ngpt 2.12.0__tar.gz → 2.13.0__tar.gz

{ngpt-2.12.0 → ngpt-2.13.0}/CONTRIBUTING.md

@@ -29,7 +29,12 @@ Thank you for your interest in contributing to NGPT! This document provides guid
     - `config_manager.py` - CLI configuration handling
     - `formatters.py` - Output formatting logic
     - `interactive.py` - Interactive mode implementation
-    - `modes/` - Different operational modes (e.g., chat, run)
+    - `modes/` - Different operational modes
+      - `chat.py` - Chat mode functionality
+      - `code.py` - Code generation mode
+      - `shell.py` - Shell command generation
+      - `text.py` - Text generation mode
+      - `rewrite.py` - Text rewriting mode
     - `renderers.py` - Output rendering logic (e.g., markdown)
     - `ui.py` - User interface elements (e.g., prompts, spinners)
   - `utils/` - Utility modules
@@ -37,6 +42,10 @@ Thank you for your interest in contributing to NGPT! This document provides guid
     - `config.py` - API endpoint and general configuration management
     - `cli_config.py` - CLI-specific option configuration management
     - `log.py` - Logging setup and utilities
+- `docs/` - Documentation files
+  - `api/` - API reference documentation
+  - `examples/` - Example code and usage
+  - `usage/` - Usage guides and tutorials
 - `.github/` - GitHub workflows and templates
 - `pyproject.toml` - Project configuration and dependencies
 

{ngpt-2.12.0 → ngpt-2.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ngpt
-Version: 2.12.0
+Version: 2.13.0
 Summary: A lightweight Python CLI and library for interacting with OpenAI-compatible APIs, supporting both official and self-hosted LLM endpoints.
 Project-URL: Homepage, https://github.com/nazdridoy/ngpt
 Project-URL: Repository, https://github.com/nazdridoy/ngpt
@@ -29,6 +29,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Utilities
 Requires-Python: >=3.8
 Requires-Dist: prompt-toolkit>=3.0.0
+Requires-Dist: pyperclip>=1.8.0
 Requires-Dist: requests>=2.31.0
 Requires-Dist: rich>=10.0.0
 Description-Content-Type: text/markdown
@@ -103,6 +104,15 @@ ngpt --shell "list all files in the current directory"
 # Read from stdin and use the content in your prompt
 echo "What is this text about?" | ngpt --stdin "Analyze the following text: {}"
 
+# Rewrite text to improve quality while preserving tone and meaning
+echo "your text" | ngpt --rewrite
+
+# Rewrite text from a command-line argument
+ngpt --rewrite "your text to rewrite"
+
+# Use interactive multiline editor to enter text to rewrite
+ngpt --rewrite
+
 # Display markdown responses with beautiful formatting
 ngpt --prettify "Explain markdown syntax with examples"
 
@@ -138,10 +148,12 @@ For more examples and detailed usage, visit the [CLI Usage Guide](https://nazdri
 - 💬 **Interactive Chat**: Continuous conversation with memory in modern UI
 - 📊 **Streaming Responses**: Real-time output for better user experience
 - 🔍 **Web Search**: Integrated with compatible API endpoints
+- 📥 **Stdin Processing**: Process piped content by using `{}` placeholder in prompts
 - 🎨 **Markdown Rendering**: Beautiful formatting of markdown and code with syntax highlighting
 - ⚡ **Real-time Markdown**: Stream responses with live updating syntax highlighting and formatting
 - ⚙️ **Multiple Configurations**: Cross-platform config system supporting different profiles
 - 💻 **Shell Command Generation**: OS-aware command execution
+- 🧠 **Text Rewriting**: Improve text quality while maintaining original tone and meaning
 - 🧩 **Clean Code Generation**: Output code without markdown or explanations
 - 📝 **Rich Multiline Editor**: Interactive multiline text input with syntax highlighting and intuitive controls
 - 🎭 **System Prompts**: Customize model behavior with custom system prompts
@@ -349,38 +361,52 @@ For detailed information about building CLI tools with nGPT, see the [CLI Framew
 
