@senomas/proxy-provider

A pi-coding-agent extension that registers a deepseek provider via a configurable AI proxy.

What it does

This package extends pi with a provider named "deepseek". On every session:

1. Walks up from the current directory looking for .pi-project.json
2. Reads the project and proxy fields from that file
3. Fetches model definitions from ${proxy}/static/providers/deepseek.json
4. Registers the provider with the proxy as baseUrl and the project name as the AI-Proxy-Project header

Prerequisites

• Node.js 18+ (for global fetch)
• pi-coding-agent installed (npm install -g @earendil-works/pi-coding-agent)

Installation

pi install npm:@senomas/proxy-provider

Configuration

Create a .pi-project.json file in your project root:

{
  "project": "my-project",
  "proxy": "https://deepseek-proxy-dev.senomas.com"
}

| Field | Type | Description | |-------|------|-------------| | project | string | Project name sent as the AI-Proxy-Project header | | proxy | string | Base URL of the AI proxy server |

Verification

After installation, list available models to confirm the provider is registered:

pi --list-models | grep deepseek

You should see the deepseek models exposed by your proxy.

How it works

The extension exports an async default function that:

1. Uses fs.existsSync and fs.readFileSync (Node built-ins) to find and parse .pi-project.json
2. Calls fetch() to retrieve provider metadata from the proxy
3. Calls pi.registerProvider("deepseek", config) with the fetched models, proxy baseUrl, and AI-Proxy-Project header

License

MIT