Harness engineering beginner tutorial, from 0 to 1
TypeScript agentagenticagentic-aiaiai-agentai-agentsdshdsh-pluginharnessharness-engineeringharness-frameworkllm
Refine README screenshots and lecture 01 diagrams
sanbuphyc491d171f54e
diff --git a/README-CN.md b/README-CN.mdindex cb5c4ee..2814887 100644--- a/README-CN.md+++ b/README-CN.md@@ -15,21 +15,17 @@ Learn Harness Engineering 是一门专注于 AI 编程智能体工程化落地## 页面截图-### 中文+中文首页-<p>- <img src="./docs/public/screenshots/readme/zh-home.png" alt="中文首页预览" width="32%" />- <img src="./docs/public/screenshots/readme/zh-lecture-01.png" alt="中文讲义预览" width="32%" />- <img src="./docs/public/screenshots/readme/zh-resources.png" alt="中文资料库预览" width="32%" />-</p>+-### English+中文讲义页-<p>- <img src="./docs/public/screenshots/readme/en-home.png" alt="English homepage preview" width="32%" />- <img src="./docs/public/screenshots/readme/en-lecture-01.png" alt="English lecture preview" width="32%" />- <img src="./docs/public/screenshots/readme/en-resources.png" alt="English resources preview" width="32%" />-</p>+++中文资料库++## PDF 构建与 Release 流水线diff --git a/README.md b/README.mdindex 55d85eb..fa95f15 100644--- a/README.md+++ b/README.md@@ -15,21 +15,17 @@ Learn Harness Engineering is a course dedicated to the engineering of AI coding## Visual Preview-### English+English home page-<p>- <img src="./docs/public/screenshots/readme/en-home.png" alt="English homepage preview" width="32%" />- <img src="./docs/public/screenshots/readme/en-lecture-01.png" alt="English lecture preview" width="32%" />- <img src="./docs/public/screenshots/readme/en-resources.png" alt="English resources preview" width="32%" />-</p>+-### 中文+English lecture page-<p>- <img src="./docs/public/screenshots/readme/zh-home.png" alt="中文首页预览" width="32%" />- <img src="./docs/public/screenshots/readme/zh-lecture-01.png" alt="中文讲义预览" width="32%" />- <img src="./docs/public/screenshots/readme/zh-resources.png" alt="中文资料库预览" width="32%" />-</p>+++English resource library++## PDF Coursebooksdiff --git a/docs/.vitepress/theme/style.css b/docs/.vitepress/theme/style.cssindex ebbd146..367d183 100644--- a/docs/.vitepress/theme/style.css+++ b/docs/.vitepress/theme/style.css@@ -538,18 +538,17 @@margin: 20px 0;display: flex;justify-content: center;- overflow-x: auto;+ overflow-x: visible;overflow-y: visible;- -webkit-overflow-scrolling: touch;cursor: zoom-in;position: relative;}.vp-doc .mermaid svg {display: block;- width: clamp(780px, 100%, 1040px) !important;- max-width: none !important;- min-width: 780px;+ width: 100% !important;+ max-width: 100% !important;+ min-width: 0;height: auto !important;margin: 0 auto;}@@ -557,7 +556,7 @@.vp-doc .mermaid .label,.vp-doc .mermaid .nodeLabel,.vp-doc .mermaid .edgeLabel {- font-size: 18px !important;+ font-size: 16px !important;}.vp-doc .mermaid::after {@@ -601,14 +600,15 @@ html:lang(zh-CN) .vp-doc .mermaid::after {}.vp-doc .mermaid svg {- width: clamp(640px, 100%, 920px) !important;- min-width: 640px;+ width: 100% !important;+ max-width: 100% !important;+ min-width: 0;}.vp-doc .mermaid .label,.vp-doc .mermaid .nodeLabel,.vp-doc .mermaid .edgeLabel {- font-size: 