ruta serve chat

.gitignore

@@ -10,3 +10,6 @@ wheels/
 .venv
 .python-version
 .env
+
+# Databases
+*.sqlite3

Dockerfile

@@ -0,0 +1,42 @@
+# Multi-stage build for a Python backend with Deno frontend
+
+# Stage 1: Build the frontend
+FROM denoland/deno:2.4.3 AS frontend-builder
+
+# Set working directory for frontend
+WORKDIR /app/frontend
+
+# Copy frontend files
+COPY frontend/ .
+
+# Install dependencies and build the frontend
+RUN deno install --allow-scripts
+RUN deno run build
+
+# Stage 2: Setup Python backend with uv
+FROM python:3.11-slim AS backend
+
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /bin/uv
+
+# Set working directory
+WORKDIR /app
+
+# Copy Python project files
+COPY pyproject.toml uv.lock ./
+
+# Install Python dependencies
+RUN uv sync --frozen
+
+# Copy backend source code and .env file
+COPY *.py ./
+COPY .env ./
+
+# Copy built frontend from previous stage
+COPY --from=frontend-builder /app/frontend/dist ./frontend/dist
+
+# Expose the port (adjust if your app uses a different port)
+EXPOSE 8000
+
+# Run the application
+CMD ["uv", "run", "app.py"]

README.md

@@ -1,82 +0,0 @@
-# ChatSBT - Multi-Model Chat Application
-
-A modern chat application supporting multiple AI models through OpenRouter API.
-
-## Features
-
-- Chat with multiple AI models (Qwen, Deepseek, Kimi)
-- Real-time streaming responses
-- Conversation history
-- Simple REST API backend
-- Modern Svelte frontend
-
-## Tech Stack
-
-### Frontend
-- Svelte
-- DaisyUI (Tailwind component library)
-- Vite
-
-### Backend
-- Starlette (async Python web framework)
-- LangChain (LLM orchestration)
-- LangGraph (for potential future agent workflows)
-- OpenRouter API (multi-model provider)
-
-## API Endpoints
-
-| Method | Path | Description |
-|--------|------|-------------|
-| POST   | /chats | Create new chat session |
-| GET    | /chats/{chat_id} | Get chat history |
-| POST   | /chats/{chat_id}/messages | Post new message |
-| GET    | /chats/{chat_id}/stream | Stream response from AI |
-
-## Prerequisites
-
-- Python 3.11+
-- Deno
-- UV (Python package manager)
-- OpenRouter API key (set in `.env` file)
-
-## Installation
-
-1. Clone the repository
-2. Set up environment variables:
-
-```bash
-echo "OPENROUTER_API_KEY=your_key_here" > .env
-echo "OPENROUTER_BASE_URL=https://openrouter.ai/api/v1" >> .env
-```
-
-
-4. Install frontend dependencies:
-
-```bash
-cd chatsbt
-deno install
-```
-
-## Running
-
-1. Start backend server:
-
-```bash
-uv run app.py
-```
-
-2. Start the frontend (another terminal):
-
-```bash
-cd chatsbt
-deno run dev
-```
-
-The application will be available at `http://localhost:5173`
-
-## Configuration
-
-Available models:
-- `qwen/qwen3-235b-a22b-2507`
-- `deepseek/deepseek-r1-0528`
-- `moonshotai/kimi-k2`

TESTING.md

@@ -0,0 +1,131 @@
+# Backend API Testing with Hurl
+
+This document provides instructions for testing the chat backend API using Hurl.
+
+## Prerequisites
+
+1. **Install Hurl**: 
+   - macOS: `brew install hurl`
+   - Ubuntu/Debian: `sudo apt update && sudo apt install hurl`
+   - Windows: Download from [hurl.dev](https://hurl.dev)
+   - Or use Docker: `docker pull ghcr.io/orange-opensource/hurl:latest`
+
+2. **Start the backend server**:
+   ```bash
+   # Make sure you're in the project root directory
+   python -m uvicorn app:application --host 0.0.0.0 --port 8000 --reload
+   ```
+
+## Running the Tests
+
+### Basic Test Run
+```bash
+# Run all tests
+hurl test-backend.hurl
+
+# Run with verbose output
+hurl --verbose test-backend.hurl
+
+# Run with color output
+hurl --color test-backend.hurl
+```
+
+### Advanced Options
+```bash
+# Run with detailed report
+hurl --report-html report.html test-backend.hurl
+
+# Run specific tests (first 5 tests)
+hurl --to-entry 5 test-backend.hurl
+
+# Run tests with custom variables
+hurl --variable host=localhost --variable port=8000 test-backend.hurl
+
+# Run with retry on failure
+hurl --retry 3 test-backend.hurl
+```
+
+## Test Coverage
+
+The test script covers:
+
+### ✅ Happy Path Tests
+- **GET /api/models** - Retrieves available AI models
+- **POST /api/chats** - Creates new chat sessions
+- **GET /api/chats/{id}** - Retrieves chat history
+- **POST /api/chats/{id}/messages** - Sends messages to chat
+- **GET /api/chats/{id}/stream** - Streams AI responses via SSE
+
+### ✅ Error Handling Tests
+- Invalid model names
+- Non-existent chat IDs
+- Missing required parameters
+
+### ✅ Multi-turn Conversation Tests
+- Multiple message exchanges
+- Conversation history persistence
+- Different model selection
+
+## Test Structure
+
+The tests are organized in logical flow:
+
+1. **Model Discovery** - Get available models
+2. **Chat Creation** - Create new chat sessions
+3. **Message Exchange** - Send messages and receive responses
+4. **History Verification** - Ensure messages are persisted
+5. **Error Scenarios** - Test edge cases and error handling
+
+## Environment Variables
+
+You can customize the test environment:
+
+```bash
+# Set custom host/port
+export HURL_host=localhost
+export HURL_port=8000
+
+# Or pass as arguments
+hurl --variable host=127.0.0.1 --variable port=8080 test-backend.hurl
+```
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Connection refused**
+   - Ensure the backend is running on port 8000
+   - Check firewall settings
+
+2. **Tests fail with 404 errors**
+   - Verify the backend routes are correctly configured
+   - Check if database migrations have been run
+
+3. **SSE streaming tests timeout**
+   - Increase timeout: `hurl --max-time 30 test-backend.hurl`
+   - Check if AI provider is responding
+
+### Debug Mode
+
+Run tests with maximum verbosity:
+```bash
+hurl --very-verbose test-backend.hurl
+```
+
+## Continuous Integration
+
+Add to your CI/CD pipeline:
+
+```yaml
+# GitHub Actions example
+- name: Run API Tests
+  run: |
+    hurl --test --report-junit results.xml test-backend.hurl
+```
+
+## Test Results
+
+After running tests, you'll see:
+- ✅ **Green** - Tests passed
+- ❌ **Red** - Tests failed with details
+- 📊 **Summary** - Total tests, duration, and success rate

