) {
return { error: `Unknown option: ${arg}` }
}
if (!file) {
file = arg
continue
}
return { error: `Unexpected positional argument: ${arg}` }
}
if (!file) {
return { error: "Missing input file" }
}
return { file, maxWords, outputDir }
}
function parsePositiveInt(value: string | undefined, fallback: number): number {
if (!value) return fallback
const parsed = Number.parseInt(value, 10)
return Number.isFinite(parsed) && parsed > 0 ? parsed : fallback
}
function normalizeNewlines(text: string): string {
return text.replace(/^\uFEFF/, "").replace(/\r\n?/g, "\n")
}
function trimBoundaryBlankLines(text: string): string {
return text.replace(/^\n+/, "").replace(/\n+$/, "")
}
function extractFrontmatter(content: string): { frontmatter: string; body: string } {
const lines = content.split("\n")
if (lines[0] !== "---") {
return { frontmatter: "", body: content }
}
for (let index = 1; index < lines.length; index += 1) {
if (lines[index] === "---" || lines[index] === "...") {
return {
frontmatter: lines.slice(0, index + 1).join("\n"),
body: lines.slice(index + 1).join("\n").replace(/^\n+/, ""),
}
}
}
return { frontmatter: "", body: content }
}
function parseMarkdown(content: string): Block[] {
if (!content.trim()) return []
const lines = content.split("\n")
const tokens = parser.parse(content, {})
const blocks: Block[] = []
for (const token of tokens) {
if (!token.map || token.level !== 0) continue
if (token.nesting !== 1 && token.nesting !== 0) continue
const [startLine, endLine] = token.map
const md = trimBoundaryBlankLines(lines.slice(startLine, endLine).join("\n"))
if (!md) continue
blocks.push(makeBlock(tokenTypeToBlockKind(token.type), md))
}
if (blocks.length === 0) {
const body = trimBoundaryBlankLines(content)
if (body) {
blocks.push(makeBlock("flow", body))
}
}
return blocks
}
function tokenTypeToBlockKind(tokenType: string): BlockKind {
if (tokenType === "heading_open") return "heading"
if (tokenType === "hr") return "thematicBreak"
if (tokenType === "html_block") return "html"
if (tokenType === "fence" || tokenType === "code_block") return "code"
return "flow"
}
function makeBlock(kind: BlockKind, md: string): Block {
return {
kind,
md: trimBoundaryBlankLines(md),
words: countWords(md),
}
}
function buildChunks(blocks: Block[], maxWordsPerChunk: number): Chunk[] {
const sections = splitIntoSections(blocks)
const normalizedBlocks: Block[] = []
for (const section of sections) {
const sectionWords = section.reduce((sum, block) => sum + block.words, 0)
if (sectionWords <= maxWordsPerChunk) {
normalizedBlocks.push(makeBlock("flow", section.map(block => block.md).join("\n\n")))
continue
}
for (const block of section) {
normalizedBlocks.push(...splitOversizedBlock(block, maxWordsPerChunk))
}
}
const chunks: Chunk[] = []
let currentBlocks: Block[] = []
let currentWords = 0
for (const block of normalizedBlocks) {
if (currentWords + block.words > maxWordsPerChunk && currentBlocks.length > 0) {
chunks.push({ blocks: currentBlocks, words: currentWords })
currentBlocks = [block]
currentWords = block.words
continue
}
currentBlocks.push(block)
currentWords += block.words
}
if (currentBlocks.length > 0) {
chunks.push({ blocks: currentBlocks, words: currentWords })
}
return chunks
}
function splitIntoSections(blocks: Block[]): Block[][] {
const sections: Block[][] = []
let current: Block[] = []
for (const block of blocks) {
if (block.kind === "heading" && current.length > 0) {
sections.push(current)
current = [block]
continue
}
current.push(block)
}
if (current.length > 0) {
sections.push(current)
}
return sections
}
function splitOversizedBlock(block: Block, maxWordsPerChunk: number): Block[] {
if (block.words <= maxWordsPerChunk) return [block]
