# Smart Task Planner [![React](https://img.shields.io/badge/React-19-blue?style=for-the-badge&logo=react)](https://react.dev/) [![TypeScript](https://img.shields.io/badge/TypeScript-5.x-blue?style=for-the-badge&logo=typescript)](https://www.typescriptlang.org/) [![Vercel](https://img.shields.io/badge/Vercel-Edge-black?style=for-the-badge&logo=vercel)](https://vercel.com/docs/functions/edge-functions) [![Tailwind CSS](https://img.shields.io/badge/Tailwind_CSS-3.x-38B2AC?style=for-the-badge&logo=tailwind-css)](https://tailwindcss.com/) An intelligent web application that turns your ambitious goals into actionable, step-by-step plans using the power of Google's Gemini AI. --- ## Live & Demo Experience the live application and see how your goals are transformed into a manageable project plan in seconds. Live link: **[https://goal-planner-liart.vercel.app/](https://goal-planner-liart.vercel.app/)** Demo Video: **[https://drive.google.com/file/d/1SefadZbCxVUL7FB8phFoG5xJ3eoPevrj/view?usp=drive_link](https://drive.google.com/file/d/1SefadZbCxVUL7FB8phFoG5xJ3eoPevrj/view?usp=drive_link)** --- ## About The Project Smart Task Planner bridges the gap between vision and execution. It leverages Google's advanced Gemini API to analyze a user's high-level goal and intelligently generate a comprehensive roadmap. The result is a detailed list of tasks, complete with descriptions, time estimates, and dependencies, giving users a clear and actionable path to success. This project was built to demonstrate a modern, secure, and performant full-stack application using a serverless backend architecture, ensuring both a great user experience and robust security. --- ## Application Screenshots **Landing Page:** image **Planner View:** image **Task Editing Modal:** image --- ## Core Features & Application Logic This application integrates several key technical features to deliver a seamless and powerful planning experience. ### AI-Powered Plan Generation - **Logic**: The core of the application resides in the `/api/generate-plan.ts` Vercel Edge Function. When a user submits a goal, the frontend sends a request to this secure backend endpoint. The function then constructs a detailed prompt, instructing the Gemini AI to act as an expert project manager. - **Structured Output**: To ensure a reliable and predictable response from the AI, the backend enforces a strict JSON schema via the `responseSchema` configuration. This forces the Gemini model to return a perfectly formatted JSON array of tasks, which the frontend can parse and render without requiring complex data manipulation. ### Dynamic Task Dependency System - **Logic**: The AI generates a `dependencies` array for each task (e.g., `["task-1", "task-3"]`). On the frontend, the `TaskList` component maintains a `Set` of completed task IDs for efficient lookups. - **User Experience**: Before rendering each task, the application checks if all of its prerequisite tasks have been completed. A task is visually "locked" (greyed out and non-interactive) if any of its dependencies are not yet met. Once all dependencies are finished, the task automatically unlocks, creating an intuitive and logical workflow for the user. ### Interactive Progress Tracking - **Logic**: The `PlannerView` component uses React's `useMemo` hook to efficiently calculate progress metrics whenever the `tasks` array changes. It counts completed tasks versus the total and sums the `durationInHours` for all tasks to provide a total project estimate. - **User Experience**: Users get immediate visual feedback via a dynamic progress bar, a "X / Y Tasks" counter, and a total estimated project duration, keeping them motivated and informed. ### Secure Serverless Architecture - **Logic**: The frontend **never** communicates directly with the Gemini API. All API calls are proxied through the `/api/generate-plan` serverless function. The `API_KEY` is stored securely as an environment variable on Vercel's servers and is never exposed to the client's browser. This is a critical security best practice that prevents key leakage. ### Simulated Authentication Flow - **Logic**: The application