Some documentation update

Author: gcclinux

README.md

@@ -26,6 +26,7 @@ Quick overview of current menu shotcuts and key combinations
 - **Keyboard Shortcuts**: Efficient keyboard-driven workflow
 - **Session Management**: Unsaved changes confirmation on exit
 - **Cross-Platform**: Runs on Linux, Windows, and macOS
+- **Language Support**: Shell, Bash, Python, Go, Markdown
 
 ## Integrated Git Operations
 
@@ -109,12 +110,6 @@ When the Commit button is selected:
 - **Repository Detection**: Automatically detects if current directory is a Git repository
 - **Cross-Platform**: Works consistently on Linux, Windows, and macOS
 
-### Keyboard Shortcut
-
-| Shortcut | Action |
-|----------|--------|
-| `Ctrl+G` | Open/Close Git Operations Panel |
-
 ### Technical Details
 
 The Git integration uses:
@@ -163,91 +158,6 @@ Your file is marked as modified but not automatically saved, giving you full con
 - `/config` - Edit configuration settings interactively
 - `/help` - Display keyboard shortcuts and agent commands
 
-### Usage Examples
-
-#### Basic Fix Request
-
-```
-You: fix the syntax error on line 15
-```
-
-The AI detects "fix" keyword, reads your file, identifies the syntax error, and applies the correction.
-
-#### Using /fix Command
-
-```
-You: /fix add error handling to the main function
-```
-
-Explicitly requests agentic mode. The AI adds error handling code to your main function.
-
-#### Using /ask Command
-
-```
-You: /ask how does this function work?
-```
-
-Explicitly requests conversational mode. The AI explains the function without modifying code.
-
-#### Using /preview Command
-
-```
-You: /preview refactor this to use a switch statement
-```
-
-The AI shows you what changes it would make before applying them. You can then approve or request modifications.
-
-#### Using /model Command
-
-```
-You: /model
-```
-
-The AI displays the current agent (ollama or gemini) and model being used (e.g., llama2, gemini-2.5-flash-lite). If using Gemini, it also displays the API key from the configuration.
-
-#### Using /config Command
-
-```
-You: /config
-```
-
-Opens an interactive configuration editor where you can modify settings without leaving the application:
-- Navigate fields with Up/Down or K/J keys
-- Press Enter to edit a field value
-- Press Enter again to save the edited value
-- Press Esc to save all changes and exit config mode
-
-The configuration is saved to `~/.ti/config.json` and applied immediately without restarting the application.
-
-#### Using /help Command
-
-```
-You: /help
-```
-
-The AI displays a comprehensive help message including:
-- All keyboard shortcuts (same as Ctrl+H)
-- Agent commands (/fix, /ask, /preview, /model, /config, /help)
-- Fix keywords (fix, change, update, modify, correct) with descriptions
-
-You can also press Ctrl+H at any time to see the help dialog with all keyboard shortcuts and agent commands organized by category.
-
-#### Multiple Changes
-
-```
-You: update the function to handle edge cases and add comments
-```
-
-The AI applies multiple changes in a single operation: adds edge case handling and documentation comments.
-
-### What Gets Modified
-
-- The AI only modifies the currently open file in the editor
-- Changes are applied immediately and visible in the editor
-- The file is marked as modified (indicated in the UI)
-- You must save manually with `Ctrl+S` to persist changes
-- You can undo changes using standard editor undo mechanisms
-
 ### Best Practices
 
 1. **Be Specific**: Clearly describe what you want to change
@@ -276,18 +186,12 @@ The AI handles errors gracefully:
 ### Supported File Types
 
 Agentic code fixing works with:
-- Bash scripts (`.sh`, `.bash`)
-- Shell scripts (`.sh`)
+- Shell scripts (`.sh`, `.bash`)
 - PowerShell scripts (`.ps1`)
 - Python scripts (`.py`)
 - Go source files (`.go`)
 - Markdown documents (`.md`)
 
-## Requirements
-
-- Go 1.21 or higher
-- Ollama (optional, for AI features)
-
 ## Installation
 
 ### From Source
@@ -297,15 +201,6 @@ Agentic code fixing works with:
 git clone https://github.com/user/terminal-intelligence.git
 cd terminal-intelligence
 
-# Build the application
-make linux
-```
-
-### Compile in windows
-```powershell
- .\build.ps1 windows
-```
-
 ### Pre-built Binaries
 
 Download pre-built binaries for your platform from the releases page.
@@ -337,7 +232,7 @@ You can edit this file to customize your settings. The application will load it
 ```json
 {
   "agent": "gemini",
-  "model": "gemini-3-flash-lite",
+  "model": "gemini-3.1-flash-lite",
   "ollama_url": "",
   "gemini_api": "your-api-key-here",
   "workspace": "/home/user/project-workspace"
@@ -390,81 +285,11 @@ make windows    # Build for Windows
 make darwin     # Build for macOS
 ```
 
