Add e203_ifu_litebpu example to workshop demo

Author: SFangYy

.github/workflows/envbase.yaml

@@ -91,10 +91,6 @@ jobs:
 
   build-and-push-workshop:
     runs-on: ubuntu-latest
-    # Optional: depends on full image if we use it as base, 
-    # but here we use ucagent:latest which is built from main repo.
-    # To be safe, we can run it after build-and-push-full if we want to ensure base layers are available
-    needs: build-and-push-full
     permissions:
       contents: read
       packages: write

docker/Dockerfile.workshop

@@ -1,5 +1,5 @@
 # UCAgent Workshop Docker Image
-ARG BASE_IMAGE=localhost/lucagent:latest
+ARG BASE_IMAGE=ghcr.io/xs-mlvp/ucagent:latest
 FROM ${BASE_IMAGE}
 
 # Set environment variables
@@ -10,7 +10,7 @@ ENV SUMMIT_DATA_DIR=/workspace/UCAgent/summit_examples
 COPY workshop/data/ ${SUMMIT_DATA_DIR}/
 
 # Copy and setup startup script
-COPY docker/start_demo.sh /workspace/UCAgent/start_demo.sh
+COPY workshop/start_demo.sh /workspace/UCAgent/start_demo.sh
 RUN chmod +x /workspace/UCAgent/start_demo.sh
 
 # Expose ports for Web UI and Agents

workshop/ADD_NEW_EXAMPLE.md

@@ -7,7 +7,8 @@ This guide will walk you through pulling the pre-built environment, launching th
 ## 📦 Repository Overview
 
 In this repository, you will find:
-- **Pre-prepared Cases**: Classic verification examples along with their historical offline verification records.
+
+- **Pre-prepared Cases**: Classic verification examples along with their historical verification records.
 - **Docker Scripts**: The `Dockerfile` and `start_demo.sh` scripts, which our CI uses to automatically build and publish the workshop image.
 - **Environment Template**: A `.env.template` file for optional API configuration.
 
@@ -18,23 +19,30 @@ In this repository, you will find:
 You **do not** need to build the Docker image yourself. The tutorial repository's CI has automatically built and published the image for you.
 
 ### 1. Pull the Docker Image
+
 First, pull the latest workshop image to your local machine:
+
 ```bash
-docker pull ghcr.io/xs-mlvp/ucagent:workshop_demo
+docker pull ghcr.io/xs-mlvp/workshop:latest
 ```
 
 ### 2. Launch the Demo Environment
+
 Start the container using the following command. This will spin up the Master API server and load the pre-configured background agents:
+
 ```bash
 docker run -it --rm --network host ghcr.io/xs-mlvp/ucagent:workshop_demo
 ```
-*(Note: We use `--network host` so the container can easily map to your local ports and share your host's network settings.)*
+
+_(Note: We use `--network host` so the container can easily map to your local ports and share your host's network settings.)_
 
 ### 3. Explore the Web UI
+
 Once the terminal indicates that all services have started, open your web browser and navigate to:
 👉 **http://localhost:8800**
 
 In this unified Master Web Interface, you can:
+
 - **View Pre-loaded Tasks**: On the left-hand task panel, you will see the cases. Both should have a green **Online** status indicator.
 - **Review History**: Click the **API** connection button next to any task to jump into its real-time control center. Here, you can review previously generated code, stage verification logs, and Diff files without needing any LLM API keys.
 