app.py

@@ -1,8 +1,11 @@
 from starlette.applications import Starlette
-from starlette.routing import Route
+from starlette.routing import Route, Mount
+from starlette.staticfiles import StaticFiles
+from starlette.responses import FileResponse
 from controllers import create_chat, post_message, chat_stream, history, get_models
 from starlette.middleware import Middleware
 from starlette.middleware.cors import CORSMiddleware
+import os
 
 middleware = [
     Middleware(
@@ -14,12 +17,24 @@ middleware = [
     )
 ]
 
+async def serve_frontend(request):
+    """Serve the frontend index.html file"""
+    return FileResponse(os.path.join("frontend", "dist", "index.html"))
+
+async def serve_chat(request):
+    """Serve the chat.html file for specific chat routes"""
+    return FileResponse(os.path.join("frontend", "dist", "chat.html"))
+
 routes = [
-    Route("/models", get_models, methods=["GET"]),
-    Route("/chats", create_chat, methods=["POST"]),
-    Route("/chats/{chat_id:str}", history, methods=["GET"]),
-    Route("/chats/{chat_id:str}/messages", post_message, methods=["POST"]),
-    Route("/chats/{chat_id:str}/stream",   chat_stream, methods=["GET"]),
+    Route("/", serve_frontend, methods=["GET"]),
+    Route("/chats/{chat_id:str}", serve_chat, methods=["GET"]),
+    Route("/api/models", get_models, methods=["GET"]),
+    Route("/api/chats", create_chat, methods=["POST"]),
+    Route("/api/chats/{chat_id:str}", history, methods=["GET"]),
+    Route("/api/chats/{chat_id:str}/messages", post_message, methods=["POST"]),
+    Route("/api/chats/{chat_id:str}/stream",   chat_stream, methods=["GET"]),
+    Mount("/assets", StaticFiles(directory=os.path.join("frontend", "dist", "assets")), name="assets"),
+    Mount("/icon", StaticFiles(directory=os.path.join("frontend", "dist", "icon")), name="icon"),
 ]
 
 

chatgraph.py

@@ -2,16 +2,18 @@ from langchain_openai import ChatOpenAI
 from langchain_core.messages import HumanMessage, AIMessage
 from os import getenv
 from dotenv import load_dotenv
+from pydantic import SecretStr
 
 load_dotenv()
 
 def get_llm(provider: str):
     """Return a LangChain chat model for the requested provider."""
     return ChatOpenAI(
-      openai_api_key=getenv("OPENROUTER_API_KEY"),
-      openai_api_base=getenv("OPENROUTER_BASE_URL"),
-      model_name=provider,
+      api_key=SecretStr(getenv("OPENROUTER_API_KEY","")),
+      base_url=getenv("OPENROUTER_BASE_URL"),
+      model=provider,
     )
 
 def get_messages(chats, chat_id):
-    return [HumanMessage(**m) if m["role"] == "human" else AIMessage(**m) for m in chats[chat_id]]
+    print(chats)
+    return [HumanMessage(**m) if m["role"] == "human" else AIMessage(**m) for m in chats]

