ngpt 3.0.0__tar.gz → 3.0.2__tar.gz

ngpt-3.0.2/.github/workflows/aur-publish.yml

@@ -0,0 +1,40 @@
+name: Publish AUR Package
+
+on:
+  push:
+    tags:
+      - 'v*'  # Trigger on version tags
+
+jobs:
+  publish-aur:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0  # Required for accurate versioning
+
+      - name: Update version in PKGBUILD
+        run: |
+          # Extract version from tag (remove 'v' prefix)
+          VERSION=${GITHUB_REF#refs/tags/v}
+          echo "Package version: $VERSION"
+          
+          # Update version in PKGBUILD
+          sed -i "s/^pkgver=.*/pkgver=$VERSION/" PKGBUILD
+
+      - name: Publish AUR package
+        uses: KSXGitHub/github-actions-deploy-aur@v4.1.1
+        with:
+          pkgname: ngpt
+          pkgbuild: ./PKGBUILD
+          assets: |
+            LICENSE
+            README.md
+          commit_username: ${{ secrets.AUR_USERNAME }}
+          commit_email: ${{ secrets.AUR_EMAIL }}
+          ssh_private_key: ${{ secrets.AUR_SSH_PRIVATE_KEY }}
+          commit_message: "Update to version ${{ github.ref_name }}"
+          ssh_keyscan_types: rsa,ecdsa,ed25519
+          updpkgsums: true  # Let the action update checksums automatically
+          test: true  # Verify the PKGBUILD can be built 

{ngpt-3.0.0 → ngpt-3.0.2}/COMMIT_GUIDELINES.md

@@ -113,4 +113,5 @@ Also fixed that other bug people were complaining about.
 
 - [Conventional Commits](https://www.conventionalcommits.org/)
 - [How to Write a Git Commit Message](https://chris.beams.io/posts/git-commit/)
-- [A Note About Git Commit Messages](https://tbaggery.com/2008/04/19/a-note-about-git-commit-messages.html)
+- [A Note About Git Commit Messages](https://tbaggery.com/2008/04/19/a-note-about-git-commit-messages.html)
+- [GitHub Commit Labels](https://greasyfork.org/en/scripts/526153-github-commit-labels) - A userscript that adds colorful labels to conventional commits on GitHub

{ngpt-3.0.0 → ngpt-3.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ngpt
-Version: 3.0.0
+Version: 3.0.2
 Summary: Swiss army knife for LLMs: powerful CLI, interactive chatbot, and flexible Python library. Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible API.
 Project-URL: Homepage, https://github.com/nazdridoy/ngpt
 Project-URL: Repository, https://github.com/nazdridoy/ngpt
@@ -36,20 +36,52 @@ Description-Content-Type: text/markdown
 
 # nGPT
 
+<p align="center">
+  <a href="https://pypi.org/project/ngpt/"><img src="https://img.shields.io/pypi/v/ngpt.svg" alt="PyPI version"></a>
+  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
+  <a href="https://nazdridoy.github.io/ngpt/"><img src="https://img.shields.io/badge/docs-available-brightgreen.svg" alt="Documentation"></a>
+</p>
+
+<p align="center">
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/Linux-support-blue?logo=linux" alt="Linux"></a>
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/Windows-support-blue?logo=windows" alt="Windows"></a>
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/macOS-support-blue?logo=apple" alt="macOS"></a>
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/Android-Termux-blue?logo=android" alt="Android"></a>
+</p> 
+
 🤖 nGPT: A Swiss army knife for LLMs: powerful CLI, interactive chatbot, and flexible library all in one package. Seamlessly work with OpenAI, Ollama, Groq, Claude, Gemini, or any OpenAI-compatible API to generate code, craft git commits, rewrite text, and execute shell commands. Fast, lightweight, and designed for both casual users and developers.
 
-[![PyPI version](https://img.shields.io/pypi/v/ngpt.svg)](https://pypi.org/project/ngpt/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Documentation](https://img.shields.io/badge/docs-available-brightgreen.svg)](https://nazdridoy.github.io/ngpt/)
-[![Linux](https://img.shields.io/badge/Linux-support-blue?logo=linux)](https://nazdridoy.github.io/ngpt/installation.html)
-[![Windows](https://img.shields.io/badge/Windows-support-blue?logo=windows)](https://nazdridoy.github.io/ngpt/installation.html)
-[![macOS](https://img.shields.io/badge/macOS-support-blue?logo=apple)](https://nazdridoy.github.io/ngpt/installation.html)
-[![Android](https://img.shields.io/badge/Android-Termux-blue?logo=android)](https://nazdridoy.github.io/ngpt/installation.html)
-[![Python Versions](https://img.shields.io/pypi/pyversions/ngpt.svg)](https://pypi.org/project/ngpt/)
 