if (
block.kind === "heading"
|| block.kind === "thematicBreak"
|| block.kind === "html"
|| block.kind === "code"
) {
return [block]
}
const lines = block.md.split("\n")
if (lines.length <= 1) {
return [block]
}
const splitBlocks: Block[] = []
let buffer: string[] = []
let bufferWords = 0
for (const line of lines) {
const lineWords = countWords(line)
if (bufferWords + lineWords > maxWordsPerChunk && buffer.length > 0) {
splitBlocks.push(makeBlock(block.kind, buffer.join("\n")))
buffer = [line]
bufferWords = lineWords
continue
}
buffer.push(line)
bufferWords += lineWords
}
if (buffer.length > 0) {
splitBlocks.push(makeBlock(block.kind, buffer.join("\n")))
}
return splitBlocks
}
function countWords(text: string): number {
const cleaned = text.replace(/[#*`\[\]()>|_~-]/g, " ")
const cjk = cleaned.match(/[\u4e00-\u9fff\u3400-\u4dbf\uf900-\ufaff]/g)
const latin = cleaned.match(/[a-zA-Z0-9]+/g)
return (cjk?.length || 0) + (latin?.length || 0)
return (cjk?.length ?? 0) + (latin?.length ?? 0)
}
interface Block {
md: string
words: number
if (import.meta.main) {
process.exit(runChunkCli(process.argv.slice(2), process.argv[1] ?? "chunk.ts"))
}
function splitNodeToBlocks(node: Content): Block[] {
const md = nodeToMd(node)
const words = countWords(md)
if (words <= maxWords) return [{ md, words }]
if (node.type === "heading" || node.type === "thematicBreak" || node.type === "html") {
return [{ md, words }]
}
if ("children" in node && Array.isArray(node.children)) {
const blocks: Block[] = []
for (const child of node.children as Content[]) {
blocks.push(...splitNodeToBlocks(child))
}
return blocks
}
const lines = md.split("\n")
if (lines.length > 1) {
const blocks: Block[] = []
let buf: string[] = []
let bufWords = 0
for (const line of lines) {
const lw = countWords(line)
if (bufWords + lw > maxWords && buf.length > 0) {
blocks.push({ md: buf.join("\n"), words: bufWords })
buf = [line]
bufWords = lw
} else {
buf.push(line)
bufWords += lw
}
}
if (buf.length > 0) blocks.push({ md: buf.join("\n"), words: bufWords })
return blocks
}
return [{ md, words }]
}
let frontmatter = ""
const blocks: Block[] = []
for (const node of tree.children) {
if (node.type === "yaml") {
frontmatter = `---\n${node.value}\n---`
continue
}
blocks.push(...splitNodeToBlocks(node as Content))
}
const chunks: { blocks: Block[]; words: number }[] = []
let cur: Block[] = []
let curWords = 0
for (const b of blocks) {
if (curWords + b.words > maxWords && cur.length > 0) {
chunks.push({ blocks: cur, words: curWords })
cur = [b]
curWords = b.words
} else {
cur.push(b)
curWords += b.words
}
}
if (cur.length > 0) chunks.push({ blocks: cur, words: curWords })
const dir = outputDir ? join(outputDir, "chunks") : join(dirname(file), "chunks")
mkdirSync(dir, { recursive: true })
if (frontmatter) {
writeFileSync(join(dir, "frontmatter.md"), frontmatter)
}
chunks.forEach((chunk, i) => {
const num = String(i + 1).padStart(2, "0")
const out = join(dir, `chunk-${num}.md`)
writeFileSync(out, chunk.blocks.map(b => b.md).join("\n\n"))
})
console.log(JSON.stringify({
source: file,
chunks: chunks.length,
output_dir: dir,
frontmatter: !!frontmatter,
words_per_chunk: chunks.map(c => c.words)
}))
+55
View File
@@ -0,0 +1,55 @@
#!/usr/bin/env bun
import path from "node:path"
import process from "node:process"
import { runChunkCli } from "./chunk.js"
function formatScriptCommand(fallback: string): string {
const raw = process.argv[1]
const displayPath = raw
? (() => {
const relative = path.relative(process.cwd(), raw)
return relative && !relative.startsWith("..") ? relative : raw
})()
: fallback
const quotedPath = displayPath.includes(" ")
? `"${displayPath.replace(/"/g, '\\"')}"`
