Import initial din SVN ROAAUTO/Trunk @HEAD

This commit is contained in:
2026-04-11 17:11:32 +03:00
commit 656d98697f
1856 changed files with 163525 additions and 0 deletions

View File

@@ -0,0 +1,42 @@
# CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Project Overview
This is a single-file chatbot application for Romfast technical support. The project consists of a standalone HTML file (`chatbot_maria.html`) that implements a full-featured chatbot interface using the Flowise embed library.
## Architecture
The chatbot integrates with a Flowise API backend hosted at `https://mutual-special-koala.ngrok-free.app` using chatflow ID `d4911620-07fe-41f8-adb4-f2f52d6ec766`.
Key architectural components:
- **Flowise Integration**: Uses the Flowise embed library from CDN for the main chatbot functionality
- **Direct API Mode**: Supports URL parameter-based message handling that bypasses the chat interface and displays responses in a modal overlay
- **Dual Display Modes**:
- Standard chatbot widget with starter prompts
- Direct API response modal when `?message=` URL parameter is present
## Key Features
- **Maria ChatBot**: Romanian language technical support assistant for Romfast ROA system
- **URL Parameter Support**: Can accept initial messages via `?message=` URL parameter
- **Conditional UI**: Hides starter prompts when a direct message is provided
- **Chat History**: Saves conversation history to localStorage when transitioning from API mode to chat mode
- **Responsive Design**: Mobile-friendly layout with collapsible menu
## Configuration
The chatbot configuration is embedded in the JavaScript module:
- API Host: `https://mutual-special-koala.ngrok-free.app`
- Chatflow ID: `d4911620-07fe-41f8-adb4-f2f52d6ec766`
- Romanian language interface with predefined starter prompts about eFactura, SAFT declarations, and auto service workflows
## Development Notes
This is a static HTML file with no build process. To modify:
1. Edit `chatbot_maria.html` directly
2. Test by opening in a browser
3. For URL parameter testing, use format: `chatbot_maria.html?message=your%20message%20here`
The application handles two distinct user flows based on URL parameters, switching between embedded chatbot widget and full-screen API response modal.