 ![2025-04-23_16-18-01](https://github.com/user-attachments/assets/b8e58926-5165-4352-b48b-9f4a982da86e)
 
 
+## Features
+
+- ✅ **Versatile**: Use as a CLI tool, Python library, or CLI framework for building custom tools
+- 🪶 **Lightweight**: Minimal dependencies with everything you need included
+- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any compatible endpoint
+- 💬 **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
+- 📑 **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
+- 🎭 **System Prompts**: Customize model behavior with custom system prompts
+- 📃 **Conversation Logging**: Save your conversations to text files for later reference
+- 🧰 **CLI Components**: Reusable components for building custom AI-powered command-line tools
+- 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
+- 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
+- 🚀 **Performance Optimized**: Fast response times and minimal resource usage
+
+See the [Feature Overview](https://nazdridoy.github.io/ngpt/overview.html) for more details.
+
+
 ## Table of Contents
 - [Quick Start](#quick-start)
 - [Features](#features)
@@ -172,32 +204,6 @@ ngpt --provider Ollama "Explain quantum physics" > ollama_response.txt
 
 For more examples and detailed usage, visit the [CLI Usage Guide](https://nazdridoy.github.io/ngpt/usage/cli_usage.html).
 
-## Features
-
-- ✅ **Versatile**: Use as a CLI tool, Python library, or CLI framework for building custom tools
-- 🪶 **Lightweight**: Minimal dependencies with everything you need included
-- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any compatible endpoint
-- 💬 **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
-- 📑 **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
-- 🎭 **System Prompts**: Customize model behavior with custom system prompts
-- 📃 **Conversation Logging**: Save your conversations to text files for later reference
-- 🧰 **CLI Components**: Reusable components for building custom AI-powered command-line tools
-- 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
-- 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
-- 🚀 **Performance Optimized**: Fast response times and minimal resource usage
-
-See the [Feature Overview](https://nazdridoy.github.io/ngpt/overview.html) for more details.
-
 ## Documentation
 
 Comprehensive documentation, including API reference, usage guides, and examples, is available at:
@@ -432,120 +438,160 @@ For detailed information about building CLI tools with nGPT, see the [CLI Framew
 
