- 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>
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>
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>
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>
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>
- 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>
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>
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>
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.
- Add short text (<5 sentences) annotation reduction rule to translator's notes
- Explicitly pass resolved style preset to 02-prompt.md assembly in all modes
- Fix Provider Selection: default to Replicate when multiple keys available (matches code)
- Add Replicate column to Quality Presets table (normal→1K, 2k→2K)
- Add Replicate aspect ratio behavior (match_input_image when --ref without --ar)
- Remove stale Google Imagen reference from Aspect Ratios
- Add batch file format example with JSON schema to SKILL.md
- Note that batch paths resolve relative to batch file directory
- Move batch execution strategy in article-illustrator before numbered steps
- Fix translate image-language reminder to use standard markdown syntax
with note to match article's own image syntax convention
Add screen-print as 7th rendering style with halftone textures and limited
colors. Add duotone as 10th color palette for dramatic two-color compositions.
Update all compatibility matrices and style presets (poster-art, mondo,
art-deco, propaganda, cinematic).
Add screen-print as new style option with poster aesthetic (bold silhouettes,
halftone textures, limited colors). Add --preset flag for quick type + style
selection (e.g., --preset tech-explainer, --preset opinion-piece).
Support glossary_files in EXTEND.md for loading glossaries from external
markdown tables or YAML files. Add frontmatter transformation rules to
rename source metadata fields with source prefix during translation.
Enable bottom citations by default for markdown articles. Add --no-cite
flag to all posting scripts (wechat-api, wechat-article, md-to-wechat)
to optionally disable. WeChat mp links stay inline.
Add optional --cite flag to convert ordinary external links to numbered
bottom citations. WeChat links stay inline. Also translate theme and
color descriptions from Chinese to English for consistency.
- Save rendered HTML as sibling -captured.html file alongside markdown
- Defuddle-first conversion with automatic fallback to legacy Readability/selector extractor
- Add rawHtml, conversionMethod, fallbackReason to ConversionResult
- Log converter method and fallback reason in CLI output
- Add --video flag for video uploads (max 18 files total)
- Switch from clipboard paste to DOM.setFileInputFiles for uploads
- Add Chrome health check with auto-restart for unresponsive instances
- Add navigation check to ensure Weibo home page before posting
Add 5 new style presets (academic, business, humorous, conversational,
elegant) to existing options. Wire --style CLI flag, update subagent
prompt template with style section, and document in both READMEs.
- chunk.ts: add --output-dir option so chunks write to output directory instead of source directory
- Refined workflow: split Review into Critical Review + Revision (5→6 steps)
- Add Europeanized language diagnosis for CJK targets
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add automatic check after article images are inserted: verifies remaining
XIMGPH placeholders and expected vs actual image count. Increase CDP timeout
to 60s and add 3s DOM stabilization delay between image insertions.
- Add --download-media flag to download images/videos to local dirs and rewrite markdown links
- Extract coverImage from page meta (og:image) into YAML front matter
- Handle data-src lazy loading for WeChat and similar sites
- Add EXTEND.md preferences with first-time setup for download_media setting
- Add media-localizer module adapted from x-to-markdown
In WSL2, auto-resolve Windows USERPROFILE via cmd.exe/wslpath
so Chrome profile is stored on Windows-native filesystem.
Fixes login state persistence when using Windows Chrome from WSL.
Replace free-form dimension calculation with closest-match from predefined
standard sizes to avoid invalid resolution errors from the API.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add OPENAI_IMAGE_USE_CHAT env var (true|false) to route image generation
through /chat/completions instead of /images/generations. Extracts base64
image data URLs from the chat response, enabling compatibility with
OpenAI-compatible providers that return images via chat API.