 ### Command Line Options
 
-You can configure the client using the following options:
+You can configure nGPT using the following options:
+
+#### Mode Options (Mutually Exclusive)
+
+| Option | Description |
+|--------|-------------|
+| `-i, --interactive` | Start an interactive chat session with conversation memory and special commands |
+| `-s, --shell` | Generate and execute shell commands appropriate for your operating system |
+| `-c, --code` | Generate clean code without markdown formatting or explanations |
+| `-t, --text` | Open interactive multiline editor for complex prompts with syntax highlighting |
+| `--stdin` | Read from stdin and use content with prompt. Use {} in prompt as placeholder for stdin content |
+| `--rewrite` | Rewrite text to improve quality while preserving original tone and meaning |
+
+#### Global Options
 
 | Option | Description |
 |--------|-------------|
-| `--api-key` | API key for the service |
-| `--base-url` | Base URL for the API |
-| `--model` | Model to use |
-| `--list-models` | List all available models for the selected configuration (can be combined with --config-index) |
-| `--web-search` | Enable web search capability |
+| `--api-key KEY` | API key for the service |
+| `--base-url URL` | Base URL for the API |
+| `--model MODEL` | Model to use |
+| `--web-search` | Enable web search capability (if your API endpoint supports it) |
+| `--temperature VALUE` | Set temperature (controls randomness, default: 0.7) |
+| `--top_p VALUE` | Set top_p (controls diversity, default: 1.0) |
+| `--max_tokens NUMBER` | Set maximum response length in tokens |
+| `--preprompt TEXT` | Set custom system prompt to control AI behavior |
+| `--language LANG` | Programming language to generate code in (for code mode, default: python) |
 | `--no-stream` | Return the whole response without streaming |
-| `--temperature` | Set temperature (controls randomness, default: 0.7) |
-| `--top_p` | Set top_p (controls diversity, default: 1.0) |
-| `--max_tokens` | Set maximum response length in tokens |
-| `--preprompt` | Set custom system prompt to control AI behavior |
-| `--log` | Enable logging: use `--log` to create a temporary log file, or `--log PATH` for a specific location |
-| `--prettify` | Render markdown responses and code with syntax highlighting |
-| `--stream-prettify` | Enable real-time markdown rendering with syntax highlighting while streaming |
-| `--renderer` | Select which markdown renderer to use with --prettify (auto, rich, or glow) |
-| `--list-renderers` | Show available markdown renderers for use with --prettify |
-| `--config` | Path to a custom configuration file or, when used without a value, enters interactive configuration mode |
-| `--config-index` | Index of the configuration to use (default: 0) |
-| `--provider` | Provider name to identify the configuration to use (alternative to --config-index) |
+| `--prettify` | Render markdown responses and code with syntax highlighting and formatting |
+| `--stream-prettify` | Enable streaming with markdown rendering (automatically uses Rich renderer) |
+| `--renderer {auto,rich,glow}` | Select which markdown renderer to use with --prettify (default: auto) |
+| `--log [FILE]` | Set filepath to log conversation to, or create a temporary log file if no path provided |
+
+#### Configuration Options
+
+| Option | Description |
+|--------|-------------|
+| `--config [PATH]` | Path to a custom config file or, if no value provided, enter interactive configuration mode |
+| `--config-index INDEX` | Index of the configuration to use or edit (default: 0) |
+| `--provider NAME` | Provider name to identify the configuration to use |
 | `--remove` | Remove the configuration at the specified index (requires --config and --config-index or --provider) |
-| `--show-config` | Show configuration details and exit |
-| `--all` | Used with `--show-config` to display all configurations |
-| `-i, --interactive` | Start an interactive chat session with stylish UI, conversation history, and special commands |
-| `-s, --shell` | Generate and execute shell commands |
-| `-c, --code` | Generate clean code output |
-| `-t, --text` | Open interactive multiline editor for complex prompts |
-| `--language` | Programming language to generate code in (for code mode, default: python) |
-| `--cli-config` | Manage CLI configuration settings (set, get, unset, list, help) |
-| `-v, --version` | Show version information |
+| `--show-config` | Show the current configuration(s) and exit |
+| `--all` | Show details for all configurations (requires --show-config) |
+| `--list-models` | List all available models for the current configuration and exit |
+| `--list-renderers` | Show available markdown renderers for use with --prettify |
+| `--cli-config [COMMAND]` | Manage CLI configuration (set, get, unset, list, help) |
+| `-v, --version` | Show version information and exit |
 
 For a complete reference of all available options, see the [CLI Usage Guide](https://nazdridoy.github.io/ngpt/usage/cli_usage.html).
 