 ### Command Line 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 |
-| `-p, --pipe` | Read from stdin and use content with prompt. Use {} in prompt as placeholder for stdin content |
-| `-r, --rewrite` | Rewrite text to improve quality while preserving original tone and meaning |
-| `-g, --gitcommsg` | Generate AI-powered git commit messages from staged changes or diff files |
-
-#### Global Options
-
-| Option | Description |
-|--------|-------------|
-| `--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 |
-| `--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 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 |
+```console
+❯ ngpt -h
+usage: ngpt [-h] [-v] [--language LANGUAGE] [--config [CONFIG]] [--config-index CONFIG_INDEX] [--provider PROVIDER]
+            [--remove] [--show-config] [--all] [--list-models] [--list-renderers] [--cli-config [COMMAND ...]]
+            [--api-key API_KEY] [--base-url BASE_URL] [--model MODEL] [--web-search] [--temperature TEMPERATURE]
+            [--top_p TOP_P] [--max_tokens MAX_TOKENS] [--log [FILE]] [--preprompt PREPROMPT] [--no-stream] [--prettify]
+            [--stream-prettify] [--renderer {auto,rich,glow}] [--rec-chunk] [--diff [FILE]] [--chunk-size CHUNK_SIZE]
+            [--analyses-chunk-size ANALYSES_CHUNK_SIZE] [--max-msg-lines MAX_MSG_LINES]
+            [--max-recursion-depth MAX_RECURSION_DEPTH] [-i | -s | -c | -t | -p | -r | -g]
+            [prompt]
+
+nGPT - Interact with AI language models via OpenAI-compatible APIs
+
+positional arguments::
+
+[PROMPT]                            The prompt to send
+
+options::
+
+-h, --help                          show this help message and exit
+-v, --version                       Show version information and exit
+--language LANGUAGE                 Programming language to generate code in (for code mode)
+
+Configuration Options::
+
+--config [CONFIG]                   Path to a custom config file or, if no value provided, enter interactive
+                                    configuration mode to create a new config
+--config-index CONFIG_INDEX         Index of the configuration to use or edit (default: 0)
+--provider PROVIDER                 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 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)
+
+Global Options::
+
+--api-key API_KEY                   API key for the service
+--base-url BASE_URL                 Base URL for the API
+--model MODEL                       Model to use
+--web-search                        Enable web search capability (Note: Your API endpoint must support this
+                                    feature)
+--temperature TEMPERATURE           Set temperature (controls randomness, default: 0.7)
+--top_p TOP_P                       Set top_p (controls diversity, default: 1.0)
+--max_tokens MAX_TOKENS             Set max response length in tokens
+--log [FILE]                        Set filepath to log conversation to, or create a temporary log file if no path
+                                    provided
+--preprompt PREPROMPT               Set custom system prompt to control AI behavior
+--no-stream                         Return the whole response without streaming
+--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 (auto, rich, or glow)
+
+Git Commit Message Options::
+
+--rec-chunk                         Process large diffs in chunks with recursive analysis if needed
+--diff [FILE]                       Use diff from specified file instead of staged changes. If used without a path,
+                                    uses the path from CLI config.
+--chunk-size CHUNK_SIZE             Number of lines per chunk when chunking is enabled (default: 200)
+--analyses-chunk-size ANALYSES_CHUNK_SIZE
+                                    Number of lines per chunk when recursively chunking analyses (default: 200)
+--max-msg-lines MAX_MSG_LINES       Maximum number of lines in commit message before condensing (default: 20)
+--max-recursion-depth MAX_RECURSION_DEPTH
+                                    Maximum recursion depth for commit message condensing (default: 3)
+
+Modes (mutually exclusive)::
+
+-i, --interactive                   Start an interactive chat session
+-s, --shell                         Generate and execute shell commands
+-c, --code                          Generate code
+-t, --text                          Enter multi-line text input (submit with Ctrl+D)
+-p, --pipe                          Read from stdin and use content with prompt. Use {} in prompt as placeholder
+                                    for stdin content
+-r, --rewrite                       Rewrite text from stdin to be more natural while preserving tone and meaning
+-g, --gitcommsg                     Generate AI-powered git commit messages from staged changes or diff file
+```
+
+> **Note**: For better visualization of conventional commit messages on GitHub, you can use the [GitHub Commit Labels](https://greasyfork.org/en/scripts/526153-github-commit-labels) userscript, which adds colorful labels to your commits.
 
 For a complete reference of all available options, see the [CLI Usage Guide](https://nazdridoy.github.io/ngpt/usage/cli_usage.html).
 
 ### CLI Configuration
 
-NGPT offers a CLI configuration system that allows you to set default values for command-line options:
-
-```bash
-# Set default options
-ngpt --cli-config set language typescript
-ngpt --cli-config set temperature 0.9
-ngpt --cli-config set prettify true
-
-# View current settings
-ngpt --cli-config get
-
-# Get a specific setting
-ngpt --cli-config get language
-
-# Remove a setting
-ngpt --cli-config unset prettify
+NGPT offers a CLI configuration system that allows you to set default values for command-line options. This is especially useful when you:
+
+- Repeatedly use the same provider or model
+- Have preferred settings for specific tasks
+- Want to create different workflows based on context
+
+For example, setting your preferred language for code generation or temperature value means you won't have to specify these parameters each time:
+
+```console
+
+❯ ngpt --cli-config help
+
+CLI Configuration Help:
+  Command syntax:
+    ngpt --cli-config help                - Show this help message
+    ngpt --cli-config set OPTION VALUE    - Set a default value for OPTION
+    ngpt --cli-config get OPTION          - Get the current value of OPTION
+    ngpt --cli-config get                 - Show all CLI configuration settings
+    ngpt --cli-config unset OPTION        - Remove OPTION from configuration
+    ngpt --cli-config list                - List all available options
+
+  Available options:
+    General options (all modes):
+      config-index - int (default: 0) [exclusive with: provider]
+      log - str 
+      max_tokens - int 
+      no-stream - bool (default: False) [exclusive with: prettify, stream-prettify]
+      preprompt - str 
+      prettify - bool (default: False) [exclusive with: no-stream, stream-prettify]
+      provider - str  [exclusive with: config-index]
+      renderer - str (default: auto)
+      stream-prettify - bool (default: False) [exclusive with: no-stream, prettify]
+      temperature - float (default: 0.7)
+      top_p - float (default: 1.0)
+      web-search - bool (default: False)
+
+    Options for Code generation mode:
+      language - str (default: python)
+
+    Options for Git commit message mode:
+      analyses-chunk-size - int (default: 200)
+      chunk-size - int (default: 200)
+      diff - str 
+      max-msg-lines - int (default: 20)
+      max-recursion-depth - int (default: 3)
+      rec-chunk - bool (default: False)
+
+  Example usage:
+    ngpt --cli-config set language java        - Set default language to java for code generation
+    ngpt --cli-config set provider Gemini      - Set Gemini as your default provider
+    ngpt --cli-config set temperature 0.9      - Set default temperature to 0.9
+    ngpt --cli-config set no-stream true       - Disable streaming by default
+    ngpt --cli-config set recursive-chunk true - Enable recursive chunking for git commit messages
+    ngpt --cli-config set diff /path/to/file.diff - Set default diff file for git commit messages
+    ngpt --cli-config get temperature          - Check the current temperature setting
+    ngpt --cli-config get                      - Show all current CLI settings
+    ngpt --cli-config unset language           - Remove language setting
+
+  Notes:
+    - CLI configuration is stored in:
+      • Linux: ~/.config/ngpt/ngpt-cli.conf
+      • macOS: ~/Library/Application Support/ngpt/ngpt-cli.conf
+      • Windows: %APPDATA%\ngpt\ngpt-cli.conf
+    - Settings are applied based on context (e.g., language only applies to code generation mode)
+    - Command-line arguments always override CLI configuration
+    - Some options are mutually exclusive and will not be applied together
 