chatsbt/.vscode/extensions.json

@@ -1,3 +0,0 @@
-{
-  "recommendations": ["svelte.svelte-vscode"]
-}

chatsbt/public/vite.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="31.88" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 257"><defs><linearGradient id="IconifyId1813088fe1fbc01fb466" x1="-.828%" x2="57.636%" y1="7.652%" y2="78.411%"><stop offset="0%" stop-color="#41D1FF"></stop><stop offset="100%" stop-color="#BD34FE"></stop></linearGradient><linearGradient id="IconifyId1813088fe1fbc01fb467" x1="43.376%" x2="50.316%" y1="2.242%" y2="89.03%"><stop offset="0%" stop-color="#FFEA83"></stop><stop offset="8.333%" stop-color="#FFDD35"></stop><stop offset="100%" stop-color="#FFA800"></stop></linearGradient></defs><path fill="url(#IconifyId1813088fe1fbc01fb466)" d="M255.153 37.938L134.897 252.976c-2.483 4.44-8.862 4.466-11.382.048L.875 37.958c-2.746-4.814 1.371-10.646 6.827-9.67l120.385 21.517a6.537 6.537 0 0 0 2.322-.004l117.867-21.483c5.438-.991 9.574 4.796 6.877 9.62Z"></path><path fill="url(#IconifyId1813088fe1fbc01fb467)" d="M185.432.063L96.44 17.501a3.268 3.268 0 0 0-2.634 3.014l-5.474 92.456a3.268 3.268 0 0 0 3.997 3.378l24.777-5.718c2.318-.535 4.413 1.507 3.936 3.838l-7.361 36.047c-.495 2.426 1.782 4.5 4.151 3.78l15.304-4.649c2.372-.72 4.652 1.36 4.15 3.788l-11.698 56.621c-.732 3.542 3.979 5.473 5.943 2.437l1.313-2.028l72.516-144.72c1.215-2.423-.88-5.186-3.54-4.672l-25.505 4.922c-2.396.462-4.435-1.77-3.759-4.114l16.646-57.705c.677-2.35-1.37-4.583-3.769-4.113Z"></path></svg>

chatsbt/src/assets/svelte.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="26.6" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 308"><path fill="#FF3E00" d="M239.682 40.707C211.113-.182 154.69-12.301 113.895 13.69L42.247 59.356a82.198 82.198 0 0 0-37.135 55.056a86.566 86.566 0 0 0 8.536 55.576a82.425 82.425 0 0 0-12.296 30.719a87.596 87.596 0 0 0 14.964 66.244c28.574 40.893 84.997 53.007 125.787 27.016l71.648-45.664a82.182 82.182 0 0 0 37.135-55.057a86.601 86.601 0 0 0-8.53-55.577a82.409 82.409 0 0 0 12.29-30.718a87.573 87.573 0 0 0-14.963-66.244"></path><path fill="#FFF" d="M106.889 270.841c-23.102 6.007-47.497-3.036-61.103-22.648a52.685 52.685 0 0 1-9.003-39.85a49.978 49.978 0 0 1 1.713-6.693l1.35-4.115l3.671 2.697a92.447 92.447 0 0 0 28.036 14.007l2.663.808l-.245 2.659a16.067 16.067 0 0 0 2.89 10.656a17.143 17.143 0 0 0 18.397 6.828a15.786 15.786 0 0 0 4.403-1.935l71.67-45.672a14.922 14.922 0 0 0 6.734-9.977a15.923 15.923 0 0 0-2.713-12.011a17.156 17.156 0 0 0-18.404-6.832a15.78 15.78 0 0 0-4.396 1.933l-27.35 17.434a52.298 52.298 0 0 1-14.553 6.391c-23.101 6.007-47.497-3.036-61.101-22.649a52.681 52.681 0 0 1-9.004-39.849a49.428 49.428 0 0 1 22.34-33.114l71.664-45.677a52.218 52.218 0 0 1 14.563-6.398c23.101-6.007 47.497 3.036 61.101 22.648a52.685 52.685 0 0 1 9.004 39.85a50.559 50.559 0 0 1-1.713 6.692l-1.35 4.116l-3.67-2.693a92.373 92.373 0 0 0-28.037-14.013l-2.664-.809l.246-2.658a16.099 16.099 0 0 0-2.89-10.656a17.143 17.143 0 0 0-18.398-6.828a15.786 15.786 0 0 0-4.402 1.935l-71.67 45.674a14.898 14.898 0 0 0-6.73 9.975a15.9 15.9 0 0 0 2.709 12.012a17.156 17.156 0 0 0 18.404 6.832a15.841 15.841 0 0 0 4.402-1.935l27.345-17.427a52.147 52.147 0 0 1 14.552-6.397c23.101-6.006 47.497 3.037 61.102 22.65a52.681 52.681 0 0 1 9.003 39.848a49.453 49.453 0 0 1-22.34 33.12l-71.664 45.673a52.218 52.218 0 0 1-14.563 6.398"></path></svg>

chatsbt/src/lib/router.svelte.js

@@ -1,31 +0,0 @@
-import { chatStore } from "./chatStore.svelte.js";
-
-// keyed by chat_id → chatStore instance
-const cache = $state({});
-
-// which chat is on screen right now
-export const activeChatId = $state(null);
-
-export function getStore(chatId) {
-  if (!cache[chatId]) {
-    cache[chatId] = chatStore(chatId);
-  }
-  return cache[chatId];
-}
-
-export function switchChat(chatId) {
-  activeChatId = chatId;
-}
-
-export function newChat() {
-  const id = "chat_" + crypto.randomUUID();
-  switchChat(id);
-  return id;
-}
-
-// restore last opened chat (or create first one)
-(() => {
-  const ids = JSON.parse(localStorage.getItem("chat_ids") || "[]");
-  if (ids.length) switchChat(ids[0]);
-  else newChat();
-})();

config/__init__.py

@@ -0,0 +1 @@
+# Masonite-orm module

config/database.py

@@ -0,0 +1,11 @@
+from masoniteorm.connections import ConnectionResolver
+
+DATABASES = {
+    "default": "sqlite",
+    "sqlite": {
+        "driver": "sqlite",
+        "database": "database.sqlite3",
+    }
+}
+
+DB = ConnectionResolver().set_connection_details(DATABASES)

controllers.py

@@ -1,12 +1,13 @@
 import uuid
+import json
 from typing import Dict, List, Tuple
 from starlette.responses import JSONResponse
 from starlette.requests import Request
 from sse_starlette.sse import EventSourceResponse
 from chatgraph import get_messages, get_llm
+from models.Chat import Chat
 