: displayPath
return `npx -y bun ${quotedPath}`
}
function printUsage(exitCode: number): never {
const cmd = formatScriptCommand("scripts/main.ts")
console.log(`Baoyu Translate CLI
Usage:
${cmd} <file> [--max-words 5000] [--output-dir <dir>]
${cmd} chunk <file> [--max-words 5000] [--output-dir <dir>]
Commands:
chunk Split markdown into chunks
Options:
--max-words <n> Maximum words per chunk (default: 5000)
--output-dir <dir> Write chunks into <dir>/chunks/
-h, --help Show help
`)
process.exit(exitCode)
}
const args = process.argv.slice(2)
if (args.length === 0) {
printUsage(1)
}
if (args[0] === "-h" || args[0] === "--help") {
printUsage(0)
}
if (args[0] === "chunk") {
process.exit(runChunkCli(args.slice(1), `${formatScriptCommand("scripts/main.ts")} chunk`))
}
process.exit(runChunkCli(args, formatScriptCommand("scripts/main.ts")))
+4 -6
View File
@@ -1,9 +1,7 @@
{
"name": "baoyu-translate-chunk",
"private": true,
"dependencies": {
"remark-frontmatter": "^5.0.0",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"remark-stringify": "^11.0.0",
"unified": "^11.0.5"
"markdown-it": "14.1.1"
}
}
}
@@ -0,0 +1,307 @@
import assert from "node:assert/strict";
import { spawn, type ChildProcess } from "node:child_process";
import fs from "node:fs/promises";
import http from "node:http";
import os from "node:os";
import path from "node:path";
import process from "node:process";
import test, { type TestContext } from "node:test";
import {
discoverRunningChromeDebugPort,
findChromeExecutable,
findExistingChromeDebugPort,
getFreePort,
openPageSession,
resolveSharedChromeProfileDir,
waitForChromeDebugPort,
} from "./index.ts";
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
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: string): Promise<string> {
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
}
async function startDebugServer(port: number): Promise<http.Server> {
const server = http.createServer((req, res) => {
if (req.url === "/json/version") {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({
webSocketDebuggerUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
}));
return;
}
res.writeHead(404);
res.end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(port, "127.0.0.1", () => resolve());
});
return server;
}
async function closeServer(server: http.Server): Promise<void> {
await new Promise<void>((resolve, reject) => {
server.close((error) => {
if (error) reject(error);
else resolve();
});
});
}
function shellPathForPlatform(): string | null {
if (process.platform === "win32") return null;
return "/bin/bash";
}
async function startFakeChromiumProcess(port: number): Promise<ChildProcess | null> {
const shell = shellPathForPlatform();
if (!shell) return null;
const child = spawn(
shell,
[
"-lc",
`exec -a chromium-mock ${JSON.stringify(process.execPath)} -e 'setInterval(() => {}, 1000)' -- --remote-debugging-port=${port}`,
],
{ stdio: "ignore" },
);
await new Promise((resolve) => setTimeout(resolve, 250));
return child;
}
async function stopProcess(child: ChildProcess | null): Promise<void> {
if (!child) return;
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 100));
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
if (child.exitCode !== null || child.signalCode !== null) return;
await new Promise((resolve) => child.once("exit", resolve));
}
test("getFreePort honors a fixed environment override and otherwise allocates a TCP port", async (t) => {
useEnv(t, { TEST_FIXED_PORT: "45678" });
assert.equal(await getFreePort("TEST_FIXED_PORT"), 45678);
const dynamicPort = await getFreePort();
assert.ok(Number.isInteger(dynamicPort));
assert.ok(dynamicPort > 0);
});