{ngpt-2.12.0 → ngpt-2.13.0}/README.md

@@ -68,6 +68,15 @@ ngpt --shell "list all files in the current directory"
 # Read from stdin and use the content in your prompt
 echo "What is this text about?" | ngpt --stdin "Analyze the following text: {}"
 
+# Rewrite text to improve quality while preserving tone and meaning
+echo "your text" | ngpt --rewrite
+
+# Rewrite text from a command-line argument
+ngpt --rewrite "your text to rewrite"
+
+# Use interactive multiline editor to enter text to rewrite
+ngpt --rewrite
+
 # Display markdown responses with beautiful formatting
 ngpt --prettify "Explain markdown syntax with examples"
 
@@ -103,10 +112,12 @@ For more examples and detailed usage, visit the [CLI Usage Guide](https://nazdri
 - 💬 **Interactive Chat**: Continuous conversation with memory in modern UI
 - 📊 **Streaming Responses**: Real-time output for better user experience
 - 🔍 **Web Search**: Integrated with compatible API endpoints
+- 📥 **Stdin Processing**: Process piped content by using `{}` placeholder in prompts
 - 🎨 **Markdown Rendering**: Beautiful formatting of markdown and code with syntax highlighting
 - ⚡ **Real-time Markdown**: Stream responses with live updating syntax highlighting and formatting
 - ⚙️ **Multiple Configurations**: Cross-platform config system supporting different profiles
 - 💻 **Shell Command Generation**: OS-aware command execution
+- 🧠 **Text Rewriting**: Improve text quality while maintaining original tone and meaning
 - 🧩 **Clean Code Generation**: Output code without markdown or explanations
 - 📝 **Rich Multiline Editor**: Interactive multiline text input with syntax highlighting and intuitive controls
 - 🎭 **System Prompts**: Customize model behavior with custom system prompts
@@ -314,38 +325,52 @@ For detailed information about building CLI tools with nGPT, see the [CLI Framew
 
 ### Command Line Options
 
-You can configure the client using the following options:
+You can configure nGPT using the following options:
+
+#### Mode Options (Mutually Exclusive)
+
+| Option | Description |
+|--------|-------------|
+| `-i, --interactive` | Start an interactive chat session with conversation memory and special commands |
+| `-s, --shell` | Generate and execute shell commands appropriate for your operating system |
+| `-c, --code` | Generate clean code without markdown formatting or explanations |
+| `-t, --text` | Open interactive multiline editor for complex prompts with syntax highlighting |
+| `--stdin` | Read from stdin and use content with prompt. Use {} in prompt as placeholder for stdin content |
+| `--rewrite` | Rewrite text to improve quality while preserving original tone and meaning |
+
+#### Global Options
 