-# List all available options
-ngpt --cli-config list
-
-# Show help information
-ngpt --cli-config help
-```
-
-Key features of CLI configuration:
-- **Context-Aware**: Settings are applied based on the current command mode (e.g., `language` only applies in code generation mode `-c`).
-- **Priority**: When determining option values, NGPT uses the following priority order (highest to lowest):
-  1. Command-line arguments
-  2. Environment variables
-  3. CLI configuration (ngpt-cli.conf)
-  4. Main configuration file (ngpt.conf)
-  5. Default values
-- **Mutual Exclusivity**: For options like `no-stream`, `prettify`, and `stream-prettify`, setting one to `True` automatically sets the others to `False` in the configuration file, ensuring consistency.
-- **Smart Selection**: The `provider` setting is used to select which configuration profile to use, offering a persistent way to select your preferred API.
-
-Available options include:
-- General options (all modes): `provider`, `temperature`, `top_p`, `max_tokens`, `preprompt`, `renderer`, `config-index`, `web-search`
-- Mode-specific options: `language` (code mode only), `log` (interactive and text modes)
-- Mutually exclusive options: `no-stream`, `prettify`, `stream-prettify`
-
-#### Practical Examples
-
-```bash
-# Set Gemini as your default provider
-ngpt --cli-config set provider Gemini
-# Now you can run commands without specifying --provider
-ngpt "Explain quantum computing"
-
-# Configure code generation for TypeScript
-ngpt --cli-config set language typescript
-# Now in code mode, TypeScript will be used by default
-ngpt -c "Write a function to sort an array"
-
-# Set a higher temperature for more creative responses
-ngpt --cli-config set temperature 0.9
 ```
 
-The CLI configuration is stored in:
-- Linux: `~/.config/ngpt/ngpt-cli.conf`
-- macOS: `~/Library/Application Support/ngpt/ngpt-cli.conf`
-- Windows: `%APPDATA%\ngpt\ngpt-cli.conf`
-
 For more details, see the [CLI Configuration Guide](https://nazdridoy.github.io/ngpt/usage/cli_config.html).
 
 ### Interactive Configuration
@@ -642,4 +688,4 @@ Please check the [CONTRIBUTING.md](CONTRIBUTING.md) file for detailed guidelines
 
 ## License
 
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

ngpt-3.0.2/PKGBUILD

@@ -0,0 +1,24 @@
+# Maintainer: nazdridoy <nazdridoy399@gmail.com>
+pkgname=ngpt
+pkgver=0.0.0  # Automatically updated by CI on release
+pkgrel=1
+pkgdesc="Swiss army knife for LLMs: powerful CLI, interactive chatbot, and flexible Python library. Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible API."
+arch=('any')
+url="https://github.com/nazdridoy/ngpt"
+license=('MIT')
+depends=('python' 'python-requests>=2.31.0' 'python-rich>=10.0.0' 'python-prompt_toolkit>=3.0.0' 'python-pyperclip>=1.8.0')
+makedepends=('python-build' 'python-installer' 'python-wheel' 'python-hatchling')
+source=("${pkgname}-${pkgver}.tar.gz::https://github.com/nazdridoy/${pkgname}/archive/v${pkgver}.tar.gz")
+sha256sums=('SKIP')  # Automatically updated by CI on release
+
+build() {
+  cd "$pkgname-$pkgver"
+  python -m build --wheel --no-isolation
+}
+
+package() {
+  cd "$pkgname-$pkgver"
+  python -m installer --destdir="$pkgdir" dist/*.whl
+  install -Dm644 LICENSE "$pkgdir/usr/share/licenses/$pkgname/LICENSE"
+  install -Dm644 README.md "$pkgdir/usr/share/doc/$pkgname/README.md"
+}

{ngpt-3.0.0 → ngpt-3.0.2}/README.md

@@ -1,19 +1,51 @@
 # nGPT
 
+<p align="center">
+  <a href="https://pypi.org/project/ngpt/"><img src="https://img.shields.io/pypi/v/ngpt.svg" alt="PyPI version"></a>
+  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
+  <a href="https://nazdridoy.github.io/ngpt/"><img src="https://img.shields.io/badge/docs-available-brightgreen.svg" alt="Documentation"></a>
+</p>
+
+<p align="center">
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/Linux-support-blue?logo=linux" alt="Linux"></a>
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/Windows-support-blue?logo=windows" alt="Windows"></a>
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/macOS-support-blue?logo=apple" alt="macOS"></a>
+  <a href="https://nazdridoy.github.io/ngpt/installation.html"><img src="https://img.shields.io/badge/Android-Termux-blue?logo=android" alt="Android"></a>
+</p> 
+
 🤖 nGPT: A Swiss army knife for LLMs: powerful CLI, interactive chatbot, and flexible library all in one package. Seamlessly work with OpenAI, Ollama, Groq, Claude, Gemini, or any OpenAI-compatible API to generate code, craft git commits, rewrite text, and execute shell commands. Fast, lightweight, and designed for both casual users and developers.
 
