AJ Isaacs 942f5ddce7 Fix repetitive roast responses with anti-repetition mechanisms ...

Add frequency_penalty (0.8) and presence_penalty (0.6) to LLM chat
calls to discourage repeated tokens. Inject the bot's last 5 responses
into the system prompt so the model knows what to avoid. Strengthen
the roast prompt with explicit anti-repetition rules and remove example
lines the model was copying verbatim ("Real ___ energy", etc.).

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

2026-02-23 15:15:11 -05:00

..

__init__.py

Initial commit: Breehavior Monitor Discord bot

2026-02-20 22:39:40 -05:00

database.py

Persist bot mode across restarts via database

2026-02-23 09:26:00 -05:00

drama_tracker.py

Simplify user notes trimming to keep last 10 lines

2026-02-22 23:43:36 -05:00

llm_client.py

Fix repetitive roast responses with anti-repetition mechanisms

2026-02-23 15:15:11 -05:00