Add Live Ozan Radio — DeepSeek DJ, Lyria 3, and player chat.

Personal AI station that generates tracks from taste seeds or Spotify; safe to share — secrets and cache are gitignored.

Co-authored-by: Cursor <cursoragent@cursor.com>

AGENTS.md

@@ -0,0 +1,37 @@
+# AGENTS.md — Live Ozan Radio
+
+Public demo repo under `tinqs/live-ozan-radio`. AI agents run the station — humans listen.
+
+## Identity
+
+- **No catalog playback.** Spotify is taste input only. Every track is generated.
+- **DeepSeek** plans mood + Lyria prompts. **Google Lyria 3** renders audio.
+- Respond in English.
+
+## Session start
+
+1. Read `README.md`
+2. Check `.env` exists (never commit secrets)
+3. Skill: `.cursor/skills/ozan-radio/SKILL.md`
+
+## Commands
+
+```bash
+python -m ozan_radio serve      # radio server :8787
+python -m ozan_radio generate   # one track, CLI
+curl -X POST http://127.0.0.1:8787/api/generate
+```
+
+## Keys
+
+| Key | Purpose |
+|-----|---------|
+| `GEMINI_API_KEY` | Lyria 3 |
+| `DEEPSEEK_API_KEY` | DJ brain |
+| `SPOTIFY_*` | Optional taste |
+
+## Siblings
+
+- `tinqs-ltd/docs` — hub
+- `tinqs-ltd/audio` / `music` — Ariki production audio (FMOD, stems)
+- `tinqs/studio` — inference proxy for DeepSeek