-[![PyPI version](https://img.shields.io/pypi/v/ngpt.svg)](https://pypi.org/project/ngpt/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Documentation](https://img.shields.io/badge/docs-available-brightgreen.svg)](https://nazdridoy.github.io/ngpt/)
-[![Linux](https://img.shields.io/badge/Linux-support-blue?logo=linux)](https://nazdridoy.github.io/ngpt/installation.html)
-[![Windows](https://img.shields.io/badge/Windows-support-blue?logo=windows)](https://nazdridoy.github.io/ngpt/installation.html)
-[![macOS](https://img.shields.io/badge/macOS-support-blue?logo=apple)](https://nazdridoy.github.io/ngpt/installation.html)
-[![Android](https://img.shields.io/badge/Android-Termux-blue?logo=android)](https://nazdridoy.github.io/ngpt/installation.html)
-[![Python Versions](https://img.shields.io/pypi/pyversions/ngpt.svg)](https://pypi.org/project/ngpt/)
 
 ![2025-04-23_16-18-01](https://github.com/user-attachments/assets/b8e58926-5165-4352-b48b-9f4a982da86e)
 
 
+## Features
+
+- ✅ **Versatile**: Use as a CLI tool, Python library, or CLI framework for building custom tools
+- 🪶 **Lightweight**: Minimal dependencies with everything you need included
+- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any compatible endpoint
+- 💬 **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
+- 📑 **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
+- 🎭 **System Prompts**: Customize model behavior with custom system prompts
+- 📃 **Conversation Logging**: Save your conversations to text files for later reference
+- 🧰 **CLI Components**: Reusable components for building custom AI-powered command-line tools
+- 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
+- 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
+- 🚀 **Performance Optimized**: Fast response times and minimal resource usage
+
+See the [Feature Overview](https://nazdridoy.github.io/ngpt/overview.html) for more details.
+
+
 ## Table of Contents
 - [Quick Start](#quick-start)
 - [Features](#features)
@@ -136,32 +168,6 @@ ngpt --provider Ollama "Explain quantum physics" > ollama_response.txt
 
 For more examples and detailed usage, visit the [CLI Usage Guide](https://nazdridoy.github.io/ngpt/usage/cli_usage.html).
 
-## Features
-
-- ✅ **Versatile**: Use as a CLI tool, Python library, or CLI framework for building custom tools
-- 🪶 **Lightweight**: Minimal dependencies with everything you need included
-- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any compatible endpoint
-- 💬 **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
-- 📑 **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
-- 🎭 **System Prompts**: Customize model behavior with custom system prompts
-- 📃 **Conversation Logging**: Save your conversations to text files for later reference
-- 🧰 **CLI Components**: Reusable components for building custom AI-powered command-line tools
-- 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
-- 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
-- 🚀 **Performance Optimized**: Fast response times and minimal resource usage
-
-See the [Feature Overview](https://nazdridoy.github.io/ngpt/overview.html) for more details.
-
 ## Documentation
 
 Comprehensive documentation, including API reference, usage guides, and examples, is available at:
@@ -396,120 +402,160 @@ For detailed information about building CLI tools with nGPT, see the [CLI Framew
 
 ### Command Line 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 |
-| `-p, --pipe` | Read from stdin and use content with prompt. Use {} in prompt as placeholder for stdin content |
-| `-r, --rewrite` | Rewrite text to improve quality while preserving original tone and meaning |
-| `-g, --gitcommsg` | Generate AI-powered git commit messages from staged changes or diff files |
-
-#### Global Options
-
-| Option | Description |
-|--------|-------------|
-| `--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 |
-| `--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 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 |
+```console
+❯ ngpt -h
+usage: ngpt [-h] [-v] [--language LANGUAGE] [--config [CONFIG]] [--config-index CONFIG_INDEX] [--provider PROVIDER]
+            [--remove] [--show-config] [--all] [--list-models] [--list-renderers] [--cli-config [COMMAND ...]]
+            [--api-key API_KEY] [--base-url BASE_URL] [--model MODEL] [--web-search] [--temperature TEMPERATURE]
+            [--top_p TOP_P] [--max_tokens MAX_TOKENS] [--log [FILE]] [--preprompt PREPROMPT] [--no-stream] [--prettify]
+            [--stream-prettify] [--renderer {auto,rich,glow}] [--rec-chunk] [--diff [FILE]] [--chunk-size CHUNK_SIZE]
+            [--analyses-chunk-size ANALYSES_CHUNK_SIZE] [--max-msg-lines MAX_MSG_LINES]