test("findChromeExecutable prefers env overrides and falls back to candidate paths", async (t) => {
const root = await makeTempDir("baoyu-chrome-bin-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const envChrome = path.join(root, "env-chrome");
const fallbackChrome = path.join(root, "fallback-chrome");
await fs.writeFile(envChrome, "");
await fs.writeFile(fallbackChrome, "");
useEnv(t, { BAOYU_CHROME_PATH: envChrome });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
envChrome,
);
useEnv(t, { BAOYU_CHROME_PATH: null });
assert.equal(
findChromeExecutable({
envNames: ["BAOYU_CHROME_PATH"],
candidates: { default: [fallbackChrome] },
}),
fallbackChrome,
);
});
test("resolveSharedChromeProfileDir supports env overrides, WSL paths, and default suffixes", (t) => {
useEnv(t, { BAOYU_SHARED_PROFILE: "/tmp/custom-profile" });
assert.equal(
resolveSharedChromeProfileDir({
envNames: ["BAOYU_SHARED_PROFILE"],
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.resolve("/tmp/custom-profile"),
);
useEnv(t, { BAOYU_SHARED_PROFILE: null });
assert.equal(
resolveSharedChromeProfileDir({
wslWindowsHome: "/mnt/c/Users/demo",
appDataDirName: "demo-app",
profileDirName: "demo-profile",
}),
path.join("/mnt/c/Users/demo", ".local", "share", "demo-app", "demo-profile"),
);
const fallback = resolveSharedChromeProfileDir({
appDataDirName: "demo-app",
profileDirName: "demo-profile",
});
assert.match(fallback, /demo-app[\\/]demo-profile$/);
});
test("findExistingChromeDebugPort reads DevToolsActivePort and validates it against a live endpoint", async (t) => {
const root = await makeTempDir("baoyu-cdp-profile-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await findExistingChromeDebugPort({ profileDir: root, timeoutMs: 1000 });
assert.equal(found, port);
});
test("discoverRunningChromeDebugPort reads DevToolsActivePort from the provided user-data dir", async (t) => {
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
await fs.writeFile(path.join(root, "DevToolsActivePort"), `${port}\n/devtools/browser/demo\n`);
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.deepEqual(found, {
port,
wsUrl: `ws://127.0.0.1:${port}/devtools/browser/demo`,
});
});
test("discoverRunningChromeDebugPort ignores unrelated debugging processes", async (t) => {
if (process.platform === "win32") {
t.skip("Process discovery fallback is not used on Windows.");
return;
}
const root = await makeTempDir("baoyu-cdp-user-data-");
t.after(() => fs.rm(root, { recursive: true, force: true }));
const port = await getFreePort();
const server = await startDebugServer(port);
t.after(() => closeServer(server));
const fakeChromium = await startFakeChromiumProcess(port);
t.after(async () => { await stopProcess(fakeChromium); });
const found = await discoverRunningChromeDebugPort({
userDataDirs: [root],
timeoutMs: 1000,
});
assert.equal(found, null);
});
test("openPageSession reports whether it created a new target", async () => {
const calls: string[] = [];
const cdpExisting = {
send: async <T>(method: string): Promise<T> => {
calls.push(method);
if (method === "Target.getTargets") {
return {
targetInfos: [{ targetId: "existing-target", type: "page", url: "https://gemini.google.com/app" }],
} as T;
}
if (method === "Target.attachToTarget") return { sessionId: "session-existing" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const existing = await openPageSession({
cdp: cdpExisting as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(existing, {
sessionId: "session-existing",
targetId: "existing-target",
createdTarget: false,
});
assert.deepEqual(calls, ["Target.getTargets", "Target.attachToTarget"]);
const createCalls: string[] = [];
const cdpCreated = {