 | Option | Description |
 |--------|-------------|
-| `--api-key` | API key for the service |
-| `--base-url` | Base URL for the API |
-| `--model` | Model to use |
-| `--list-models` | List all available models for the selected configuration (can be combined with --config-index) |
-| `--web-search` | Enable web search capability |
+| `--api-key KEY` | API key for the service |
+| `--base-url URL` | Base URL for the API |
+| `--model MODEL` | Model to use |
+| `--web-search` | Enable web search capability (if your API endpoint supports it) |
+| `--temperature VALUE` | Set temperature (controls randomness, default: 0.7) |
+| `--top_p VALUE` | Set top_p (controls diversity, default: 1.0) |
+| `--max_tokens NUMBER` | Set maximum response length in tokens |
+| `--preprompt TEXT` | Set custom system prompt to control AI behavior |
+| `--language LANG` | Programming language to generate code in (for code mode, default: python) |
 | `--no-stream` | Return the whole response without streaming |
-| `--temperature` | Set temperature (controls randomness, default: 0.7) |
-| `--top_p` | Set top_p (controls diversity, default: 1.0) |
-| `--max_tokens` | Set maximum response length in tokens |
-| `--preprompt` | Set custom system prompt to control AI behavior |
-| `--log` | Enable logging: use `--log` to create a temporary log file, or `--log PATH` for a specific location |
-| `--prettify` | Render markdown responses and code with syntax highlighting |
-| `--stream-prettify` | Enable real-time markdown rendering with syntax highlighting while streaming |
-| `--renderer` | Select which markdown renderer to use with --prettify (auto, rich, or glow) |
-| `--list-renderers` | Show available markdown renderers for use with --prettify |
-| `--config` | Path to a custom configuration file or, when used without a value, enters interactive configuration mode |
-| `--config-index` | Index of the configuration to use (default: 0) |
-| `--provider` | Provider name to identify the configuration to use (alternative to --config-index) |
+| `--prettify` | Render markdown responses and code with syntax highlighting and formatting |
+| `--stream-prettify` | Enable streaming with markdown rendering (automatically uses Rich renderer) |
+| `--renderer {auto,rich,glow}` | Select which markdown renderer to use with --prettify (default: auto) |
+| `--log [FILE]` | Set filepath to log conversation to, or create a temporary log file if no path provided |
+
+#### Configuration Options
+
+| Option | Description |
+|--------|-------------|
+| `--config [PATH]` | Path to a custom config file or, if no value provided, enter interactive configuration mode |
+| `--config-index INDEX` | Index of the configuration to use or edit (default: 0) |
+| `--provider NAME` | Provider name to identify the configuration to use |
 | `--remove` | Remove the configuration at the specified index (requires --config and --config-index or --provider) |
-| `--show-config` | Show configuration details and exit |
-| `--all` | Used with `--show-config` to display all configurations |
-| `-i, --interactive` | Start an interactive chat session with stylish UI, conversation history, and special commands |
-| `-s, --shell` | Generate and execute shell commands |
-| `-c, --code` | Generate clean code output |
-| `-t, --text` | Open interactive multiline editor for complex prompts |
-| `--language` | Programming language to generate code in (for code mode, default: python) |
-| `--cli-config` | Manage CLI configuration settings (set, get, unset, list, help) |
-| `-v, --version` | Show version information |
+| `--show-config` | Show the current configuration(s) and exit |
+| `--all` | Show details for all configurations (requires --show-config) |
+| `--list-models` | List all available models for the current configuration and exit |
+| `--list-renderers` | Show available markdown renderers for use with --prettify |
+| `--cli-config [COMMAND]` | Manage CLI configuration (set, get, unset, list, help) |
+| `-v, --version` | Show version information and exit |
 
 For a complete reference of all available options, see the [CLI Usage Guide](https://nazdridoy.github.io/ngpt/usage/cli_usage.html).
 

{ngpt-2.12.0 → ngpt-2.13.0}/docs/CONTRIBUTING.md

@@ -1,4 +1,6 @@
 ---
+title: Contributing to NGPT
+description: Guidelines and instructions for contributing to the NGPT project
 ---
 
 # Contributing to NGPT
@@ -32,7 +34,12 @@ Thank you for your interest in contributing to NGPT! This document provides guid
     - `config_manager.py` - CLI configuration handling
     - `formatters.py` - Output formatting logic
     - `interactive.py` - Interactive mode implementation
-    - `modes/` - Different operational modes (e.g., chat, run)
+    - `modes/` - Different operational modes
+      - `chat.py` - Chat mode functionality
+      - `code.py` - Code generation mode
+      - `shell.py` - Shell command generation
+      - `text.py` - Text generation mode
+      - `rewrite.py` - Text rewriting mode
     - `renderers.py` - Output rendering logic (e.g., markdown)
     - `ui.py` - User interface elements (e.g., prompts, spinners)
   - `utils/` - Utility modules
@@ -40,6 +47,10 @@ Thank you for your interest in contributing to NGPT! This document provides guid
     - `config.py` - API endpoint and general configuration management
     - `cli_config.py` - CLI-specific option configuration management
     - `log.py` - Logging setup and utilities
+- `docs/` - Documentation files
+  - `api/` - API reference documentation
+  - `examples/` - Example code and usage
+  - `usage/` - Usage guides and tutorials
 - `.github/` - GitHub workflows and templates
 - `pyproject.toml` - Project configuration and dependencies
 