 
-CHATS: Dict[str, List[dict]] = {}          # chat_id -> messages
 PENDING: Dict[str, Tuple[str, str]] = {}   # message_id -> (chat_id, provider)
 
 MODELS = {
@@ -32,16 +33,22 @@ async def create_chat(request: Request):
     provider = body.get("model","")
     if provider not in MODELS:
             return JSONResponse({"error": "Unknown model"}, status_code=400)
-    chat_id = str(uuid.uuid4())[:8]
-    CHATS[chat_id] = []
+    chat = Chat()
+    chat_id = str(uuid.uuid4())
+    chat.id = chat_id
+    chat.title = "New Chat"
+    chat.messages = json.dumps([])
+    chat.save()
     return JSONResponse({"id": chat_id, "model": provider})
 
 async def history(request : Request):
     """GET /chats/{chat_id}  -> previous messages"""
     chat_id = request.path_params["chat_id"]
-    if chat_id not in CHATS:
+    chat = Chat.find(chat_id)
+    if not chat:
         return JSONResponse({"error": "Not found"}, status_code=404)
-    return JSONResponse({"messages": CHATS[chat_id]})
+    messages = json.loads(chat.messages) if chat.messages else []
+    return JSONResponse({"messages": messages})
 
 async def post_message(request: Request):
     """POST /chats/{chat_id}/messages
@@ -49,7 +56,8 @@ async def post_message(request: Request):
        Returns: {"message_id": "<chat_id>"}
     """
     chat_id = request.path_params["chat_id"]
-    if chat_id not in CHATS:
+    chat = Chat.find(chat_id)
+    if not chat:
         return JSONResponse({"error": "Chat not found"}, status_code=404)
 
     body = await request.json()
@@ -58,9 +66,14 @@ async def post_message(request: Request):
     if provider not in MODELS:
         return JSONResponse({"error": "Unknown model"}, status_code=400)
 
+    # Load existing messages and add the new user message
+    messages = json.loads(chat.messages) if chat.messages else []
+    messages.append({"role": "human", "content": user_text})
+    chat.messages = json.dumps(messages)
+    chat.save()
+
     message_id = str(uuid.uuid4())
     PENDING[message_id] = (chat_id, provider)
-    CHATS[chat_id].append({"role": "human", "content": user_text})
 
     return JSONResponse({
         "status": "queued",
@@ -72,13 +85,18 @@ async def chat_stream(request):
     chat_id = request.path_params["chat_id"]
     message_id = request.query_params.get("message_id")
 
-    if chat_id not in CHATS or message_id not in PENDING:
+    if message_id not in PENDING:
         return JSONResponse({"error": "Not found"}, status_code=404)
 
     chat_id_from_map, provider = PENDING.pop(message_id)
     assert chat_id == chat_id_from_map
 
-    msgs = get_messages(CHATS, chat_id)
+    chat = Chat.find(chat_id)
+    if not chat:
+        return JSONResponse({"error": "Chat not found"}, status_code=404)
+
+    messages = json.loads(chat.messages) if chat.messages else []
+    msgs = get_messages( messages , chat_id)
     llm = get_llm(provider)
 
     async def event_generator():
@@ -88,7 +106,10 @@ async def chat_stream(request):
             buffer += token
             yield {"data": token}
         # Finished: store assistant reply
-        CHATS[chat_id].append({"role": "assistant", "content": buffer})
+        messages.append({"role": "assistant", "content": buffer})
+        chat.messages = json.dumps(messages)
+        chat.save()
         yield {"event": "done", "data": ""}
 
     return EventSourceResponse(event_generator())
+

databases/migrations/2025_08_04_00001_create_chats_table.py

@@ -0,0 +1,12 @@
+from masoniteorm.migrations import Migration
+
+
+class CreateChatsTable(Migration):
+    def up(self):
+        with self.schema.create("chats") as table:
+            table.uuid("id").primary()
+            table.string("title")
+            table.json("messages")
+
+    def down(self):
+        self.schema.drop("chats")

