Files

T

Tao Yang 960d0d1f23 feat: extract models from command-code dist, load via models.json

- Add scripts/extract-models.ts to parse command-code npm dist file
- Generate models.json (21 models, 15 pricing entries) with contextWindow
  and maxOutputTokens pre-filled; no nulls or hardcoded fallbacks in index.ts
- Rewrite index.ts to load model list and costs from models.json
- Cap gateway model maxOutputTokens at 65536 (API limit for Baseten/Vercel)
- Add 'Update models' section to README documenting the generation flow
- Add npm run extract-models script

2026-05-25 16:37:08 +08:00

3.8 KiB

Raw Blame History

pi-commandcode-provider

A pi custom provider that connects pi to the Command Code API.

Disclaimer: This is an unofficial, community-maintained package. I am not affiliated with, endorsed by, or connected to Command Code in any way. This provider simply forwards requests to the public Command Code API using your own API key.

Note: This package only provides a model provider. It does not include an API key. You must bring your own Command Code API key or subscription.

💰 Current offer: Command Code offers 4× usage of DeepSeek V4 (Pro and Flash) at no extra cost.

Models

18 models across premium and open-source providers:

Category	Models
Anthropic	Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5
OpenAI	GPT-5.5, GPT-5.4, GPT-5.3 Codex, GPT-5.4 Mini
Open-source	DeepSeek V4, DeepSeek V4 Pro, DeepSeek V4 Flash, Kimi K2.6, Kimi K2.5, GLM-5.1, GLM-5, MiniMax M2.7, MiniMax M2.5, Qwen 3.6 Max, Qwen 3.6 Plus

Install

pi install npm:pi-commandcode-provider

Or shorthand:

pi install pi-commandcode-provider

Then reload pi:

/reload

Setup

Set your Command Code API key using one of these methods:

In pi, run:

/login

Then select Command Code from the provider list.

This opens Command Code in your browser and stores the returned API key in pi's auth file. If the browser shows "Copy your API key" because automatic transfer failed, copy that key and paste it into the pi terminal prompt.

Note: /login commandcode is not supported by pi currently; use interactive /login and select Command Code.

2. Environment variable

export COMMANDCODE_API_KEY="user_..."

3. Auth file

Create ~/.commandcode/auth.json:

{
  "apiKey": "user_..."
}

Or use pi's auth file at ~/.pi/agent/auth.json:

{
  "commandcode": "user_..."
}

Usage

After installing and setting your API key, select a Command Code model in pi:

/model deepseek/deepseek-v4-flash

Any query will then use the Command Code API. You can list available models:

pi -e index.ts --list-models

Or within pi:

/models

Update models

The model list (models.json) is extracted from the command-code npm package's dist file. When Command Code releases a new version with updated models, regenerate it:

npm run extract-models

This runs scripts/extract-models.ts, which:

Downloads the latest command-code tarball from npm (npm pack command-code)
Parses the minified dist/index.mjs to extract provider definitions, model metadata, and pricing
Fills in contextWindow and maxOutputTokens with sensible defaults where the CLI omits them
Writes the result to models.json

To use a specific version or local dist file:

npx tsx scripts/extract-models.ts /path/to/command-code/dist/index.mjs

models.json is committed to the repo and included in the npm package.

Publish

npm login
npm publish --access public

License

MIT

3.8 KiB Raw Blame History Unescape Escape