Compare commits

...

2 Commits

Author SHA1 Message Date
Jim Liu 宝玉 499a1ee478 chore: release v1.24.2 2026-01-28 13:14:44 -06:00
Jim Liu 宝玉 fa89eaf2f7 refactor(baoyu-image-gen): default to sequential generation 2026-01-28 13:14:39 -06:00
4 changed files with 25 additions and 8 deletions
+1 -1
View File
@@ -6,7 +6,7 @@
}, },
"metadata": { "metadata": {
"description": "Skills shared by Baoyu for improving daily work efficiency", "description": "Skills shared by Baoyu for improving daily work efficiency",
"version": "1.24.1" "version": "1.24.2"
}, },
"plugins": [ "plugins": [
{ {
+5
View File
@@ -2,6 +2,11 @@
English | [中文](./CHANGELOG.zh.md) English | [中文](./CHANGELOG.zh.md)
## 1.24.2 - 2026-01-28
### Refactor
- `baoyu-image-gen`: default to sequential generation; parallel available on request.
## 1.24.1 - 2026-01-28 ## 1.24.1 - 2026-01-28
### Features ### Features
+5
View File
@@ -2,6 +2,11 @@
[English](./CHANGELOG.md) | 中文 [English](./CHANGELOG.md) | 中文
## 1.24.2 - 2026-01-28
### 重构
- `baoyu-image-gen`:默认改为顺序生成图片;并行生成需明确请求。
## 1.24.1 - 2026-01-28 ## 1.24.1 - 2026-01-28
### 新功能 ### 新功能
+14 -7
View File
@@ -1,6 +1,6 @@
--- ---
name: baoyu-image-gen name: baoyu-image-gen
description: AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images. description: AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.
--- ---
# Image Generation (AI SDK) # Image Generation (AI SDK)
@@ -124,25 +124,32 @@ Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
- Google Imagen: uses `aspectRatio` parameter - Google Imagen: uses `aspectRatio` parameter
- OpenAI: maps to closest supported size - OpenAI: maps to closest supported size
## Parallel Generation ## Generation Mode
Supports concurrent image generation via background subagents for batch operations. **Default**: Sequential generation (one image at a time). This ensures stable output and easier debugging.
**Parallel Generation**: Only use when user explicitly requests parallel/concurrent generation.
| Mode | When to Use |
|------|-------------|
| Sequential (default) | Normal usage, single images, small batches |
| Parallel | User explicitly requests, large batches (10+) |
**Parallel Settings** (when requested):
| Setting | Value | | Setting | Value |
|---------|-------| |---------|-------|
| Recommended concurrency | 4 subagents | | Recommended concurrency | 4 subagents |
| Max concurrency | 8 subagents | | Max concurrency | 8 subagents |
| Use case | Batch generation (slides, comics, infographics) | | Use case | Large batch generation when user requests parallel |
**Agent Implementation**: **Agent Implementation** (parallel mode only):
``` ```
# Launch multiple generations in parallel using Task tool # Launch multiple generations in parallel using Task tool
# Each Task runs as background subagent with run_in_background=true # Each Task runs as background subagent with run_in_background=true
# Collect results via TaskOutput when all complete # Collect results via TaskOutput when all complete
``` ```
**Best Practice**: When generating 4+ images, spawn background subagents (recommended 4 concurrent) instead of sequential execution.
## Error Handling ## Error Handling
- Missing API key → error with setup instructions - Missing API key → error with setup instructions