+            [--max-recursion-depth MAX_RECURSION_DEPTH] [-i | -s | -c | -t | -p | -r | -g]
+            [prompt]
+
+nGPT - Interact with AI language models via OpenAI-compatible APIs
+
+positional arguments::
+
+[PROMPT]                            The prompt to send
+
+options::
+
+-h, --help                          show this help message and exit
+-v, --version                       Show version information and exit
+--language LANGUAGE                 Programming language to generate code in (for code mode)
+
+Configuration Options::
+
+--config [CONFIG]                   Path to a custom config file or, if no value provided, enter interactive
+                                    configuration mode to create a new config
+--config-index CONFIG_INDEX         Index of the configuration to use or edit (default: 0)
+--provider PROVIDER                 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 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)
+
+Global Options::
+
+--api-key API_KEY                   API key for the service
+--base-url BASE_URL                 Base URL for the API
+--model MODEL                       Model to use
+--web-search                        Enable web search capability (Note: Your API endpoint must support this
+                                    feature)
+--temperature TEMPERATURE           Set temperature (controls randomness, default: 0.7)
+--top_p TOP_P                       Set top_p (controls diversity, default: 1.0)
+--max_tokens MAX_TOKENS             Set max response length in tokens
+--log [FILE]                        Set filepath to log conversation to, or create a temporary log file if no path
+                                    provided
+--preprompt PREPROMPT               Set custom system prompt to control AI behavior
+--no-stream                         Return the whole response without streaming
+--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 (auto, rich, or glow)
+
+Git Commit Message Options::
+
+--rec-chunk                         Process large diffs in chunks with recursive analysis if needed
+--diff [FILE]                       Use diff from specified file instead of staged changes. If used without a path,
+                                    uses the path from CLI config.
+--chunk-size CHUNK_SIZE             Number of lines per chunk when chunking is enabled (default: 200)
+--analyses-chunk-size ANALYSES_CHUNK_SIZE
+                                    Number of lines per chunk when recursively chunking analyses (default: 200)
+--max-msg-lines MAX_MSG_LINES       Maximum number of lines in commit message before condensing (default: 20)
+--max-recursion-depth MAX_RECURSION_DEPTH
+                                    Maximum recursion depth for commit message condensing (default: 3)
+
+Modes (mutually exclusive)::
+
+-i, --interactive                   Start an interactive chat session
+-s, --shell                         Generate and execute shell commands
+-c, --code                          Generate code
+-t, --text                          Enter multi-line text input (submit with Ctrl+D)
+-p, --pipe                          Read from stdin and use content with prompt. Use {} in prompt as placeholder
+                                    for stdin content
+-r, --rewrite                       Rewrite text from stdin to be more natural while preserving tone and meaning
+-g, --gitcommsg                     Generate AI-powered git commit messages from staged changes or diff file
+```
+
+> **Note**: For better visualization of conventional commit messages on GitHub, you can use the [GitHub Commit Labels](https://greasyfork.org/en/scripts/526153-github-commit-labels) userscript, which adds colorful labels to your commits.
 
 For a complete reference of all available options, see the [CLI Usage Guide](https://nazdridoy.github.io/ngpt/usage/cli_usage.html).
 
 ### CLI Configuration
 
-NGPT offers a CLI configuration system that allows you to set default values for command-line options:
-
-```bash
-# Set default options
-ngpt --cli-config set language typescript
-ngpt --cli-config set temperature 0.9
-ngpt --cli-config set prettify true
-
-# View current settings
-ngpt --cli-config get
-
-# Get a specific setting
-ngpt --cli-config get language
-
-# Remove a setting
-ngpt --cli-config unset prettify
+NGPT offers a CLI configuration system that allows you to set default values for command-line options. This is especially useful when you:
+
+- Repeatedly use the same provider or model
+- Have preferred settings for specific tasks
+- Want to create different workflows based on context
+