{ngpt-2.12.0 → ngpt-2.13.0}/docs/api/cli.md

@@ -544,6 +544,136 @@ text_mode(
 )
 ```
 
+### Rewrite Mode
+
+```python
+from ngpt.cli.modes.rewrite import rewrite_mode
+
+def rewrite_mode(
+    client,
+    args,
+    logger=None
+)
+```
+
+Executes a text rewriting operation to improve text quality while preserving meaning and tone.
+
+**Parameters:**
+- `client` (NGPTClient): The initialized client for the operation
+- `args` (namespace): Parsed command-line arguments including:
+  - `prompt` (str, optional): Text to rewrite from command line
+  - `temperature` (float): Temperature setting (0.0-1.0)
+  - `top_p` (float): Top-p sampling value (0.0-1.0)
+  - `max_tokens` (int, optional): Maximum tokens to generate
+  - `no_stream` (bool): Whether to disable streaming
+  - `prettify` (bool): Whether to prettify markdown output
+  - `stream_prettify` (bool): Enable real-time markdown rendering
+  - `renderer` (str): Markdown renderer to use
+  - `web_search` (bool): Whether to enable web search
+- `logger` (object, optional): Logger instance
+
+**Input Methods:**
+The rewrite mode supports three input methods:
+1. Stdin (piped input): Content read from stdin if available
+2. Command-line argument: Text provided via args.prompt
+3. Multiline editor: If neither stdin nor prompt is available, opens interactive editor
+
+**Features:**
+- **Text Quality Improvement**: Fixes grammar, flow, readability while preserving meaning
+- **Multiline Editor**: Interactive editor with syntax highlighting for entering text when no input is piped or provided as argument
+- **Clipboard Integration**: Offers to copy rewritten text to clipboard with cross-platform support
+- **Format Preservation**: Maintains original formatting including code blocks, lists, and markdown
+
+**Example with Stdin:**
+```python
+import sys
+import subprocess
+from ngpt import NGPTClient, load_config
+from ngpt.cli.modes.rewrite import rewrite_mode
+import argparse
+
+client = NGPTClient(**load_config())
+
+# Create args namespace with required parameters
+args = argparse.Namespace()
+args.prompt = None
+args.temperature = 0.7
+args.top_p = 1.0
+args.max_tokens = None
+args.no_stream = False
+args.prettify = True
+args.stream_prettify = False
+args.renderer = 'rich'
+args.web_search = False
+
+# Redirect stdin from a string or file
+original_stdin = sys.stdin
+sys.stdin = open('text_to_rewrite.txt', 'r')
+
+# Call rewrite mode
+rewrite_mode(client=client, args=args)
+
+# Restore stdin
+sys.stdin = original_stdin
+```
+
+**Example with Command-line Argument:**
+```python
+from ngpt import NGPTClient, load_config
+from ngpt.cli.modes.rewrite import rewrite_mode
+import argparse
+
+client = NGPTClient(**load_config())
+
+# Create args namespace with required parameters
+args = argparse.Namespace()
+args.prompt = "We was hoping you could help with this issue what we are having with the server."
+args.temperature = 0.7
+args.top_p = 1.0
+args.max_tokens = None
+args.no_stream = False
+args.prettify = True
+args.stream_prettify = False
+args.renderer = 'rich'
+args.web_search = False
+
+rewrite_mode(
+    client=client,
+    args=args
+)
+```
+
+**Example with Multiline Editor:**
+```python
+from ngpt import NGPTClient, load_config
+from ngpt.cli.modes.rewrite import rewrite_mode
+import argparse
+import sys
+
+client = NGPTClient(**load_config())
+
+# Create args namespace with required parameters
+args = argparse.Namespace()
+args.prompt = None
+args.temperature = 0.7
+args.top_p = 1.0
+args.max_tokens = None
+args.no_stream = False
+args.prettify = True
+args.stream_prettify = False
+args.renderer = 'rich'
+args.web_search = False
+
+# Ensure stdin appears to be a TTY
+# (This will trigger the multiline editor in a real terminal)
+# Note: This is just to illustrate how the condition works
+if sys.stdin.isatty():
+    print("Multiline editor will open in a real terminal")
+    rewrite_mode(client=client, args=args)
+else:
+    print("This example would open a multiline editor in a real terminal")
+```
+
 ## Reference Tables
 
 ### Markdown Renderers

{ngpt-2.12.0 → ngpt-2.13.0}/docs/configuration.md

@@ -124,6 +124,7 @@ You can also set configuration options directly via command-line arguments:
 - `-c, --code`: Generate code.
   - `--language <lang>`: Specify the programming language for code generation (e.g., `python`, `javascript`, default: `python`).
 - `-t, --text`: Use a multiline editor for input.
+- `--stdin`: Read from stdin and use content in your prompt with {} placeholder.
 - `--no-stream`: Disable streaming output.
 - `--prettify`: Enable formatted markdown/code output (disables streaming).
   - `--renderer <name>`: Choose the renderer (`auto`, `rich`, `glow`).
@@ -162,6 +163,9 @@ ngpt --interactive --log conversation.log
 
 # Create a temporary log file automatically
 ngpt --log "Tell me about quantum computing"
+
+# Process text from stdin using the {} placeholder
+echo "What is this text about?" | ngpt --stdin "Analyze the following text: {}"
 ```
 