16px !important;+ font-size: 14px !important;}.vp-doc .mermaid::after {diff --git a/docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md b/docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.mdindex 65e2f61..7808e67 100644--- a/docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md+++ b/docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md@@ -24,20 +24,26 @@ This isn't because the model isn't smart enough. It's because the working enviro```mermaidflowchart TB- Spec["Task not specific<br/>'add search' can mean many things"] --> Fail["Result:<br/>agent writes code<br/>but work is unreliable"]- Context["Project rules missing<br/>agent cannot see them"] --> Fail- Env["Environment broken<br/>deps or commands fail"] --> Fail- Verify["No tests or check commands"] --> Fail- State["No progress file<br/>next session starts blind"] --> Fail- Fail --> Fix["Fix the broken layer,<br/>then rerun"]+ Start["Start the task"] --> Q1{"Is the task specific?"}+ Q1 -->|No| Bad["Result:<br/>lots of code<br/>still unstable"]+ Q1 -->|Yes| Q2{"Are the rules in the repo?"}+ Q2 -->|No| Bad+ Q2 -->|Yes| Q3{"Does the environment run?"}+ Q3 -->|No| Bad+ Q3 -->|Yes| Q4{"Are there check commands?"}+ Q4 -->|No| Bad+ Q4 -->|Yes| Q5{"Is progress recorded?"}+ Q5 -->|No| Bad+ Q5 -->|Yes| Good["More likely to finish cleanly"]``````mermaid-flowchart LR- Same["Same prompt<br/>same model"] --> Bare["Bare run<br/>20 min / $9<br/>core features broken"]- Same --> Full["Add planning, checks, and evaluation<br/>6 hr / $200<br/>playable app"]- Bare --> Lesson["Only the harness changed"]- Full --> Lesson+flowchart TB+ Same["Same task<br/>same model"]+ Same --> Bare["Just one prompt<br/>20 min / $9"]+ Same --> Full["Rules and checks first<br/>6 hr / $200"]+ Bare --> Bad["Core features broken"]+ Full --> Good["Playable app"]```## Why This Happensdiff --git a/docs/zh/lectures/lecture-01-why-capable-agents-still-fail/index.md b/docs/zh/lectures/lecture-01-why-capable-agents-still-fail/index.mdindex e9f815b..96bc6bc 100644--- a/docs/zh/lectures/lecture-01-why-capable-agents-still-fail/index.md+++ b/docs/zh/lectures/lecture-01-why-capable-agents-still-fail/index.md@@ -24,20 +24,26 @@```mermaidflowchart TB- Spec["任务没写清楚<br/>比如“加搜索”含义很多"] --> Fail["结果:<br/>agent 写了很多代码<br/>但做事还是不稳定"]- Context["项目规则没写进仓库<br/>agent 看不到"] --> Fail- Env["环境没配好<br/>依赖或命令跑不起来"] --> Fail- Verify["没有测试或检查命令"] --> Fail- State["没有进度文件<br/>下一会话两眼一抹黑"] --> Fail- Fail --> Fix["把出错那一层补上<br/>再重新跑"]+ Start["开始做任务"] --> Q1{"任务写清了吗?"}+ Q1 -->|否| Bad["结果:<br/>写了很多代码<br/>但还是不稳"]+ Q1 -->|是| Q2{"规则写进仓库了吗?"}+ Q2 -->|否| Bad+ Q2 -->|是| Q3{"环境跑得起来吗?"}+ Q3 -->|否| Bad+ Q3 -->|是| Q4{"有检查命令吗?"}+ Q4 -->|否| Bad+ Q4 -->|是| Q5{"有进度记录吗?"}+ Q5 -->|否| Bad+ Q5 -->|是| Good["更容易稳定完成"]``````mermaid-flowchart LR- Same["同一个任务<br/>同一个模型"] --> Bare["裸跑<br/>20 分钟 / $9<br/>核心功能失效"]- Same --> Full["加上规划、检查和评估<br/>6 小时 / $200<br/>应用可以正常使用"]- Bare --> Lesson["变的只有 harness"]- Full --> Lesson+flowchart TB+ Same["同一个任务<br/>同一个模型"]+ Same --> Bare["只给一句话<br/>20 分钟 / $9"]+ Same --> Full["先定规则和检查<br/>6 小时 / $200"]+ Bare --> Bad["核心功能失效"]+ Full --> Good["应用可用"]```## 为什么会这样