finish/USAGE.md

Usage Guide

Installation

Install and set up finishte:

finishte install
source ~/.bashrc

Configuration

View current settings:

finishte config

Change settings:

finishte config set temperature 0.5
finishte config set endpoint http://localhost:1234/v1/chat/completions
finishte config set model your-model-name

Reset to defaults:

finishte config reset

Model Selection

Select a model interactively:

finishte model

Use arrow keys to navigate, Enter to select, or 'q' to quit.

Basic Commands

Show help:

finishte --help

Test completions without caching:

finishte command "your command here"

Preview the prompt sent to the model:

finishte command --dry-run "your command here"

View system information:

finishte system

Usage Statistics

Check your usage stats and costs:

finishte usage

Cache Management

Clear cached completions and logs:

finishte clear

Enable/Disable

Temporarily disable:

finishte disable

Re-enable:

finishte enable

Uninstallation

Remove finishte completely:

finishte remove

Using finishte

Once enabled, just type a command and press Tab twice to get suggestions:

git <TAB><TAB>
docker <TAB><TAB>
find <TAB><TAB>

Natural language also works:

# convert video to mp4 <TAB><TAB>
# list all processes using port 8080 <TAB><TAB>
# compress this folder to tar.gz <TAB><TAB>

Configuration File

The config file is located at ~/.finishte/config and contains:

• provider: Model provider (lmstudio, ollama)
• model: Model name
• temperature: Response randomness (0.0 - 1.0)
• endpoint: API endpoint URL
• api_prompt_cost: Cost per input token
• api_completion_cost: Cost per output token
• max_history_commands: Number of recent commands to include in context
• max_recent_files: Number of recent files to include in context
• cache_dir: Directory for cached completions
• cache_size: Maximum number of cached items
• log_file: Path to usage log file