readme file updated

Author: SHRAVANIRANE

README.md

@@ -1,120 +1,126 @@
-# 🚀 CodeScribeAI
+# CodeScribeAI
+
+CodeScribeAI is a local-first coding assistant with:
+- FastAPI backend
+- React + Vite frontend
+- GitHub repository analysis
+- Ollama-powered AI responses
+
+## Current Architecture
+- Backend: `main.py` (FastAPI)
+- Frontend: `frontend/` (React, Vite)
+- Session store: SQLite (`sessions.db`)
+- Optional async workers: Celery + Redis
+
+## Prerequisites
+- Python 3.10+
+- Node.js 18+
+- Ollama installed and running
+- (Optional) Redis for async chat endpoints
+
+## Environment Setup
+1. Copy `.env.example` to `.env`
+2. Fill real credentials and secrets
 
-🚧 Note: The Project is in development
-<br>
-**CodeScribeAI** is an AI-powered coding assistant that helps you **explore, debug, and understand code** effortlessly.  
-Built with **React**, **Node.js**, and **Ollama LLM**, it’s designed to boost developer productivity and make coding more intuitive.  
-
----
-
-## ✨ Features
-
-- 🤖 **AI-Powered Assistance** – Get instant explanations, debugging help, and code insights.  
-- 📂 **File Analysis** – Upload or select files for detailed breakdowns.  
-- 💡 **Smart Suggestions** – Improve your code with AI-driven recommendations.  
-- 🎨 **Clean UI** – Minimal and distraction-free interface built with React + Tailwind.  
-- 🛠️ **Extensible Backend** – Node.js + Express API with modular routes.  
-- 🔒 **In Progress** – Actively being developed with new features coming soon!  
-
----
-
-## 🛠️ Tech Stack
-
-**Frontend**  
-- ⚛️ React  
-- 🎨 Tailwind CSS  
-- 🔄 React Router  
-- ✨ GSAP (animations)  
-
-**Backend**  
-- 🟢 Node.js + Express  
-- 🗄️ MySQL2 (with SSL for DigitalOcean)  
-- 📦 Multer (file uploads)  
-- 📧 Nodemailer (email handling)  
-
-**AI**  
-- 🧠 [Ollama](https://ollama.ai) – Local LLM integration  
-
----
+```bash
+cp .env.example .env
+```
 
-## 🚀 Getting Started
+Required keys:
+```env
+APP_ENV=development
+SECRET_KEY=replace-with-a-long-random-string
+FRONTEND_URL=http://localhost:5173
+SESSION_TTL_SECONDS=3600
+SESSIONS_DB_PATH=sessions.db
+GITHUB_CLIENT_ID=your_github_client_id
+GITHUB_CLIENT_SECRET=your_github_client_secret
+GITHUB_TOKEN=your_github_token
+OLLAMA_URL=http://127.0.0.1:11434
+OLLAMA_MODEL=phi3:mini
+OLLAMA_FALLBACK_MODELS=
+```
 
-Follow these steps to set up CodeScribeAI locally:
+Optional async keys:
+```env
+CELERY_BROKER_URL=redis://localhost:6379/0
+CELERY_RESULT_BACKEND=redis://localhost:6379/0
+```
 
-### 1️⃣ Clone the Repository
+## Install
+### Backend
 ```bash
-git clone https://github.com/your-username/codescribeAI.git
-cd codescribeAI
+# from repo root
+python -m venv venv
+# Windows PowerShell
+.\venv\Scripts\Activate.ps1
+pip install fastapi uvicorn httpx python-dotenv itsdangerous pydantic celery
 ```
-### 2️⃣ Install Dependencies
+
+### Frontend
 ```bash
-Frontend:
 cd frontend
 npm install
-Backend:
-cd backend
-npm install
 ```
-### 3️⃣ Configure Environment
-Copy `.env.example` to `.env` and fill values:
+
+## Run Locally
+### 1) Start Ollama
 ```bash
-cp .env.example .env
+ollama serve
+ollama pull phi3:mini
 ```
-Required values:
+
+### 2) Start backend
 ```bash
-APP_ENV=development
-SECRET_KEY=replace-with-a-long-random-string
-GITHUB_CLIENT_ID=your_github_client_id
-GITHUB_CLIENT_SECRET=your_github_client_secret
-GITHUB_TOKEN=your_github_token
-OLLAMA_URL=http://127.0.0.1:11434
+# from repo root
+.\venv\Scripts\Activate.ps1
+uvicorn main:app --reload --host 127.0.0.1 --port 8000
 ```
-Security notes:
-- Never commit `.env` to git.
-- Rotate secrets immediately if they were ever shared.
-### 4️⃣ Run the Project
-Start backend:
+
+### 3) Start frontend
 ```bash
-cd backend
-npm run dev
-Start frontend:
 cd frontend
 npm run dev
 ```
 
----
-
-## 📌 Roadmap
- AI-powered debugging suggestions
-
- Multi-file context awareness
-
- Chat-like interface for conversations with AI
-
- Cloud deployment (Vercel + DigitalOcean)
-
- Authentication & user profiles
-
-## 🤝 Contributing
-Contributions are welcome!
+Open: `http://localhost:5173`
 
-Fork the repo
+## Optional: Async Worker (Celery)
+Only needed if you use async task endpoints.
 
