fix

Dockerfile

@@ -52,7 +52,6 @@ RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir -r requirements.txt
 
 # Copy application code
-COPY --chown=user:user anycoder_app/ ./anycoder_app/
 COPY --chown=user:user backend_api.py .
 COPY --chown=user:user backend_models.py .
 COPY --chown=user:user backend_docs_manager.py .
@@ -61,7 +60,6 @@ COPY --chown=user:user backend_parsers.py .
 COPY --chown=user:user backend_deploy.py .
 COPY --chown=user:user backend_search_replace.py .
 COPY --chown=user:user project_importer.py .
-COPY --chown=user:user app.py .
 
 # Copy built frontend from builder stage
 COPY --chown=user:user --from=frontend-builder /build/.next ./frontend/.next

README.md

@@ -14,8 +14,6 @@ hf_oauth_scopes:
 - write-discussions
 ---
 
-> **Note:** This is the Docker Space configuration for the React frontend version.  
-> For the original Gradio app, see `README_GRADIO.md`.
 
 # AnyCoder - AI Code Generator with React Frontend
 
@@ -42,12 +40,6 @@ anycoder/
 │   │   ├── lib/            # API client, auth utilities
 │   │   └── types/          # TypeScript types
 │   └── package.json
-├── anycoder_app/           # Original Gradio app modules
-│   ├── agent.py
-│   ├── config.py
-│   ├── deploy.py
-│   └── ...
-├── app.py                  # Original Gradio interface
 ├── requirements.txt        # Python dependencies
 ├── Dockerfile              # Docker Space configuration
 └── start_fullstack.sh      # Local development script