send: async <T>(method: string): Promise<T> => {
createCalls.push(method);
if (method === "Target.getTargets") return { targetInfos: [] } as T;
if (method === "Target.createTarget") return { targetId: "created-target" } as T;
if (method === "Target.attachToTarget") return { sessionId: "session-created" } as T;
throw new Error(`Unexpected method: ${method}`);
},
};
const created = await openPageSession({
cdp: cdpCreated as never,
reusing: false,
url: "https://gemini.google.com/app",
matchTarget: (target) => target.url.includes("gemini.google.com"),
activateTarget: false,
});
assert.deepEqual(created, {
sessionId: "session-created",
targetId: "created-target",
createdTarget: true,
});
assert.deepEqual(createCalls, ["Target.getTargets", "Target.createTarget", "Target.attachToTarget"]);
});
test("waitForChromeDebugPort retries until the debug endpoint becomes available", async (t) => {
const port = await getFreePort();
const serverPromise = (async () => {
await new Promise((resolve) => setTimeout(resolve, 200));
const server = await startDebugServer(port);
t.after(() => closeServer(server));
})();
const websocketUrl = await waitForChromeDebugPort(port, 4000, {
includeLastError: true,
});
await serverPromise;
assert.equal(websocketUrl, `ws://127.0.0.1:${port}/devtools/browser/demo`);
});
@@ -43,6 +43,19 @@ type FindExistingChromeDebugPortOptions = {
timeoutMs?: number;
};
export type ChromeChannel = "stable" | "beta" | "canary" | "dev";
export type DiscoveredChrome = {
port: number;
wsUrl: string;
};
type DiscoverRunningChromeOptions = {
channels?: ChromeChannel[];
userDataDirs?: string[];
timeoutMs?: number;
};
type LaunchChromeOptions = {
chromePath: string;
profileDir: string;
@@ -73,6 +86,7 @@ type OpenPageSessionOptions = {
export type PageSession = {
sessionId: string;
targetId: string;
createdTarget: boolean;
};
export function sleep(ms: number): Promise<void> {
@@ -173,16 +187,32 @@ async function isDebugPortReady(port: number, timeoutMs = 3_000): Promise<boolea
}
}
function isPortListening(port: number, timeoutMs = 3_000): Promise<boolean> {
return new Promise((resolve) => {
const socket = new net.Socket();
const timer = setTimeout(() => { socket.destroy(); resolve(false); }, timeoutMs);
socket.once("connect", () => { clearTimeout(timer); socket.destroy(); resolve(true); });
socket.once("error", () => { clearTimeout(timer); resolve(false); });
socket.connect(port, "127.0.0.1");
});
}
function parseDevToolsActivePort(filePath: string): { port: number; wsPath: string } | null {
try {
const content = fs.readFileSync(filePath, "utf-8");
const lines = content.split(/\r?\n/);
const port = Number.parseInt(lines[0]?.trim() ?? "", 10);
const wsPath = lines[1]?.trim();
if (port > 0 && wsPath) return { port, wsPath };
} catch {}
return null;
}
export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {
const timeoutMs = options.timeoutMs ?? 3_000;
const portFile = path.join(options.profileDir, "DevToolsActivePort");
const parsed = parseDevToolsActivePort(path.join(options.profileDir, "DevToolsActivePort"));
try {
const content = fs.readFileSync(portFile, "utf-8");
const [portLine] = content.split(/\r?\n/);
const port = Number.parseInt(portLine?.trim() ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) return port;
} catch {}
if (parsed && parsed.port > 0 && await isDebugPortReady(parsed.port, timeoutMs)) return parsed.port;
if (process.platform === "win32") return null;
@@ -204,6 +234,85 @@ export async function findExistingChromeDebugPort(options: FindExistingChromeDeb
return null;
}
export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {
const home = os.homedir();
const dirs: string[] = [];