frontend/deno.lock

@@ -6,9 +6,9 @@
     "npm:@tailwindcss/vite@^4.1.11": "4.1.11_vite@7.0.5__picomatch@4.0.3",
     "npm:daisyui@^5.0.46": "5.0.46",
     "npm:marked@^16.1.1": "16.1.1",
+    "npm:rolldown-vite@latest": "7.0.12_picomatch@4.0.3",
     "npm:svelte@^5.35.5": "5.36.8_acorn@8.15.0",
-    "npm:tailwindcss@^4.1.11": "4.1.11",
-    "npm:vite@^7.0.4": "7.0.5_picomatch@4.0.3"
+    "npm:tailwindcss@^4.1.11": "4.1.11"
   },
   "npm": {
     "@ampproject/remapping@2.3.0": {
@@ -201,6 +201,95 @@
         "@tybys/wasm-util@0.10.0"
       ]
     },
+    "@napi-rs/wasm-runtime@1.0.1": {
+      "integrity": "sha512-KVlQ/jgywZpixGCKMNwxStmmbYEMyokZpCf2YuIChhfJA2uqfAKNEM8INz7zzTo55iEXfBhIIs3VqYyqzDLj8g==",
+      "dependencies": [
+        "@emnapi/core",
+        "@emnapi/runtime",
+        "@tybys/wasm-util@0.10.0"
+      ]
+    },
+    "@oxc-project/runtime@0.78.0": {
+      "integrity": "sha512-jOU7sDFMyq5ShGJC21UobalVzqcdtWGfySVp8ELvKoVLzMpLHb4kv1bs9VKxaP8XC7Z9hlAXwEKVhCTN+j21aQ=="
+    },
+    "@oxc-project/types@0.78.0": {
+      "integrity": "sha512-8FvExh0WRWN1FoSTjah1xa9RlavZcJQ8/yxRbZ7ElmSa2Ij5f5Em7MvRbSthE6FbwC6Wh8iAw0Gpna7QdoqLGg=="
+    },
+    "@rolldown/binding-android-arm64@1.0.0-beta.30": {
+      "integrity": "sha512-4j7QBitb/WMT1fzdJo7BsFvVNaFR5WCQPdf/RPDHEsgQIYwBaHaL47KTZxncGFQDD1UAKN3XScJ0k7LAsZfsvg==",
+      "os": ["android"],
+      "cpu": ["arm64"]
+    },
+    "@rolldown/binding-darwin-arm64@1.0.0-beta.30": {
+      "integrity": "sha512-4vWFTe1o5LXeitI2lW8qMGRxxwrH/LhKd2HDLa/QPhdxohvdnfKyDZWN96XUhDyje2bHFCFyhMs3ak2lg2mJFA==",
+      "os": ["darwin"],
+      "cpu": ["arm64"]
+    },
+    "@rolldown/binding-darwin-x64@1.0.0-beta.30": {
+      "integrity": "sha512-MxrfodqImbsDFFFU/8LxyFPZjt7s4ht8g2Zb76EmIQ+xlmit46L9IzvWiuMpEaSJ5WbnjO7fCDWwakMGyJJ+Dw==",
+      "os": ["darwin"],
+      "cpu": ["x64"]
+    },
+    "@rolldown/binding-freebsd-x64@1.0.0-beta.30": {
+      "integrity": "sha512-c/TQXcATKoO8qE1bCjCOkymZTu7yVUAxBSNLp42Q97XHCb0Cu9v6MjZpB6c7Hq9NQ9NzW44uglak9D/r77JeDw==",
+      "os": ["freebsd"],
+      "cpu": ["x64"]
+    },
+    "@rolldown/binding-linux-arm-gnueabihf@1.0.0-beta.30": {
+      "integrity": "sha512-Vxci4xylM11zVqvrmezAaRjGBDyOlMRtlt7TDgxaBmSYLuiokXbZpD8aoSuOyjUAeN0/tmWItkxNGQza8UWGNQ==",
+      "os": ["linux"],
+      "cpu": ["arm"]
+    },
+    "@rolldown/binding-linux-arm64-gnu@1.0.0-beta.30": {
+      "integrity": "sha512-iEBEdSs25Ol0lXyVNs763f7YPAIP0t1EAjoXME81oJ94DesJslaLTj71Rn1shoMDVA+dfkYA286w5uYnOs9ZNA==",
+      "os": ["linux"],
+      "cpu": ["arm64"]
+    },
+    "@rolldown/binding-linux-arm64-musl@1.0.0-beta.30": {
+      "integrity": "sha512-Ny684Sn1X8c+gGLuDlxkOuwiEE3C7eEOqp1/YVBzQB4HO7U/b4n7alvHvShboOEY5DP1fFUjq6Z+sBLYlCIZbQ==",
+      "os": ["linux"],
+      "cpu": ["arm64"]
+    },
+    "@rolldown/binding-linux-arm64-ohos@1.0.0-beta.30": {
+      "integrity": "sha512-6moyULHDPKwt5RDEV72EqYw5n+s46AerTwtEBau5wCsZd1wuHS1L9z6wqhKISXAFTK9sneN0TEjvYKo+sgbbiA==",
+      "os": ["openharmony"],
+      "cpu": ["arm64"]
+    },
+    "@rolldown/binding-linux-x64-gnu@1.0.0-beta.30": {
+      "integrity": "sha512-p0yoPdoGg5Ow2YZKKB5Ypbn58i7u4XFk3PvMkriFnEcgtVk40c5u7miaX7jH0JdzahyXVBJ/KT5yEpJrzQn8yg==",
+      "os": ["linux"],
+      "cpu": ["x64"]
+    },
+    "@rolldown/binding-linux-x64-musl@1.0.0-beta.30": {
+      "integrity": "sha512-sM/KhCrsT0YdHX10mFSr0cvbfk1+btG6ftepAfqhbcDfhi0s65J4dTOxGmklJnJL9i1LXZ8WA3N4wmnqsfoK8Q==",
+      "os": ["linux"],
+      "cpu": ["x64"]
+    },
+    "@rolldown/binding-wasm32-wasi@1.0.0-beta.30": {
+      "integrity": "sha512-i3kD5OWs8PQP0V+JW3TFyCLuyjuNzrB45em0g84Jc+gvnDsGVlzVjMNPo7txE/yT8CfE90HC/lDs3ry9FvaUyw==",
+      "dependencies": [
+        "@napi-rs/wasm-runtime@1.0.1"