-This generates a coverage report in `coverage.html`.
-
-## Architecture
-
-The application follows a clean architecture with clear separation of concerns:
-
-- **UI Layer**: Bubble Tea components for terminal interface
-- **Business Logic**: File management, command execution, AI communication
-- **Data Layer**: File system operations
-
-### Key Components
-
-- **App**: Main Bubble Tea application orchestrating all components
-- **EditorPane**: Code editor with syntax highlighting and file editing
-- **AIChatPane**: AI interaction pane with conversation history
-- **FileManager**: Handles all file system operations
-- **CommandExecutor**: Executes system commands and scripts
-- **OllamaClient**: Communicates with Ollama service via REST API
-
-## Configuration
-
-The application can be configured via:
-
-1. **Configuration file** at `~/.ti/config.json` (loaded automatically if present)
-2. **Command-line flags** (override config file values)
-3. **Default configuration** (used when no config file or flags provided)
-
-### Configuration Priority
-
-Command-line flags > Config file > Built-in defaults
-
-### Default Configuration
-
-- **Workspace Directory**: `~/ti-workspace`
-- **Ollama URL**: `http://localhost:11434`
-- **Default Model**: `llama2`
-- **Tab Size**: 4 spaces
-- **Auto Save**: Disabled
-
-## Cross-Platform Support
-
-The application is designed to run on:
-- **Linux**: Tested on Ubuntu 20.04+
-- **Windows**: Tested on Windows 10+
-- **macOS**: Tested on macOS 11+ (Intel and Apple Silicon)
-
-## Development
-
-### Prerequisites
-
-- Go 1.21 or higher
-- Make (for build automation)
-- golangci-lint (optional, for linting)
-
-### Development Commands
-
-```bash
-make fmt        # Format code
-make lint       # Run linter
-make run        # Build and run
-make clean      # Clean build artifacts
-```
-
-## Contributing
-
-Contributions are welcome! Please ensure:
-
-1. All tests pass (`make test`)
-2. Code is formatted (`make fmt`)
-3. Linter passes (`make lint`)
-4. New features include tests
+- [TI Architecture](./docs/ARCHITECTURE.md) - Overal Architectore overview of Terminal Intelligence (TI)
 
 ## License
 
-TBD
+MIT
 
 ## Acknowledgments
 

docs/ARCHITECTURE.md

@@ -0,0 +1,69 @@
+## Architecture
+
+The application follows a clean architecture with clear separation of concerns:
+
+- **UI Layer**: Bubble Tea components for terminal interface
+- **Business Logic**: File management, command execution, AI communication
+- **Data Layer**: File system operations
+
+### Key Components
+
+- **App**: Main Bubble Tea application orchestrating all components
+- **EditorPane**: Code editor with syntax highlighting and file editing
+- **AIChatPane**: AI interaction pane with conversation history
+- **FileManager**: Handles all file system operations
+- **CommandExecutor**: Executes system commands and scripts
+- **OllamaClient**: Communicates with Ollama service via REST API
+
+## Configuration
+
+The application can be configured via:
+
+1. **Configuration file** at `~/.ti/config.json` (loaded automatically if present)
+2. **Command-line flags** (override config file values)
+3. **Default configuration** (used when no config file or flags provided)
+
+### Configuration Priority
+
+Command-line flags > Config file > Built-in defaults
+
+### Default Configuration
+
+- **Workspace Directory**: `~/ti-workspace`
+- **Ollama URL**: `http://localhost:11434`
+- **Default Model**: `llama2`
+- **Tab Size**: 4 spaces
+- **Auto Save**: Disabled
+
+## Cross-Platform Support
+
+The application is designed to run on:
+- **Linux**: Tested on Ubuntu 20.04+
+- **Windows**: Tested on Windows 10+
+- **macOS**: Tested on macOS 11+ (Intel and Apple Silicon)
+
+## Development
+
+### Prerequisites
+
+- Go 1.21 or higher
+- Make (for build automation)
+- golangci-lint (optional, for linting)
+
+### Development Commands
+
+```bash
+make fmt        # Format code
+make lint       # Run linter
+make run        # Build and run
+make clean      # Clean build artifacts
+```
+
+## Contributing
+
+Contributions are welcome! Please ensure:
+
+1. All tests pass (`make test`)
+2. Code is formatted (`make fmt`)
+3. Linter passes (`make lint`)
+4. New features include tests

main.go

@@ -11,7 +11,7 @@ import (
 	"github.com/user/terminal-intelligence/internal/ui"
 )
 
-var version = "0.0.1.0"
+var version = "0.0.2.3"
 
 // Build number (injected at compile time via -ldflags)
 var buildNumber = "dev"