const channelDirs: Record<string, { darwin: string; linux: string; win32: string }> = {
stable: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome"),
linux: path.join(home, ".config", "google-chrome"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome", "User Data"),
},
beta: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Beta"),
linux: path.join(home, ".config", "google-chrome-beta"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Beta", "User Data"),
},
canary: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Canary"),
linux: path.join(home, ".config", "google-chrome-canary"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome SxS", "User Data"),
},
dev: {
darwin: path.join(home, "Library", "Application Support", "Google", "Chrome Dev"),
linux: path.join(home, ".config", "google-chrome-dev"),
win32: path.join(process.env.LOCALAPPDATA ?? path.join(home, "AppData", "Local"), "Google", "Chrome Dev", "User Data"),
},
};
const platform = process.platform === "darwin" ? "darwin" : process.platform === "win32" ? "win32" : "linux";
for (const ch of channels) {
const entry = channelDirs[ch];
if (entry) dirs.push(entry[platform]);
}
return dirs;
}
export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChrome | null> {
const channels = options.channels ?? ["stable", "beta", "canary", "dev"];
const timeoutMs = options.timeoutMs ?? 3_000;
const userDataDirs = (options.userDataDirs ?? getDefaultChromeUserDataDirs(channels))
.map((dir) => path.resolve(dir));
for (const dir of userDataDirs) {
const parsed = parseDevToolsActivePort(path.join(dir, "DevToolsActivePort"));
if (!parsed) continue;
if (await isPortListening(parsed.port, timeoutMs)) {
return { port: parsed.port, wsUrl: `ws://127.0.0.1:${parsed.port}${parsed.wsPath}` };
}
}
if (process.platform !== "win32") {
try {
const result = spawnSync("ps", ["aux"], { encoding: "utf-8", timeout: 5_000 });
if (result.status === 0 && result.stdout) {
const lines = result.stdout
.split("\n")
.filter((line) =>
line.includes("--remote-debugging-port=") &&
userDataDirs.some((dir) => line.includes(dir))
);
for (const line of lines) {
const portMatch = line.match(/--remote-debugging-port=(\d+)/);
const port = Number.parseInt(portMatch?.[1] ?? "", 10);
if (port > 0 && await isDebugPortReady(port, timeoutMs)) {
try {
const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`http://127.0.0.1:${port}/json/version`, { timeoutMs });
if (version.webSocketDebuggerUrl) return { port, wsUrl: version.webSocketDebuggerUrl };
} catch {}
}
}
}
} catch {}
}
return null;
}
export async function waitForChromeDebugPort(
port: number,
timeoutMs: number,
@@ -376,10 +485,12 @@ export function killChrome(chrome: ChildProcess): void {
export async function openPageSession(options: OpenPageSessionOptions): Promise<PageSession> {
let targetId: string;
let createdTarget = false;
if (options.reusing) {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
} else {
const targets = await options.cdp.send<{ targetInfos: ChromeTargetInfo[] }>("Target.getTargets");
const existing = targets.targetInfos.find(options.matchTarget);
@@ -388,6 +499,7 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
} else {
const created = await options.cdp.send<{ targetId: string }>("Target.createTarget", { url: options.url });
targetId = created.targetId;
createdTarget = true;
}
}
@@ -404,5 +516,5 @@ export async function openPageSession(options: OpenPageSessionOptions): Promise<
if (options.enableDom) await options.cdp.send("DOM.enable", {}, { sessionId });
if (options.enableNetwork) await options.cdp.send("Network.enable", {}, { sessionId });
return { sessionId, targetId };
return { sessionId, targetId, createdTarget };
}