+For example, setting your preferred language for code generation or temperature value means you won't have to specify these parameters each time:
+
+```console
+
+❯ ngpt --cli-config help
+
+CLI Configuration Help:
+  Command syntax:
+    ngpt --cli-config help                - Show this help message
+    ngpt --cli-config set OPTION VALUE    - Set a default value for OPTION
+    ngpt --cli-config get OPTION          - Get the current value of OPTION
+    ngpt --cli-config get                 - Show all CLI configuration settings
+    ngpt --cli-config unset OPTION        - Remove OPTION from configuration
+    ngpt --cli-config list                - List all available options
+
+  Available options:
+    General options (all modes):
+      config-index - int (default: 0) [exclusive with: provider]
+      log - str 
+      max_tokens - int 
+      no-stream - bool (default: False) [exclusive with: prettify, stream-prettify]
+      preprompt - str 
+      prettify - bool (default: False) [exclusive with: no-stream, stream-prettify]
+      provider - str  [exclusive with: config-index]
+      renderer - str (default: auto)
+      stream-prettify - bool (default: False) [exclusive with: no-stream, prettify]
+      temperature - float (default: 0.7)
+      top_p - float (default: 1.0)
+      web-search - bool (default: False)
+
+    Options for Code generation mode:
+      language - str (default: python)
+
+    Options for Git commit message mode:
+      analyses-chunk-size - int (default: 200)
+      chunk-size - int (default: 200)
+      diff - str 
+      max-msg-lines - int (default: 20)
+      max-recursion-depth - int (default: 3)
+      rec-chunk - bool (default: False)
+
+  Example usage:
+    ngpt --cli-config set language java        - Set default language to java for code generation
+    ngpt --cli-config set provider Gemini      - Set Gemini as your default provider
+    ngpt --cli-config set temperature 0.9      - Set default temperature to 0.9
+    ngpt --cli-config set no-stream true       - Disable streaming by default
+    ngpt --cli-config set recursive-chunk true - Enable recursive chunking for git commit messages
+    ngpt --cli-config set diff /path/to/file.diff - Set default diff file for git commit messages
+    ngpt --cli-config get temperature          - Check the current temperature setting
+    ngpt --cli-config get                      - Show all current CLI settings
+    ngpt --cli-config unset language           - Remove language setting
+
+  Notes:
+    - CLI configuration is stored in:
+      • Linux: ~/.config/ngpt/ngpt-cli.conf
+      • macOS: ~/Library/Application Support/ngpt/ngpt-cli.conf
+      • Windows: %APPDATA%\ngpt\ngpt-cli.conf
+    - Settings are applied based on context (e.g., language only applies to code generation mode)
+    - Command-line arguments always override CLI configuration
+    - Some options are mutually exclusive and will not be applied together
 
-# List all available options
-ngpt --cli-config list
-
-# Show help information
-ngpt --cli-config help
-```
-
-Key features of CLI configuration:
-- **Context-Aware**: Settings are applied based on the current command mode (e.g., `language` only applies in code generation mode `-c`).
-- **Priority**: When determining option values, NGPT uses the following priority order (highest to lowest):
-  1. Command-line arguments
-  2. Environment variables
-  3. CLI configuration (ngpt-cli.conf)
-  4. Main configuration file (ngpt.conf)
-  5. Default values
-- **Mutual Exclusivity**: For options like `no-stream`, `prettify`, and `stream-prettify`, setting one to `True` automatically sets the others to `False` in the configuration file, ensuring consistency.
-- **Smart Selection**: The `provider` setting is used to select which configuration profile to use, offering a persistent way to select your preferred API.
-
-Available options include:
-- General options (all modes): `provider`, `temperature`, `top_p`, `max_tokens`, `preprompt`, `renderer`, `config-index`, `web-search`
-- Mode-specific options: `language` (code mode only), `log` (interactive and text modes)
-- Mutually exclusive options: `no-stream`, `prettify`, `stream-prettify`
-
-#### Practical Examples
-
-```bash
-# Set Gemini as your default provider
-ngpt --cli-config set provider Gemini
-# Now you can run commands without specifying --provider
-ngpt "Explain quantum computing"
-
-# Configure code generation for TypeScript
-ngpt --cli-config set language typescript
-# Now in code mode, TypeScript will be used by default
-ngpt -c "Write a function to sort an array"
-
-# Set a higher temperature for more creative responses
-ngpt --cli-config set temperature 0.9
 ```
 
