michaellee8/esp32-bluetooth-voice-agent ? reverse-engineered prompt

Build me an experimental ESP32 voice agent that pairs with a phone or tablet like a Bluetooth headset, so the phone can send and receive live voice through the board. I want the ESP32 to advertise as a hands free device, automatically connect, and route the audio over the local network to a small Go bridge on my laptop or home server. The bridge should handle the voice session, signaling, basic status pages, and keep a local SQLite history of activity. If it helps, use current docs online for the ESP32 and WebRTC pieces.

Please also add a simple optional OLED status screen for WiFi, Bluetooth, call, and agent state, plus a clean way to set WiFi and bridge settings in local config files. I’d like the project to build and run from the repo with clear setup steps, including the firmware and the bridge. Make it work with the tested ESP32 Audio Kit style hardware and keep the code organized so I can flash it, start the bridge, and test the whole flow end to end.