+      ],
+      "cpu": ["wasm32"]
+    },
+    "@rolldown/binding-win32-arm64-msvc@1.0.0-beta.30": {
+      "integrity": "sha512-q7mrYln30V35VrCqnBVQQvNPQm8Om9HC59I3kMYiOWogvJobzSPyO+HA1MP363+Qgwe39I2I1nqBKPOtWZ33AQ==",
+      "os": ["win32"],
+      "cpu": ["arm64"]
+    },
+    "@rolldown/binding-win32-ia32-msvc@1.0.0-beta.30": {
+      "integrity": "sha512-nUqGBt39XTpbBEREEnyKofdP3uz+SN/x2884BH+N3B2NjSUrP6NXwzltM35C0wKK42hX/nthRrwSgj715m99Jw==",
+      "os": ["win32"],
+      "cpu": ["ia32"]
+    },
+    "@rolldown/binding-win32-x64-msvc@1.0.0-beta.30": {
+      "integrity": "sha512-lbnvUwAXIVWSXAeZrCa4b1KvV/DW0rBnMHuX0T7I6ey1IsXZ90J37dEgt3j48Ex1Cw1E+5H7VDNP2gyOX8iu3w==",
+      "os": ["win32"],
+      "cpu": ["x64"]
+    },
+    "@rolldown/pluginutils@1.0.0-beta.30": {
+      "integrity": "sha512-whXaSoNUFiyDAjkUF8OBpOm77Szdbk5lGNqFe6CbVbJFrhCCPinCbRA3NjawwlNHla1No7xvXXh+CpSxnPfUEw=="
+    },
     "@rollup/rollup-android-arm-eabi@4.45.1": {
       "integrity": "sha512-NEySIFvMY0ZQO+utJkgoMiCAjMrGvnbDLHvcmlA33UXJpYBCvlBEbMMtV837uCkS+plG2umfhn0T5mMAxGrlRA==",
       "os": ["android"],
@@ -392,7 +481,7 @@
         "@emnapi/core",
         "@emnapi/runtime",
         "@emnapi/wasi-threads",
-        "@napi-rs/wasm-runtime",
+        "@napi-rs/wasm-runtime@0.2.12",
         "@tybys/wasm-util@0.9.0",
         "tslib"
       ],
@@ -468,6 +557,9 @@
       "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
       "bin": true
     },
+    "ansis@4.1.0": {
+      "integrity": "sha512-BGcItUBWSMRgOCe+SVZJ+S7yTRG0eGt9cXAHev72yuGcY23hnLA7Bky5L/xLyPINoSN95geovfBkqoTlNZYa7w=="
+    },
     "aria-query@5.3.2": {
       "integrity": "sha512-COROpnaoap1E2F000S62r6A60uHZnmlvomhfyT2DlTcrY1OrBKn2UhH7qn5wTC9zMvD0AY7csdPSNwKP+7WiQw=="
     },
@@ -709,6 +801,47 @@
         "source-map-js"
       ]
     },
+    "rolldown-vite@7.0.12_picomatch@4.0.3": {
+      "integrity": "sha512-Gr40FRnE98FwPJcMwcJgBwP6U7Qxw/VEtDsFdFjvGUTdgI/tTmF7z7dbVo/ajItM54G+Zo9w5BIrUmat6MbuWQ==",
+      "dependencies": [
+        "fdir",
+        "lightningcss",
+        "picomatch",
+        "postcss",
+        "rolldown",
+        "tinyglobby"
+      ],
+      "optionalDependencies": [
+        "fsevents"
+      ],
+      "bin": true
+    },
+    "rolldown@1.0.0-beta.30": {
+      "integrity": "sha512-H/LmDTUPlm65hWOTjXvd1k0qrGinNi8LrG3JsHVm6Oit7STg0upBmgoG5PZUHbAnGTHr0MLoLyzjmH261lIqSg==",
+      "dependencies": [
+        "@oxc-project/runtime",
+        "@oxc-project/types",
+        "@rolldown/pluginutils",
+        "ansis"
+      ],
+      "optionalDependencies": [
+        "@rolldown/binding-android-arm64",
+        "@rolldown/binding-darwin-arm64",
+        "@rolldown/binding-darwin-x64",
+        "@rolldown/binding-freebsd-x64",
+        "@rolldown/binding-linux-arm-gnueabihf",
+        "@rolldown/binding-linux-arm64-gnu",
+        "@rolldown/binding-linux-arm64-musl",
+        "@rolldown/binding-linux-arm64-ohos",
+        "@rolldown/binding-linux-x64-gnu",
+        "@rolldown/binding-linux-x64-musl",
+        "@rolldown/binding-wasm32-wasi",
+        "@rolldown/binding-win32-arm64-msvc",
+        "@rolldown/binding-win32-ia32-msvc",
+        "@rolldown/binding-win32-x64-msvc"
+      ],
+      "bin": true
+    },
     "rollup@4.45.1": {
       "integrity": "sha512-4iya7Jb76fVpQyLoiVpzUrsjQ12r3dM7fIVz+4NwoYvZOShknRmiv+iu9CClZml5ZLGb0XMcYLutK6w9tgxHDw==",
       "dependencies": [
@@ -830,9 +963,9 @@
         "npm:@tailwindcss/vite@^4.1.11",
         "npm:daisyui@^5.0.46",
         "npm:marked@^16.1.1",
+        "npm:rolldown-vite@latest",
         "npm:svelte@^5.35.5",
-        "npm:tailwindcss@^4.1.11",
-        "npm:vite@^7.0.4"
+        "npm:tailwindcss@^4.1.11"
       ]
     }
   }