- Render embedded tweets in articles as blockquotes with author info and text summary
- Reuse existing markdown when --download-media targets already-converted URLs
- Upgrade Twitter image downloads to 4096x4096 resolution
- Improve entity resolution with logical key lookup
- Support trailing media for all block types (headings, lists, blockquotes)
- Change output path to {username}/{tweet-id}/{content-slug}.md for stable paths
- Add gemini-3.1-flash-image-preview to supported Google multimodal models
- Improve preferences loading with blocking first-time setup flow
- Add first-time-setup.md reference for guided configuration
- Update model references in SKILL.md and preferences schema
- Update x-goog-ext-525001261-jspb header format to match upstream
HanaokaYuzu/Gemini-API (commit 42900f7, 2026-02-03), appending
`,null,null,1` to fix image generation failures
- Replace deprecated gemini-2.5-pro and gemini-2.5-flash with
gemini-3.0-flash and gemini-3.0-flash-thinking
- Add gemini-3.1-pro-preview (empty header, server auto-routed)
- Update SKILL.md and CLI help text to reflect new model options
Closes#50
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bun's fetch implementation has a known issue where long-lived connections
through HTTP proxies (e.g., Clash, V2Ray) get their sockets closed
unexpectedly, causing Google image generation requests to fail with
"The socket connection was closed unexpectedly".
This change adds automatic proxy detection and falls back to curl as the
HTTP client when a proxy is configured (via https_proxy, http_proxy,
HTTPS_PROXY, HTTP_PROXY, or ALL_PROXY environment variables). When no
proxy is detected, the original fetch-based implementation is used.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add dense-modules layout for data-rich guides and 3 new styles:
morandi-journal, pop-laboratory, retro-pop-grid. Add keyword shortcuts
for 高密度信息大图 auto-selection.
Prompt credit: AJ (https://waytoagi.feishu.cn/wiki/YG0zwalijihRREkgmPzcWRInnUg)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Runtime.evaluate reuses the same JS execution context across calls in a
session. The previous expression used `const thumbs = ...` which throws
"Identifier 'thumbs' has already been declared" on the second loop
iteration, causing result.value to be undefined and JSON.parse to throw
"JSON Parse error: Unexpected identifier 'undefined'".
Fix by inlining the querySelector into a single expression with no
variable declaration, eliminating the re-declaration error.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Switch md-to-html from manual line-by-line parsing to marked + front-matter +
highlight.js + remark-cjk-friendly for robust markdown conversion with syntax
highlighting, proper CJK handling, and standard frontmatter parsing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When generating multi-image series, use image 1 as --ref for all
subsequent images. This anchors character design, color rendering,
and illustration style across the entire series — critical for styles
with recurring characters or mascots.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Embed file path directly in PowerShell script with single-quote escaping
instead of using param()/−Path which fails with -Command parameter.
- Use fileURLToPath() for getScriptDir() to handle Windows drive-letter paths.
- Add deep analysis template for extracting specific visual elements
- Require MUST INCORPORATE section with concrete, reproducible details
- Add integration approach for spatial layout instructions
- Clarify ref-capable backend requirements (Google/OpenAI)
- Support --ref with OpenAI GPT Image models (gpt-image-1.5)
- Auto-select Google or OpenAI when --ref provided
- Change ref-related warnings to explicit errors with fix hints
- Add reference image validation before generation
- Improve retry logic to skip non-retryable errors
- Remove title from body content when extracting it for WeChat title field
to prevent duplicate title display (one in header, one in content)
- Remove manual ordered list prefix since HTML <ol> already provides numbering,
preventing "1.1.", "2.2.", "3.3." duplication
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add ArticleOptions interface with news/newspic types
- Track all image media IDs for newspic format
- Restructure publishToDraft for dual article type handling
Jim Liu 宝玉
cfh
Alec Jiang
shixy
JianJang2017
lindaifeng
ldf
Bryan Lee
luojiyin
jeff.zhao
Yangkai.Shen
李野
justnodejs
LyInfi
jeffrey94
史提芬达
AlexCheval