luke 390f138601 Devon improvements: independent audio, realism overhaul ...

- Devon audio independent of caller hangup (separate stop events)
- Personal anecdotes capped at ~30% of responses (was every time)
- Interjection criteria tightened ("default is silence")
- Devon sees his own recent history to avoid repeating info
- Response variety: permits minimal reactions, confusion, silence
- Monitor prompt rewritten to be gatekeeping, not encouraging

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

2026-03-21 02:08:22 -06:00

..

__init__.py

Initial commit: AI Radio Show web application

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

audio.py

Devon improvements: independent audio, realism overhaul

2026-03-21 02:08:22 -06:00

avatars.py

Fix avatar misgendering, returning caller overflow, false callbacks

2026-03-21 02:03:07 -06:00

caller_service.py

Add show improvement features: crossfade, emotions, returning callers, transcripts, screening

2026-02-07 02:43:01 -07:00

cost_tracker.py

Caller model routing — cycle, style-matched, mid-show override

2026-03-21 01:58:03 -06:00

edge_tts_service.py

Initial commit: AI Radio Show web application

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

intern.py

Devon improvements: independent audio, realism overhaul

2026-03-21 02:08:22 -06:00

llm.py

Caller model routing — cycle, style-matched, mid-show override

2026-03-21 01:58:03 -06:00

news.py

Add topic callers, town knowledge, dynamic response lengths

2026-02-07 00:14:38 -07:00

piper_tts.py

Initial commit: AI Radio Show web application

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

regulars.py

Fix avatar misgendering, returning caller overflow, false callbacks

2026-03-21 02:03:07 -06:00

stem_recorder.py

Full app audit: 24 fixes across backend, frontend, infra, content, social

2026-03-18 14:57:50 -06:00

transcription.py

Upgrade Whisper to distil-large-v3, fix caller identity confusion, sort clips list

2026-03-05 12:46:51 -07:00

tts.py

Cost monitoring, PTT fix, Devon tuning, WEIRD pool expansion, YT thumbnails, LLM SEO, publish ep37

2026-03-15 05:33:27 -06:00

voices.py

Initial commit: AI Radio Show web application

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