Rene Fichtmueller 998e8d8aee feat: add OpenAI/ChatGPT passthrough + per-AI savings in Overview
- New openai-proxy.ts: POST /v1/chat/completions forwards client's API key
  to OpenAI, creates tracking ticket with full cost calculation for all
  gpt-4o, gpt-4o-mini, o1, o3-mini, gpt-4-turbo, gpt-3.5-turbo models
- GET /v1/models unified in openai-proxy (removed duplicate from anthropic-proxy)
- Dashboard: POST /v1/chat/completions forwarded to core (OPENAI_BASE_URL works)
- Overview 'Savings per AI' panel: shows emoji label, request count, cost,
  tokens in/out, and savings per provider (🟣 Claude 🟢 ChatGPT 🟡 Ollama)
- Old pipeline-based proxy.ts replaced by direct API passthroughs
2026-04-14 22:55:13 +02:00
Description
Hybrid MCP + Proxy for LLM token savings
224 KiB
Languages
TypeScript 65.9%
HTML 31.3%
Shell 2%
JavaScript 0.8%