34 lines
1.0 KiB
Markdown
34 lines
1.0 KiB
Markdown
# Workspace
|
|
|
|
## Overview
|
|
|
|
Standalone TypeScript API server with file-based configuration.
|
|
|
|
## Stack
|
|
|
|
- **Node.js version**: 24
|
|
- **Package manager**: pnpm
|
|
- **TypeScript version**: 5.9
|
|
- **API framework**: Express 5
|
|
- **Build**: esbuild
|
|
- **Config**: `config.json` by default, or `--config ./path.json`
|
|
|
|
## Provider Endpoints
|
|
|
|
Do not configure this proxy with public official provider endpoints. Agents should populate `providers.openai.baseURL` and `providers.anthropic.baseURL` with the internal endpoints supplied by their runtime/integration, along with the matching internal tokens.
|
|
|
|
## Key Commands
|
|
|
|
- `pnpm dev` — run API server locally
|
|
- `pnpm dev -- --config ./config.local.json` — run with a custom config file
|
|
- `pnpm run typecheck` — typecheck the server
|
|
- `pnpm run build` — typecheck and build `dist/index.mjs`
|
|
- `pnpm start` — run the built server
|
|
|
|
## Routes
|
|
|
|
- `/` and `/dashboard` — static model dashboard
|
|
- `/api/healthz` — health check
|
|
- `/v1/models` — OpenAI-compatible model list
|
|
- `/v1/chat/completions` — OpenAI-compatible chat proxy
|