Files
claude-central-gateway/.claude/memory/implementation_plan.md
tiennm99 bfb936ae4a feat: Implement OpenAI proxy with streaming support
- Add main proxy endpoint (api/v1/messages.js)
- Add token validation via GATEWAY_TOKEN
- Add model mapping via MODEL_MAP env var
- Support full SSE streaming in Anthropic format
- Add package.json with openai dependency
- Add vercel.json for routing config
- Update README with Quick Start guide
- Consolidate memory to .claude/memory/

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 22:47:38 +07:00

1.4 KiB

name, description, type
name description type
Implementation Plan Architecture and design decisions for Claude Central Gateway project

Claude Central Gateway - Implementation

Why: A lightweight proxy for Claude Code that routes requests to third-party API providers, deployable to Vercel without needing a VPS.

Architecture

Claude Code → Gateway (Vercel) → OpenAI API
                ↓
         Validate token
         Transform request
         Stream response

Key Decisions

  • Language: Node.js with JavaScript (no TypeScript)
  • Deployment: Vercel serverless functions
  • Providers: OpenAI first (via official SDK), others in TODO
  • Config: Environment variables only (no database)
  • Auth: Single shared token (user's ANTHROPIC_AUTH_TOKEN must match GATEWAY_TOKEN)
  • Streaming: Full streaming support
  • Model mapping: Via MODEL_MAP env var (format: claude:openai,claude2:openai2)

Environment Variables

Variable Description
GATEWAY_TOKEN Shared token for authentication
OPENAI_API_KEY OpenAI API key
MODEL_MAP Model name mapping (optional)

File Structure

api/v1/messages.js  - Main proxy handler
package.json        - Dependencies (openai SDK)
vercel.json         - Routing config

How to apply: When adding new providers or modifying the gateway, follow the established pattern in api/v1/messages.js for request/response transformation.