lukeandClaude Opus 4.6 54ad04ae09 LLM: per-model params for caller_dialog + longer timeouts ...

Different models need different tuning for natural conversation:
Qwen gets high frequency penalty to fight repetition loops, Llama
gets warmer temp to reduce terseness, Grok/Mistral/DeepSeek/Kimi get
slightly warmer than Sonnet defaults. Bumps base httpx timeout from
10s to 30s and fallback per-call timeout from 8s to 20s.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-09 23:39:45 -06:00

..

services

LLM: per-model params for caller_dialog + longer timeouts

2026-04-09 23:39:45 -06:00

__init__.py

Initial commit: AI Radio Show web application

2026-02-04 23:11:20 -07:00

config.py

Fix tonight's show issues: Whisper bias, boring callers, Devon, short responses

2026-03-21 05:21:23 -06:00

main.py

Cost dashboard: TTS providers endpoint, header link, polish

2026-04-09 23:39:40 -06:00