hobokenchicken 92250a668b fix: restore full WebSocket message loop in main.py (was truncated to 77 lines, missing the entire try/except message handler) ...

The REST STT revert commit (0e74a16) deleted lines 78-262 including the message loop, identify handler, audio handler, text handler, and disconnect cleanup. This caused the WS to accept then immediately close, triggering a reconnect loop.

Refactored for clarity: transcribe_audio(), get_kira_response(), stream_tts() as standalone async helpers. Full pipeline restored.

2026-06-05 02:10:41 -04:00

..

models

init: Kira — AI body double with Honcho memory

2026-06-04 10:51:38 -04:00

routers

init: Kira — AI body double with Honcho memory

2026-06-04 10:51:38 -04:00

services

clean: archive legacy stt/tts/llm services; update ARCHITECTURE.md + README.md to current stack (REST gpt-4o-transcribe, nano, sage, Honcho, incremental TTS, white noise)

2026-06-04 15:54:12 -04:00

__init__.py

init: Kira — AI body double with Honcho memory

2026-06-04 10:51:38 -04:00

config.py

init: Kira — AI body double with Honcho memory

2026-06-04 10:51:38 -04:00

Dockerfile

init: Kira — AI body double with Honcho memory

2026-06-04 10:51:38 -04:00

main.py

fix: restore full WebSocket message loop in main.py (was truncated to 77 lines, missing the entire try/except message handler)

2026-06-05 02:10:41 -04:00

requirements.txt

feat: OpenAI Realtime API pipeline

2026-06-04 13:32:39 -04:00