uses React state to manage a `currentUser` object, simulating a complete login/signup flow. Views are conditionally rendered based on whether a user object exists in the state, protecting the main planner view from unauthenticated access. This demonstrates state management for a typical user-gated application. --- ## Tech Stack This project is built with a modern web development stack: - **Frontend:** - **React**: For building the component-based user interface. - **TypeScript**: For static typing, improved code quality, and developer experience. - **Tailwind CSS**: For rapid, utility-first styling and a responsive design. - **Backend (Serverless):** - **Vercel Edge Functions**: To create a secure, scalable backend proxy for API calls. - **Core API:** - **Google Gemini API**: The AI engine for intelligent plan generation. - **Deployment:** - **Vercel**: For seamless, Git-based deployment and hosting. --- ## Local Development Setup To get a local copy up and running, follow these steps. ### Prerequisites - Node.js (v18 or later recommended) - npm, yarn, or pnpm - A Google Gemini API Key. You can get one for free from [Google AI Studio](https://makersuite.google.com/). ### Installation & Configuration 1. **Clone the repository:** ```sh git clone https://github.com/AbhinayManikanti/goal-planner.git cd goal-planner ``` 2. **Install the Vercel CLI:** ```sh npm install -g vercel ``` 3. **Create an environment file:** Create a new file named `.env` in the root of your project and add your Gemini API key: ``` API_KEY="YOUR_GEMINI_API_KEY_HERE" ``` 4. **Run the development server:** Use the Vercel CLI to run the project. This is the best method as it correctly serves both the React frontend and the serverless function in the `/api` directory. ```sh vercel dev ``` Your application should now be running at `http://localhost:3000`. --- ## Deployment This application is optimized for deployment on [Vercel](https://vercel.com/). 1. Push your code to a Git repository (GitHub, GitLab, etc.). 2. Import the repository into Vercel. 3. **Configure the Environment Variable (Crucial Step):** - In your Vercel project settings, navigate to **Settings > Environment Variables**. - Add a variable with the name `API_KEY` and paste your Gemini API key as the value. 4. Deploy. Vercel will automatically handle the build process for both the frontend and the serverless function. --- ## Author **Abhinay Manikanti** - **GitHub**: [@AbhinayManikanti](https://github.com/abhinay-07) - **LinkedIn**: [Abhinay Manikanti](https://www.linkedin.com/in/abhinay-manikanti) - **Project Link**: [https://github.com/AbhinayManikanti/goal-planner](https://github.com/AbhinayManikanti/goal-planner) 这是前后端分开跑的项目:后端是 FastAPI(端口 8000),前端是 Vite(端口 3000)。项目根目录已经有 `.venv`,`backend\.env` 也已经写好了。 ## 1. 准备 MySQL 用 phpStudy 把 MySQL 启动起来,然后建库(表会在后端第一次启动时自动创建): ```sql CREATE DATABASE goal_planner CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci; ``` 确认 `backend\.env` 里的 `MYSQL_HOST`、`MYSQL_PORT`、`MYSQL_USER`、`MYSQL_PASSWORD` 和 phpStudy 里的 MySQL 一致。当前文件里数据库名是 `goal_planner`,用户是 `root`。 ## 2. 启动后端 在 PowerShell 里执行。必须在 `backend` 目录启动,否则读不到 `.env`。 ```powershell cd d:\phpstudy_pro\WWW\python-projects\goal-planner .\.venv\Scripts\python.exe -m pip install -r backend\requirements.txt cd backend ..\.venv\Scripts\python.exe -m uvicorn main:app --host 127.0.0.1 --port 8000 --reload ``` 看到 `Uvicorn running on http://127.0.0.1:8000` 后,浏览器打开 http://127.0.0.1:8000/api/health ,应返回 `{"status":"ok"}`。 如果提示无法运行脚本,不要用 `Activate.ps1`,直接用上面的 `python.exe` 完整路径即可。 ## 3. 启动前端 另开一个 PowerShell: ```powershell cd d:\phpstudy_pro\WWW\python-projects\goal-planner\frontend npm install npm run dev ``` 浏览器打开 http://localhost:3000 。需要 Node.js 18 或更高版本。 ## 4. 让前端能打到后端 前端请求走的是 `/api-proxy`(给 Nginx 反代用的)。Vite 目前没有这条代理,只开两个服务的话,页面能打开,但登录和生成计划会 404。 在 `frontend\vite.config.ts` 的 `server` 里加上: ```ts server: { port: 3000, host: '0.0.0.0', proxy: { '/api-proxy': { target: 'http://127.0.0.1:8000', changeOrigin: true, rewrite: (path) => path.replace(/^\/api-proxy/, ''), }, }, }, ``` 改完后重启 `npm run dev`。请求 `/api-proxy/api/...` 会被转到 `http://127.0.0.1:8000/api/...`。