-The CLI configuration is stored in:
-- Linux: `~/.config/ngpt/ngpt-cli.conf`
-- macOS: `~/Library/Application Support/ngpt/ngpt-cli.conf`
-- Windows: `%APPDATA%\ngpt\ngpt-cli.conf`
-
 For more details, see the [CLI Configuration Guide](https://nazdridoy.github.io/ngpt/usage/cli_config.html).
 
 ### Interactive Configuration
@@ -606,4 +652,4 @@ Please check the [CONTRIBUTING.md](CONTRIBUTING.md) file for detailed guidelines
 
 ## License
 
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

{ngpt-3.0.0 → ngpt-3.0.2}/docs/examples/basic.md

@@ -283,6 +283,8 @@ ngpt -g --diff changes.diff
 ngpt -g --log commit_debug.log
 ```
 
+> **Tip**: For better visualization of conventional commit messages on GitHub, you can use the [GitHub Commit Labels](https://greasyfork.org/en/scripts/526153-github-commit-labels) userscript, which adds colorful labels to your commits.
+
 ## Using CLI Config
 
 nGPT supports persistent CLI configuration for setting default values:

{ngpt-3.0.0 → ngpt-3.0.2}/docs/usage/cli_usage.md

@@ -450,6 +450,8 @@ When a commit message is successfully generated, the tool attempts to copy it to
 
 For detailed documentation on git commit message generation, see the [Git Commit Message Guide](gitcommsg.md).
 
+> **Tip**: For better visualization of conventional commit messages on GitHub, you can use the [GitHub Commit Labels](https://greasyfork.org/en/scripts/526153-github-commit-labels) userscript, which adds colorful labels to your commits.
+
 ### Generating Code
 
 Generate clean code without markdown or explanations:

{ngpt-3.0.0 → ngpt-3.0.2}/docs/usage/gitcommsg.md

@@ -352,6 +352,26 @@ The generated commit messages include:
 3. Brief summary
 4. Detailed bullet points with file and function references
 
+## GitHub Visualization
+
+The conventional commit messages generated by `--gitcommsg` work great with GitHub, but you can enhance the visualization further with the **GitHub Commit Labels** userscript.
+
+This userscript automatically adds beautiful colored labels for conventional commit types, making your commit history more readable and visually appealing.
+
+### Installation and Features
+
+1. Install a userscript manager like Tampermonkey for your browser
+2. Install the [GitHub Commit Labels](https://greasyfork.org/en/scripts/526153-github-commit-labels) userscript
+
+Key features:
+- Adds colored labels to conventional commit messages
+- Supports all standard commit types (feat, fix, docs, etc.)
+- Works with GitHub's light, dark, and dark dimmed themes
+- Adds helpful tooltips showing detailed descriptions
+- Highlights breaking changes using `type!:` or `type(scope)!:`
+
+The userscript automatically detects the conventional commit format produced by `ngpt --gitcommsg`, enhancing the readability of your commit history on GitHub.
+
 ## Logging
 
 To debug issues or review the AI's analysis process, use the `--log` option:

{ngpt-3.0.0 → ngpt-3.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ngpt"
-version = "3.0.0"
+version = "3.0.2"
 description = "Swiss army knife for LLMs: powerful CLI, interactive chatbot, and flexible Python library. Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible API."
 authors = [
     {name = "nazDridoy", email = "nazdridoy399@gmail.com"},

{ngpt-3.0.0 → ngpt-3.0.2}/uv.lock

@@ -134,7 +134,7 @@ wheels = [
 
 [[package]]
 name = "ngpt"
-version = "3.0.0"
+version = "3.0.2"
 source = { editable = "." }
 dependencies = [
     { name = "prompt-toolkit" },