kibin/LexAI

Fork 0

Files

john kevin asprec 2c00d2e431

CI — Test & Build / Test & Build (pull_request) Has been cancelled

Details

Preview — PR Build Check / PR Preview Build (pull_request) Has been cancelled

Details

feat(cli): add initial CLI implementation with argument parsing and prompt handling

- Created package.json and package-lock.json for CLI package.
- Implemented argument parsing in args.ts to handle various flags and commands.
- Developed main CLI logic in cli.ts to execute commands and handle errors.
- Added configuration loading from a JSON file in config.ts, with environment variable support.
- Implemented prompt resolution and provider interaction in prompt.ts.
- Added usage documentation for the CLI.
- Configured TypeScript settings in tsconfig.json for the CLI package.
- Updated README in vscode package to reflect the new CLI functionality.
- Refactored root tsconfig.json to streamline project structure.

2026-08-13 19:19:42 +08:00

2.3 KiB

Raw Blame History

LexAI CLI — Prompt Builder

Part of the LexAI monorepo (packages/cli). Complements the Chrome and VS Code packages.

Improve a rough idea into a paste-ready engineered prompt before you fire it at Claude Code, Cursor, or another agent.

BYO-LLM only — no LexAI servers. Uses the same Prompt Builder core as the Chrome and VS Code extensions.

Install (from this repo)

# from repo root
npm run cli:install
npm run cli:build

# make `lexai` available on your PATH
cd packages/cli && npm link

Or run without linking:

node packages/cli/out/cli.js prompt "your rough idea"

Setup

# PowerShell
$env:LEXAI_API_KEY = "sk-..."
$env:LEXAI_PROVIDER = "openai"   # optional: openai | anthropic | groq | openrouter
$env:LEXAI_MODEL = "gpt-4o"      # optional

Optional defaults file (no API key allowed here): ~/.lexai/config.json

{
  "provider": "openai",
  "model": "gpt-4o",
  "pattern": "role",
  "persona": "Expert Developer",
  "format": "Markdown",
  "style": "Concise"
}

Precedence: flags > config file > env > defaults. Key is always from LEXAI_API_KEY.

Usage

lexai prompt "add rate limiting to the express auth routes"

echo "debug flaky playwright on CI" | lexai prompt --pattern role --persona "Expert Developer"

lexai prompt -f draft.txt --format Markdown --model gpt-4o

lexai prompt --list
lexai prompt --help

The engineered prompt is written to stdout (pipe-safe). Progress and errors go to stderr.

# Windows: copy to clipboard
lexai prompt "write a unit test for parseConfig" | Set-Clipboard

Flags

Flag	Meaning
`-f, --file <path>`	Read input from file
`--pattern <id>`	Pattern id (`auto`, `role`, `cot`, …) — see `--list`
`--persona <name\|text>`	Persona preset or free text
`--format <name>`	Output format hint
`--style <name>`	Style the engineered prompt should request
`--provider` / `--model`	Provider overrides
`-l, --list`	List patterns, personas, formats, styles
`-h, --help`	Help

Exit codes: 0 success · 1 user/config error · 2 provider/network error

Scope

In: Make Prompt / Prompt Builder only.
Out: Fix/Rephrase/Code Assist, reading VS Code/Chrome keys, auto-running shell commands.

2.3 KiB Raw Blame History