feat: expand gen2D deck with deep technical slides and interactive elements
Deploy Slides / build-and-deploy (push) Successful in 1m8s

- Add 5 new slide pages: eino-deep-dive, ratelimit-overview, ratelimit-lua, async-deep-dive, harness
- Add 4 new drawio SVGs: pipeline-detail, ratelimit, async-task, harness
- Update all existing slides with v-clicks progressive reveal
- Add presenter notes and interactive prompts
- Expand slides.md to register all new pages (16 → 25+ slides)
- Fix text overflow by trimming content per Item block
- Add Eino Graph deep dive: WithGenLocalState, Pre/Post Handler, branch routing
- Add rate limiting section: algorithm comparison, Lua script, Gin middleware
- Add async task deep dive: TaskQueue FIFO, context progress injection
- Add consistency section: style/pipeline/data/deployment 4-layer guarantees
This commit is contained in:
2026-05-30 22:42:23 +08:00
parent 659c22707b
commit 67ee76e58d
24 changed files with 878 additions and 33 deletions
+14 -6
View File
@@ -2,18 +2,26 @@
基于 Eino `compose.Graph` 编排的四阶段智能体协作管线
<v-clicks>
<Item title="① PromptOptimizer — 提示词优化">
合并工程风格 + 任务风格覆盖,生成三段式规范提示词。调用 Eino Chain 驱动 LLM 优化,无 Key 自动回退模板。
合并工程风格 + 任务风格覆盖,生成三段式规范提示词。LLM 优化,无 Key 自动回退模板。
</Item>
<Item title="② AssetGenerator — 素材生成">
调用 OpenAI 兼容的文生图 API(默认 Stability AI),根据优化后提示词生成素材。
调用 OpenAI 兼容的文生图 API,根据优化后提示词生成素材。
</Item>
<Item title="③ QualitySupervisor → ④ FormatAdapter">
视觉模型自动质检,不合格触发重优化(最多 3 次)。通过后组装 Spritesheet + 元数据,上传七牛云 Kodo。
<Item title="③ QualitySupervisor — 质检">
视觉模型自动质检,不合格触发重优化(最多 3 次)。
</Item>
<div class="mt-4 flex justify-center">
<img src="../public/pipeline.svg" class="w-full max-h-[180px] object-contain" />
<Item title="④ FormatAdapter — 格式适配">
组装 Spritesheet + 元数据,上传七牛云 Kodo。
</Item>
</v-clicks>
<div class="mt-2 flex justify-center">
<img src="../public/pipeline.svg" class="w-full max-h-[140px] object-contain" />
</div>