wonder
19075592e5
Deploy Slides / build-and-deploy (push) Successful in 1m16s
- Reduce Item count per slide: pipeline 4→3, solution 4→2, highlights 6→4 - Remove tech-stack architecture layering Item (moved to tech-stack grid) - Simplify eino-graph: shorter Go code, 3 Items→2 - Simplify prompt-agent: smaller mermaid, shorter Item text - Simplify async-task: merge 3 Items→2, remove footer - Simplify data-model: merge 4 grid items→2 - Simplify architecture: reduce ASCII diagram from 38 to 20 lines - Simplify dedup-ws: remove JSON code block, shorter Items - Simplify deployment: smaller mermaid, shorter Items - Simplify problem: shorter Item text, remove bullet lists - Simplify style-system: fix typo, shorter Item text
23 lines
799 B
Markdown
23 lines
799 B
Markdown
# 提示词优化 Agent
|
|
|
|
Eino Chain 驱动的智能提示词生成
|
|
|
|
<Item title="① 风格合并">
|
|
`finalStyle = merge(projectStyle, taskStyle)` — 工程风格为基底，任务风格逐键覆盖。自定义标签自动提取。
|
|
</Item>
|
|
|
|
<Item title="② 三段式提示词组装">
|
|
**主体描述**（用户输入）+ **风格约束**（美术风格、色调、线条）+ **技术规格**（尺寸、格式、透明背景）
|
|
</Item>
|
|
|
|
<Item title="③ LLM 优化 + 回退机制">
|
|
调用 Eino Chain 发给 DeepSeek 润色。**无 API Key 自动回退模板**，失败时注入重试上下文。
|
|
</Item>
|
|
|
|
```mermaid {scale: 0.65}
|
|
graph LR
|
|
A[用户描述] --> B[风格合并] --> C[三段式组装] --> D[LLM 优化] --> E[最终提示词]
|
|
F[工程风格] --> B
|
|
G[任务覆盖] --> B
|
|
```
|