 ## Environment Variables

{ngpt-2.12.0 → ngpt-2.13.0}/docs/examples/cli_components.md

@@ -397,6 +397,197 @@ Save this as `code-review.py` and use it:
 python code-review.py --language javascript --prettify
 ```
 
+## Building a Text Rewriting Tool
+
+This example creates a text improvement tool that uses nGPT's rewrite mode to enhance text quality while preserving the original meaning and tone:
+
+```python
+#!/usr/bin/env python3
+import argparse
+import sys
+from pathlib import Path
+from ngpt import NGPTClient
+from ngpt.utils.config import load_config
+from ngpt.cli.ui import multiline_editor
+from ngpt.cli.renderers import prettify_markdown, prettify_streaming_markdown
+from ngpt.cli.formatters import ColoredHelpFormatter, COLORS
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Text improvement assistant",
+        formatter_class=ColoredHelpFormatter
+    )
+    
+    # Command line arguments
+    parser.add_argument("text", nargs="?", help="Text to rewrite (optional)")
+    parser.add_argument("--file", "-f", help="Read text from file")
+    parser.add_argument("--output", "-o", help="Save output to file")
+    parser.add_argument("--type", "-t", choices=["formal", "casual", "academic", "creative", "general"],
+                      default="general", help="Style of rewriting")
+    parser.add_argument("--stream", "-s", action="store_true", 
+                      help="Stream results with live updates")
+    parser.add_argument("--prettify", "-p", action="store_true", 
+                      help="Format output with markdown rendering")
+    
+    args = parser.parse_args()
+    
+    # Get input text
+    text = ""
+    if args.text:
+        # Text from command line
+        text = args.text
+    elif args.file:
+        # Text from file
+        try:
+            file_path = Path(args.file)
+            if not file_path.exists():
+                print(f"Error: File '{args.file}' not found", file=sys.stderr)
+                sys.exit(1)
+            with open(file_path, 'r') as f:
+                text = f.read()
+        except Exception as e:
+            print(f"Error reading file: {e}", file=sys.stderr)
+            sys.exit(1)
+    else:
+        # No text provided, use multiline editor
+        try:
+            import prompt_toolkit
+        except ImportError:
+            print("Error: prompt_toolkit is required for multiline editor", file=sys.stderr)
+            print("Install with: pip install prompt_toolkit", file=sys.stderr)
+            sys.exit(1)
+        
+        print(f"{COLORS['cyan']}Text Improvement Assistant{COLORS['reset']}")
+        print("Enter or paste the text you want to improve.")
+        print("Press Ctrl+D to submit, or Esc to cancel.")
+        
+        try:
+            text = multiline_editor(
+                message="Enter text to rewrite:",
+                default_text="",
+                lexer_name="markdown"  # Use markdown for general text
+            )
+        except KeyboardInterrupt:
+            print("\nOperation cancelled.")
+            sys.exit(0)
+        
+        if not text.strip():
+            print("No text entered. Exiting.")
+            sys.exit(0)
+    
+    # Initialize client
+    try:
+        config = load_config()
+        client = NGPTClient(**config)
+    except Exception as e:
+        print(f"{COLORS['yellow']}Error initializing AI client: {e}{COLORS['reset']}", 
+              file=sys.stderr)
+        sys.exit(1)
+    
+    # Style instructions
+    style_guide = {
+        "formal": "Use formal language, proper grammar, and professional tone.",
+        "casual": "Use conversational, friendly tone while improving clarity.",
+        "academic": "Use academic language with precise terminology and citations where appropriate.",
+        "creative": "Make the text more engaging and vibrant while maintaining meaning.",
+        "general": "Improve clarity and correctness while preserving the original tone."
+    }
+    
+    # System prompt for rewriting
+    system_prompt = f"""You are a text improvement assistant. 
+Rewrite the text to improve quality while preserving the original meaning and intent.
+{style_guide[args.type]}
