feat: add batch parallel image generation and provider-level throttling

- Add --batchfile and --jobs flags for multi-image parallel generation
  with per-provider concurrency control and rate limiting
- Refactor main.ts into prepareSingleTask/prepareBatchTasks/runBatchTasks
  with worker pool pattern and up to 3 retries per image
- Fix Replicate provider: use image_input array (nano-banana-pro schema),
  add match_input_image aspect ratio, add quality-to-resolution mapping
- Improve OpenAI error message for missing API key (Codex auth hint)
- Expand non-retryable error detection (4xx codes, disabled models)
- Add batch config to EXTEND.md schema (max_workers, provider_limits)
- Add build-batch.ts for article-illustrator batch workflow integration
- Add image-language awareness pass to baoyu-translate

Co-authored-by: 敖氏 <aoshi@MacBook-Air.local>

skills/baoyu-translate/SKILL.md

@@ -212,6 +212,7 @@ Before translating chunks:
 - **Natural flow**: Use idiomatic target language word order and sentence patterns; break or restructure sentences freely when the source structure doesn't work naturally in the target language
 - **Terminology**: Use standard translations; annotate with original term in parentheses on first occurrence
 - **Preserve format**: Keep all markdown formatting (headings, bold, italic, images, links, code blocks)
+- **Image-language awareness**: Preserve image references exactly during translation, but after the translation is complete, review referenced images and check whether their likely main text language still matches the translated article language
 - **Frontmatter transformation**: If the source has YAML frontmatter, preserve it in the translation with these changes: (1) Rename metadata fields that describe the *source* article — `url`→`sourceUrl`, `title`→`sourceTitle`, `description`→`sourceDescription`, `author`→`sourceAuthor`, `date`→`sourceDate`, and any similar origin-metadata fields — by adding a `source` prefix (camelCase). (2) Translate the values of text fields (title, description, etc.) and add them as new top-level fields. (3) Keep other fields (tags, categories, custom fields) as-is, translating their values where appropriate
 - **Respect original**: Maintain original meaning and intent; do not add, remove, or editorialize — but sentence structure and imagery may be adapted freely to serve the meaning
 - **Translator's notes**: For terms, concepts, or cultural references that target readers may not understand — due to jargon, cultural gaps, or domain-specific knowledge — add a concise explanatory note in parentheses immediately after the term. The note should explain *what it means* in plain language, not just provide the English original. Format: `译文（English original，通俗解释）`. Calibrate annotation depth to the target audience: general readers need more notes than technical readers. Only add notes where genuinely needed; do not over-annotate obvious terms.
@@ -250,6 +251,20 @@ Each step reads the previous step's file and builds on it.
 
 Final translation is always at `translation.md` in the output directory.
 
+After the final translation is written, do a lightweight image-language pass:
+
+1. Collect image references from the translated article
+2. Identify likely text-heavy images such as covers, screenshots, diagrams, charts, frameworks, and infographics
+3. If any image likely contains a main text language that does not match the translated article language, proactively remind the user
+4. The reminder must be a list only. Do not automatically localize those images unless the user asks
+
+Reminder format:
+```text
+Possible image localization needed:
+- ![[attachments/example-cover.png]]: likely still contains source-language text while the article is now in target language
+- ![[attachments/example-diagram.png]]: likely text-heavy framework graphic, check whether labels need translation
+```
+
 Display summary:
 ```
 **Translation complete** ({mode} mode)
@@ -261,6 +276,8 @@ Final: {output-dir}/translation.md
 Glossary terms applied: {count}
 ```
 
+If mismatched image-language candidates were found, append a short note after the summary telling the user that some embedded images may still need image-text localization, followed by the candidate list.
+
 ## Extension Support
 
 Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.