-Create a feature branch (git checkout -b feature-name)
-
-Commit changes (git commit -m "Add feature")
-
-Push to your branch (git push origin feature-name)
-
-Open a Pull Request 🎉
-
-## 📜 License
-This project is licensed under the MIT License.
-See the LICENSE file for details.
-
-## 🌟 Support
-If you like this project, please consider giving it a ⭐ on GitHub – it helps a lot!
+```bash
+# requires Redis running
+.\venv\Scripts\Activate.ps1
+celery -A main:celery_app worker --loglevel=info --pool=solo
+```
 
-## 📸 Screenshots (Coming Soon)
+## Testing and Quality
+### Backend tests
+```bash
+python -m unittest discover -s tests -v
+```
 
+### Frontend lint
+```bash
+cd frontend
+npm run lint
+```
 
+## Key API Endpoints
+- `GET /health`
+- `GET /api/ai-status`
+- `POST /api/chat`
+- `POST /api/chat-async` (optional, Celery)
+- `GET /repos/{username}`
+- `GET /repos/{owner}/{repo}/files?recursive=true`
+- `GET /repos/{owner}/{repo}/file-content?path=...`
+
+## Security Notes
+- Never commit `.env`.
+- Rotate any leaked credentials immediately.
+- For non-development environments:
+  - set a strong `SECRET_KEY`
+  - use secure deployment secrets management
+
+## Production Readiness
+See `PRODUCTION_READINESS.md` for checklist and current status.

frontend/src/components/FilePreview.jsx

@@ -1,4 +1,4 @@
-import { useState, useEffect } from "react";
+import { useState, useEffect } from "react";
 import { Prism as SyntaxHighlighter } from "react-syntax-highlighter";
 import { materialDark } from "react-syntax-highlighter/dist/esm/styles/prism";
 
@@ -96,7 +96,7 @@ export default function FilePreview({ owner, repo, filePath, askAI }) {
           <span className="absolute inset-0 w-full h-full bg-gradient-to-br from-blue-600 via-purple-600 to-pink-700"></span>
           <span className="absolute bottom-0 right-0 block w-64 h-64 mb-32 mr-4 transition duration-500 origin-bottom-left transform rotate-45 translate-x-24 bg-pink-500 rounded-full opacity-30 group-hover:rotate-90 ease"></span>
           <span className="relative text-white text-sm font-semibold">
-            🤖 Ask AI
+            Ask AI
           </span>
         </button>
       </div>
@@ -124,3 +124,4 @@ export default function FilePreview({ owner, repo, filePath, askAI }) {
     </div>
   );
 }
+

main.py

@@ -667,11 +667,11 @@ async def chat(req: ChatRequest):
 
     intent = detect_intent(msg)
 
-    # 1) Structured intents → GitHub API (deterministic answers)
+    # 1) Structured intents -> GitHub API (deterministic answers)
     try:
         if intent == "summarize_file":
             if not req.file_content:
-                return ChatResponse(reply="⚠️ To explain a file, please select one first.", meta={"grounded": False})
+                return ChatResponse(reply="[WARN] To explain a file, please select one first.", meta={"grounded": False})
 
             # Large files (especially notebooks) can time out local models.
             max_chars = 12000
@@ -741,7 +741,7 @@ async def chat(req: ChatRequest):
         if intent == "get_stars":
             meta = await get_repo_meta(req.github_user, req.repo)
             stars = meta.get("stargazers_count", 0)
-            return ChatResponse(reply=f"{req.repo} has ⭐ {stars} stars.", meta={"stars": stars})
+            return ChatResponse(reply=f"{req.repo} has * {stars} stars.", meta={"stars": stars})
 
         if intent == "get_repo_name":
             return ChatResponse(reply=f"The name of this repository is **{req.repo}**.")
@@ -752,28 +752,28 @@ async def chat(req: ChatRequest):
 
     except HTTPException as e:
         if e.status_code == 429:
-            return ChatResponse(reply="⚠️ GitHub rate limit reached. Please try again later.")
-        return ChatResponse(reply=f"⚠️ GitHub error: {e.detail}")
+            return ChatResponse(reply="[WARN] GitHub rate limit reached. Please try again later.")
+        return ChatResponse(reply=f"[WARN] GitHub error: {e.detail}")
     except Exception as e:
-        # Don’t block — we’ll still try LLM with context
+        # Do not block; still try LLM with context
         pass
 
-    # 2) Repo-related open questions → LLM grounded with context
+    # 2) Repo-related open questions -> LLM grounded with context
     if intent == "summarize_repo":
         ctx = await build_repo_context(req.github_user, req.repo, include_readme=True)
         ctx_block = format_context_block(ctx)
         prompt = (
             "You are a helpful software assistant. Use the provided repository context when relevant. "
-            "If the context is weak or missing details, say what you’re unsure about.\n\n"
+            "If the context is weak or missing details, say what you're unsure about.\n\n"
             f"User question:\n{msg}\n\n"
             f"Repository context:\n{ctx_block}\n\n"
             "Answer clearly and concisely."
         )
         ans = await call_llm(prompt, req.model)
         return ChatResponse(reply=ans, sources=[], meta={"grounded": True})
 
-    # 3) Anything else (general world questions, arbitrary chat) → ChatGPT-like
-    #    Still include repo context in case it helps, but don’t force it.
+    # 3) Anything else (general world questions, arbitrary chat) -> ChatGPT-like
+    #    Still include repo context in case it helps, but do not force it.
     ctx = await build_repo_context(req.github_user, req.repo, include_readme=False)
     repo_signal = re.search(r"\b(repo|repository|project|file|folder|directory|codebase|this repo)\b", msg.lower())
     if repo_signal and not (ctx.get("files") or ctx.get("dirs") or ctx.get("readme")):