+Focus on:
+1. Fixing grammar and spelling errors
+2. Improving clarity and readability
+3. Enhancing flow and structure
+4. Maintaining the author's voice and meaning
+Return ONLY the improved text without explanations or notes."""
+    
+    print(f"\n{COLORS['cyan']}Rewriting text ({args.type} style)...{COLORS['reset']}")
+    
+    # Process with AI
+    try:
+        if args.stream:
+            # Stream with live updates
+            if args.prettify:
+                streamer = prettify_streaming_markdown(
+                    renderer='rich',
+                    header_text="Improved Text"
+                )
+                
+                full_response = ""
+                for chunk in client.chat(
+                    text,
+                    system_prompt=system_prompt,
+                    stream=True
+                ):
+                    full_response += chunk
+                    streamer.update_content(full_response)
+                
+                improved_text = full_response
+            else:
+                # Simple streaming
+                print(f"\n{COLORS['green']}Improved Text:{COLORS['reset']}\n")
+                improved_text = ""
+                for chunk in client.chat(
+                    text,
+                    system_prompt=system_prompt,
+                    stream=True
+                ):
+                    improved_text += chunk
+                    print(chunk, end="", flush=True)
+                print()  # Final newline
+        else:
+            # Get complete response
+            improved_text = client.chat(
+                text,
+                system_prompt=system_prompt
+            )
+            
+            if args.prettify:
+                print(f"\n{COLORS['green']}Improved Text:{COLORS['reset']}\n")
+                print(prettify_markdown(improved_text))
+            else:
+                print(f"\n{COLORS['green']}Improved Text:{COLORS['reset']}\n")
+                print(improved_text)
+        
+        # Save to file if requested
+        if args.output:
+            try:
+                with open(args.output, 'w') as f:
+                    f.write(improved_text)
+                print(f"\n{COLORS['green']}Improved text saved to {args.output}{COLORS['reset']}")
+            except Exception as e:
+                print(f"{COLORS['yellow']}Error saving to file: {e}{COLORS['reset']}", 
+                      file=sys.stderr)
+    
+    except KeyboardInterrupt:
+        print("\nOperation cancelled.")
+    except Exception as e:
+        print(f"\n{COLORS['yellow']}Error: {e}{COLORS['reset']}", file=sys.stderr)
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()
+```
+
+Save this as `text-improver.py` and use it like:
+
+```bash
+# Use multiline editor for input
+python text-improver.py --type formal --prettify
+
+# Provide text directly from command line
+python text-improver.py "I aint never seen nothing like it" --type formal --prettify
+
+# Read from file and save to another file
+python text-improver.py --file rough_draft.txt --output improved.txt --type academic
+
+# Stream results with live updates
+python text-improver.py --file notes.txt --type casual --stream --prettify
+```
+
 ## Advanced CLI Configuration Example
 
 Create a CLI tool with persistent configuration:

{ngpt-2.12.0 → ngpt-2.13.0}/docs/usage/cli_framework.md

@@ -259,6 +259,7 @@ from ngpt.cli.modes.chat import chat_mode
 from ngpt.cli.modes.code import code_mode
 from ngpt.cli.modes.shell import shell_mode
 from ngpt.cli.modes.text import text_mode
+from ngpt.cli.modes.rewrite import rewrite_mode
 
 # Initialize the client
 client = NGPTClient(**load_config())
@@ -276,6 +277,10 @@ shell_mode(client, prompt="Find all PNG files in current directory")
 
 # Text mode - handle multiline text input
 text_mode(client, prettify=True)
+
+# Rewrite mode - improve text quality while preserving meaning and tone
+rewrite_mode(client, text="We was hoping you could help with this issue what we are having.", 
+             prettify=True, stream=True)
 ```
 
 Each mode handler encapsulates the specialized behavior for that particular mode of operation.