frontend/index.html

@@ -2,7 +2,7 @@
 <html lang="en">
   <head>
     <meta charset="UTF-8" />
-    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
+    <link rel="icon" type="image/svg+xml" href="/icon/multibot_32.svg" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>Multi chat LLM</title>
   </head>

frontend/package.json

@@ -16,6 +16,6 @@
     "marked": "^16.1.1",
     "svelte": "^5.35.5",
     "tailwindcss": "^4.1.11",
-    "vite": "^7.0.4"
+    "vite": "npm:rolldown-vite@latest"
   }
 }

frontend/src/lib/ChatList.svelte

@@ -18,7 +18,7 @@
         {#each chatStore.history as c}
             <li>
                 <a
-                    href="/{c.id}"
+                    href="?chat={c.id}"
                     class={chatStore.chatId === c.id ? "active" : ""}
                     onclick={(e) => {
                         e.preventDefault();

frontend/src/lib/chatApi.svelte.js

@@ -1,7 +1,7 @@
-const API = "http://localhost:8000"; // change if needed
+const API = import.meta.env.CHATSBT_API_URL || "";
 
 export async function createChat(model = "qwen/qwen3-235b-a22b-2507") {
-  const r = await fetch(`${API}/chats`, {
+  const r = await fetch(`${API}/api/chats`, {
     method: "POST",
     body: JSON.stringify({ model }),
   });
@@ -9,7 +9,7 @@ export async function createChat(model = "qwen/qwen3-235b-a22b-2507") {
 }
 
 export async function sendUserMessage(chatId, text, model = "") {
-  const r = await fetch(`${API}/chats/${chatId}/messages`, {
+  const r = await fetch(`${API}/api/chats/${chatId}/messages`, {
     method: "POST",
     headers: { "Content-Type": "application/json" },
     body: JSON.stringify({ message: text, model }),
@@ -19,17 +19,17 @@ export async function sendUserMessage(chatId, text, model = "") {
 
 export function openStream(chatId, messageId) {
   return new EventSource(
-    `${API}/chats/${chatId}/stream?message_id=${messageId}`,
+    `${API}/api/chats/${chatId}/stream?message_id=${messageId}`,
   );
 }
 
 export async function fetchModels() {
   try {
-    const response = await fetch(`${API}/models`);
+    const response = await fetch(`${API}/api/models`);
     const data = await response.json();
     return data.models || [];
   } catch (error) {
-    console.error('Failed to fetch models:', error);
+    console.error("Failed to fetch models:", error);
     return [];
   }
 }

frontend/src/lib/chatStore.svelte.js

@@ -40,7 +40,14 @@ export const chatStore = (() => {
     messages = stored?.messages || [];
     loading = true;
     loading = false;
-    window.history.replaceState({}, "", `/${id}`);
+    // Update URL with GET parameter
+    const url = new URL(window.location.href);
+    if (id) {
+      url.searchParams.set('chat', id);
+    } else {
+      url.searchParams.delete('chat');
+    }
+    window.history.replaceState({}, "", url);
   }
 
   async function createAndSelect() {
@@ -101,13 +108,14 @@ export const chatStore = (() => {
     }
   }
 
-  // initial route handling
-  const path = window.location.pathname.slice(1);
+  // initial route handling - use GET parameter instead of path
+  const params = new URLSearchParams(window.location.search);
+  const chatIdFromUrl = params.get('chat');
   const storedHistory = loadHistory();
-  if (path && !storedHistory.find((c) => c.id === path)) {
+  if (chatIdFromUrl && !storedHistory.find((c) => c.id === chatIdFromUrl)) {
     createAndSelect();
-  } else if (path) {
-    selectChat(path);
+  } else if (chatIdFromUrl) {
+    selectChat(chatIdFromUrl);
   }
 
   // Load models on initialization

frontend/src/lib/router.svelte.js

@@ -0,0 +1,44 @@
+// Parse chat ID from GET parameter
+export function getChatIdFromUrl() {
+  const params = new URLSearchParams(window.location.search);
+  return params.get('chat');
+}
+
+// Update URL with GET parameter
+export function updateUrlWithChatId(chatId) {
+  const url = new URL(window.location.href);
+  if (chatId) {
+    url.searchParams.set('chat', chatId);
+  } else {
+    url.searchParams.delete('chat');
+  }
+  window.history.replaceState({}, "", url);
+}
+
+// which chat is on screen right now
+export let activeChatId = $state(null);
+
+export function switchChat(chatId) {
+  activeChatId = chatId;
+  updateUrlWithChatId(chatId);
+}
+
+export function newChat() {
+  const id = "chat_" + crypto.randomUUID();
+  switchChat(id);
+  return id;
+}
+
+// restore last opened chat (or create first one)
+(() => {
+  const ids = JSON.parse(localStorage.getItem("chat_ids") || "[]");
+  const urlChatId = getChatIdFromUrl();
+  
+  if (urlChatId) {
+    switchChat(urlChatId);
+  } else if (ids.length) {
+    switchChat(ids[0]);
+  } else {
+    newChat();
+  }
+})();

models/Chat.py

@@ -0,0 +1,10 @@
+from masoniteorm.models import Model
+from masoniteorm.scopes import UUIDPrimaryKeyMixin
+
+class Chat(Model, UUIDPrimaryKeyMixin):
+    __table__ = "chats"
+    __timestamps__ = False
+    __primary_key__ = "id"
+    __incrementing__ = False
+    
+    __fillable__ = ["id", "title", "messages"]