@@ -46,6 +54,7 @@ The quick start above is perfect for exploring the UI and viewing the pre-genera
 
 1. **Prepare your `.env` file**  
    Copy the provided template and fill in your API credentials (e.g., OpenAI or a compatible interface):
+
    ```bash
    cp .env.template .env
    # Edit .env to add your OPENAI_API_KEY, OPENAI_API_BASE, and OPENAI_MODEL
@@ -54,7 +63,7 @@ The quick start above is perfect for exploring the UI and viewing the pre-genera
 2. **Launch with API Access**  
    Run the container again, this time attaching your `.env` file so the agents can connect to the LLM:
    ```bash
-   docker run -it --rm --network host --env-file .env ghcr.io/xs-mlvp/ucagent:workshop_demo
+   docker run -it --rm --network host --env-file .env ghcr.io/xs-mlvp/workshop:latest
    ```
-   
+
 With your API keys successfully loaded, the Agents are now fully empowered to execute new automated verification workflows based on your commands!

workshop/Workshop_Guide.md workshop/README.mdworkshop/Workshop_Guide.md renamed to workshop/README.md

@@ -7,7 +7,8 @@
 ## 📦 仓库内容简介
 
 在这个仓库中，包含了以下内容：
-- **预置验证案例**：经典的数字电路验证案例（如 Adder 加法器和 ALU754 浮点运算器），以及它们离线跑完的历史验证记录。
+
+- **预置验证案例**：经典的数字电路验证案例（如exu_alu和 ifu_bpu），以及它们离线跑完的历史验证记录。
 - **Docker 脚本**：`Dockerfile` 和 `start_demo.sh`，我们的 CI 流水线会自动使用它们来构建和发布本次 Workshop 的镜像。
 - **环境配置模板**：`.env.template` 文件，用于你在后续环节配置自己的大模型 API。
 
@@ -18,23 +19,30 @@
 你**不需要**从头开始构建 Docker 镜像，tutorial 仓库的 CI 已经自动帮你打包并发布好了。
 
 ### 1. 拉取镜像
+
 首先，将最新的 Workshop 镜像拉取到你的本地电脑：
+
 ```bash
-docker pull ghcr.io/xs-mlvp/ucagent:workshop_demo
+docker pull ghcr.io/xs-mlvp/workshop:latest
 ```
 
 ### 2. 启动演示环境
+
 运行以下命令来启动容器。这会自动启动 Master API 服务，并在后台加载好我们为你准备的预置任务：
+
 ```bash
-docker run -it --rm --network host ghcr.io/xs-mlvp/ucagent:workshop_demo
+docker run -it --rm --network host ghcr.io/xs-mlvp/workshop:latest
 ```
-*(注意：我们使用了 `--network host` 参数，这样容器可以直接映射并使用你宿主机的网络和端口。)*
+
+_(注意：我们使用了 `--network host` 参数，这样容器可以直接映射并使用你宿主机的网络和端口。)_
 
 ### 3. 探索 Web UI
+
 当终端提示服务启动完毕后，打开你的浏览器并访问：
 👉 **http://localhost:8800**
 
 在这个统一管理的 Master Web 界面中，你可以：
+
 - **查看预置任务**：在左侧的任务面板中，你会看到 `Adder` 和 `ALU754` 两个案例，它们应该都已经亮起了绿色的 **Online** 状态灯。
 - **复盘历史记录**：点击任意任务旁边的 **API** 按钮，即可进入该任务的实时控制台。在这里，你不需要配置任何大模型 Key，就可以直接查看 AI 之前生成的验证代码、日志以及阶段比对（Diff）。
 
@@ -46,6 +54,7 @@ docker run -it --rm --network host ghcr.io/xs-mlvp/ucagent:workshop_demo
 
 1. **准备 `.env` 配置文件**  
    复制我们提供的模板文件，填入你的 API Key 等信息（支持 OpenAI 或兼容接口）：
+
    ```bash
    cp .env.template .env
    # 编辑 .env 文件，补全 OPENAI_API_KEY, OPENAI_API_BASE 和 OPENAI_MODEL
@@ -56,5 +65,5 @@ docker run -it --rm --network host ghcr.io/xs-mlvp/ucagent:workshop_demo
    ```bash
    docker run -it --rm --network host --env-file .env ghcr.io/xs-mlvp/ucagent:workshop_demo
    ```
-   
+
 配置成功后，各个 Agent 就拥有了完整的执行能力，你可以开始下达新的指令，开启真正的自动化验证之旅了！