luke 73129374f4 Bake news context into caller backgrounds at pickup time ...

Instead of injecting research into every LLM call (which bloated prompts
and caused timeouts), do one quick SearXNG search when a caller is picked
up and add a relevant headline to their background. 3s timeout — if search
is slow, caller just doesn't reference news. Zero impact on live conversation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-06 21:47:46 -07:00

backend

Bake news context into caller backgrounds at pickup time

2026-02-06 21:47:46 -07:00

frontend

Fix AI caller hanging on 'thinking...' indefinitely

2026-02-06 21:16:15 -07:00

functions

Add banner, Apple Podcasts link, feed proxy, and fetch retry

2026-02-06 14:03:29 -07:00

tests

Update tests for SignalWire phone caller format

2026-02-05 17:47:50 -07:00

website

Add ads system, diversify callers, update website descriptions

2026-02-06 20:38:25 -07:00

.gitignore

Initial commit: AI Radio Show web application

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

audio_settings.json

Improve SignalWire streaming, randomize caller names, update frontend

2026-02-06 01:56:05 -07:00

CLAUDE.md

Add CLAUDE.md with project config and Gitea setup

2026-02-04 23:21:50 -07:00

download_sounds.py

Initial commit: AI Radio Show web application

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

generate_callers.py

Initial commit: AI Radio Show web application

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

generate_sounds.py

Initial commit: AI Radio Show web application

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

publish_episode.py

Fix LLM model list, Castopod API, and server runner

2026-02-06 01:56:09 -07:00

radio_show.py

Initial commit: AI Radio Show web application

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

radio_simple.py

Initial commit: AI Radio Show web application

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

requirements-web.txt

Initial commit: AI Radio Show web application

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

run.sh

Fix LLM model list, Castopod API, and server runner

2026-02-06 01:56:09 -07:00

test.html

Initial commit: AI Radio Show web application

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

S

Description

AI Radio Show - web-based podcast production with multiple TTS providers

MIT 18 MiB

Languages

Python 80.1%

JavaScript 6.8%

HTML 6.4%

CSS 3.9%

Lua 2.4%

Other 0.4%