pyproject.toml

@@ -8,13 +8,11 @@ dependencies = [
     "jinja2>=3.1.6",
     "langchain>=0.3.26",
     "langchain-core>=0.3.68",
+    "langchain-openai>=0.3.28",
     "starlette>=0.47.1",
     "uvicorn>=0.35.0",
     "python-dotenv>=1.1.1",
-    "websockets>=15.0.1",
     "sse-starlette>=2.4.1",
-    "langchain-openai>=0.3.28",
-    "langgraph>=0.5.4",
-    "langgraph-checkpoint-sqlite>=2.0.11",
     "aiosqlite>=0.21.0",
+    "masonite-orm>=3.0.0",
 ]

test-backend.hurl

@@ -0,0 +1,165 @@
+# Hurl Test Script for Chat Backend API
+# This script tests the complete flow of the backend API
+
+# Test 1: Get available models
+GET http://localhost:8000/api/models
+
+HTTP 200
+[Captures]
+models: jsonpath "$.models"
+
+# Validate models response
+[Asserts]
+jsonpath "$.models" count > 0
+
+# Test 2: Create a new chat
+POST http://localhost:8000/api/chats
+Content-Type: application/json
+
+{
+  "model": "qwen/qwen3-235b-a22b-2507"
+}
+
+HTTP 200
+[Captures]
+chat_id: jsonpath "$.id"
+model: jsonpath "$.model"
+# Validate chat creation response
+[Asserts]
+jsonpath "$.id" != null
+jsonpath "$.model" == "qwen/qwen3-235b-a22b-2507"
+
+# Test 3: Get chat history (should be empty initially)
+GET http://localhost:8000/api/chats/{{chat_id}}
+
+HTTP 200
+[Captures]
+messages: jsonpath "$.messages"
+# Validate empty history
+[Asserts]
+jsonpath "$.messages" count == 0
+
+# Test 4: Post a message to the chat
+POST http://localhost:8000/api/chats/{{chat_id}}/messages
+Content-Type: application/json
+{
+  "message": "Hello, this is a test message",
+  "model": "{{model}}"
+}
+
+HTTP 200
+[Captures]
+message_id: jsonpath "$.message_id"
+status: jsonpath "$.status"
+# Validate message posting
+[Asserts]
+jsonpath "$.status" == "queued"
+jsonpath "$.message_id" != null
+
+# Test 5: Stream the response (SSE)
+GET http://localhost:8000/api/chats/{{chat_id}}/stream?message_id={{message_id}}
+HTTP 200
+[Asserts]
+header "Content-Type" == "text/event-stream; charset=utf-8"
+
+# Test 6: Verify chat history now contains messages
+GET http://localhost:8000/api/chats/{{chat_id}}
+
+HTTP 200
+[Captures]
+updated_messages: jsonpath "$.messages"
+# Validate messages are stored
+[Asserts]
+jsonpath "$.messages" count == 2
+jsonpath "$.messages[0].role" == "human"
+jsonpath "$.messages[0].content" == "Hello, this is a test message"
+jsonpath "$.messages[1].role" == "assistant"
+
+# Test 7: Post another message to test multi-turn conversation
+POST http://localhost:8000/api/chats/{{chat_id}}/messages
+Content-Type: application/json
+
+{
+  "message": "Can you tell me a joke?",
+  "model": "{{model}}"
+}
+
+HTTP 200
+[Captures]
+message_id2: jsonpath "$.message_id"
+
+# Test 8: Stream second response
+GET http://localhost:8000/api/chats/{{chat_id}}/stream?message_id={{message_id2}}
+
+HTTP 200
+
+# Test 9: Verify multi-turn conversation history
+GET http://localhost:8000/api/chats/{{chat_id}}
+
+HTTP 200
+[Captures]
+final_messages: jsonpath "$.messages"
+# Validate 4 messages (2 human + 2 assistant)
+[Asserts]
+jsonpath "$.messages" count == 4
+
+# Test 10: Error handling - Invalid model
+POST http://localhost:8000/api/chats
+Content-Type: application/json
+
+{
+  "model": "invalid-model-name"
+}
+
+HTTP 400
+[Asserts]
+jsonpath "$.error" == "Unknown model"
+
+# Test 11: Error handling - Chat not found
+GET http://localhost:8000/api/chats/non-existent-chat-id
+
+HTTP 404
+[Asserts]
+jsonpath "$.error" == "Not found"
+
+# Test 12: Error handling - Invalid chat ID for messages
+POST http://localhost:8000/api/chats/non-existent-chat-id/messages
+Content-Type: application/json
+
+{
+  "message": "This should fail",
+  "model": "qwen/qwen3-235b-a22b-2507"
+}
+
+HTTP 404
+[Asserts]
+jsonpath "$.error" == "Chat not found"
+
+# Test 13: Error handling - Missing message in post
+POST http://localhost:8000/api/chats/{{chat_id}}/messages
+Content-Type: application/json
+
+{
+  "model": "{{model}}"
+}
+
+HTTP 200
+# Note: The backend seems to accept empty messages, so this might not fail
+
+# Test 14: Create another chat with different model
+POST http://localhost:8000/api/chats
+Content-Type: application/json
+
+{
+  "model": "openai/gpt-4.1"
+}
+
+HTTP 200
+[Captures]
+chat_id2: jsonpath "$.id"
+model2: jsonpath "$.model"
+
+# Test 15: Verify second chat has different ID
+[Asserts]
+variable "chat_id" != "chat_id2"
+variable "model2" == "openai/gpt-4.1"