README_GRADIO.md

@@ -1,145 +0,0 @@
----
-title: Anycoder
-emoji: 🔥
-colorFrom: indigo
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
-disable_embedding: true
-hf_oauth: true
-hf_oauth_scopes:
-- manage-repos
----
-
-# AnyCoder - AI Code Generator
-
-> **📱 New:** A React/TypeScript frontend version is now the default! This file is the backup Gradio version. For the Docker Space with modern React UI, see `README.md`.
-
-AnyCoder is an AI-powered code generator that helps you create applications by describing them in plain English. It supports multiple AI models, multimodal input, website redesign, and one-click deployment to Hugging Face Spaces. The UI is built with Gradio theming for a minimal, modern experience.
-
-## Features
-
-- **Multi-Model Support**: Choose from Moonshot Kimi-K2, Kimi K2 Turbo (Preview), Kimi K2 Thinking, DeepSeek V3, DeepSeek R1, ERNIE-4.5-VL, MiniMax M2, Qwen3-235B-A22B, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, SmolLM3-3B, GLM-4.1V-9B-Thinking, Gemini 2.5 Flash and Gemini 2.5 Pro (OpenAI-compatible)
- - Claude-Opus-4.1 (via Poe)
-- **Flexible Input**: Describe your app in text, upload a UI design image (for multimodal models), provide a reference file (PDF, TXT, MD, CSV, DOCX, or image), or enter a website URL for redesign
-- **Web Search Integration**: Enable real-time web search (Tavily, with advanced search depth) to enhance code generation with up-to-date information and best practices
-- **Code Generation**: Generate code in HTML, Python, JS, and more. Special support for transformers.js apps (outputs index.html, index.js, style.css)
-- **Live Preview**: Instantly preview generated HTML in a sandboxed iframe
-- **Modify Existing Code**: Use search/replace block format to update generated HTML
-- **One-Click Deployment**: Deploy your app to Hugging Face Spaces (Gradio, Streamlit, Static HTML, or Transformers.js) with OAuth login
-- **History & Examples**: Chat-like history of all interactions and quick example prompts for fast prototyping
-- **Minimal, Modern UI**: Built with Gradio 5.x, using only built-in theming and styling (no custom CSS)
-
-## Installation
-
-1. Clone the repository:
-```bash
-git clone <repository-url>
-cd anycoder
-```
-2. Install dependencies:
-```bash
-pip install -r requirements.txt
-```
-3. Set up environment variables:
-```bash
-export HF_TOKEN="your_huggingface_token"
-export DASHSCOPE_API_KEY="your_dashscope_api_key"  # Required for Qwen3-30B models via DashScope
-export POE_API_KEY="your_poe_api_key"  # Required for GPT-5, Grok-4, and Grok-Code-Fast-1 via Poe
-export GEMINI_API_KEY="your_gemini_api_key"  # Required for Gemini models
-export MOONSHOT_API_KEY="your_moonshot_api_key"  # Required for Kimi models
-export MINIMAX_API_KEY="your_minimax_api_key"  # Required for MiniMax M2 model
-```
-
-## Usage
-
-1. Run the application:
-```bash
-python app.py
-```
-2. Open your browser and navigate to the provided URL
-3. Describe your application in the text input field, or:
-   - Upload a UI design image (for multimodal models)
-   - Upload a reference file (PDF, TXT, MD, CSV, DOCX, or image)
-   - Enter a website URL for redesign (the app will extract and analyze the HTML and content)
-   - Enable web search for up-to-date information
-   - Choose a different AI model or code language
-4. Click "Generate" to create your code
-5. View the generated code in the Code tab or see it in action in the Preview tab
-6. Use the History tab to review previous generations
-7. **Deploy to Space**: Enter a title and click "🚀 Deploy App" to publish your application (OAuth login required) - the SDK is automatically matched to your selected code language
-
-## Supported Models
-
-- Moonshot Kimi-K2
-- Kimi K2 Turbo (Preview)
-- Kimi K2 Thinking
-- DeepSeek V3
-- DeepSeek V3.1
-- DeepSeek V3.1 Terminus
-- DeepSeek V3.2-Exp
-- DeepSeek R1
-- MiniMax M2
-- Qwen3-235B-A22B
-- Qwen3-4B-Instruct-2507
-- Qwen3-4B-Thinking-2507
-- Qwen3-30B-A3B-Instruct-2507 (via DashScope)
-- Qwen3-30B-A3B-Thinking-2507 (via DashScope)
-- GPT-5 (via Poe)
-- Grok-4 (via Poe)
- - Claude-Opus-4.1 (via Poe)
- - Gemini 2.5 Flash (OpenAI-compatible)
- - Gemini 2.5 Pro (OpenAI-compatible)
-
-## Input Options
-
-- **Text Prompt**: Describe your app or code requirements
-- **Image Upload**: For multimodal models, upload a UI design image to generate code from visuals
-- **File Upload**: Provide a reference file (PDF, TXT, MD, CSV, DOCX, or image) for code generation or text extraction (OCR for images)
-- **Website URL**: Enter a URL to extract and redesign the website (HTML and content are analyzed and modernized)
-
-## Code Generation & Modification
-
-- Generates code in HTML, Python, JS, and more (selectable via dropdown)
-- Special support for transformers.js apps (outputs index.html, index.js, style.css)
-- Svelte apps
-- For HTML, provides a live preview in a sandboxed iframe
-- For modification requests, uses a search/replace block format to update existing HTML
-
-## Deployment
-
-- Deploy generated apps to Hugging Face Spaces directly from the UI
-- Supported SDKs: Gradio (Python), Streamlit (Python), Static (HTML), Transformers.js
-- OAuth login with Hugging Face is required for deployment to user-owned Spaces
-
-## History & Examples
-
-- Maintains a chat-like history of user/assistant interactions
-- Quick example prompts are available in the sidebar for fast prototyping
-
-## UI/UX
-
-- Built with Gradio 5.x, using only Gradio's built-in theming and styling (no custom CSS)
-- Minimal, uncluttered sidebar and interface
-
-## Environment Variables
-
-- `HF_TOKEN`: Your Hugging Face API token (required)
- - `GEMINI_API_KEY`: Your Google Gemini API key (required to use Gemini models)
-- `MOONSHOT_API_KEY`: Your Moonshot AI API key (required to use Kimi models)
-- `MINIMAX_API_KEY`: Your MiniMax API key (required to use MiniMax M2 model)
-
-## Project Structure
-
-```
-anycoder/
-├── app.py          # Main application (all logic and UI)
-├── requirements.txt
-├── README.md       # This file
-```
-
-## License
-
-[Add your license information here]

app.py

@@ -1,31 +0,0 @@
-"""
-AnyCoder - AI Code Generator
-Main application entry point - now with modular architecture!
-"""
-
-# Import initialization functions from modules
-from anycoder_app.docs_manager import (
-    initialize_gradio_docs,
-    initialize_comfyui_docs,
-    initialize_fastrtc_docs
-)
-from anycoder_app.ui import demo
-
-if __name__ == "__main__":
-    # Initialize documentation systems
-    print("Initializing Gradio documentation...")
-    initialize_gradio_docs()
-    
-    print("Initializing ComfyUI documentation...")
-    initialize_comfyui_docs()
-    
-    print("Initializing FastRTC documentation...")
-    initialize_fastrtc_docs()
-    
-    # Launch the application
-    print("Launching AnyCoder application...")
-    demo.queue(api_open=False, default_concurrency_limit=20).launch(
-        show_api=False, 
-        ssr_mode=True, 
-        mcp_server=False
-    )

backend_search_replace.py

@@ -1,6 +1,6 @@
 """
 Search/Replace utilities for applying targeted code changes.
-Extracted from anycoder_app/parsers.py for use in backend.
+Search/Replace utilities for applying targeted code changes.
 """
 
 # Search/Replace block markers