Breehavior-Monitor

Go to file

AJ Isaacs 7db7a4b026 Tell roast prompt not to fabricate leaderboards or stats

The model was inventing rankings and scoreboards from the drama score
metadata. Explicitly tell it not to make up stats it doesn't have.

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

2026-02-23 18:43:36 -05:00

cogs

Trim prompts for gpt-4o-mini, remove disagreement detection

2026-02-23 16:26:44 -05:00

prompts

Tell roast prompt not to fabricate leaderboards or stats

2026-02-23 18:43:36 -05:00

scripts

Add announce script for posting to Discord channels

2026-02-23 10:11:27 -05:00

utils

Trim prompts for gpt-4o-mini, remove disagreement detection

2026-02-23 16:26:44 -05:00

.env.example

Support hybrid LLM: local Qwen triage + OpenAI escalation

2026-02-23 12:20:07 -05:00

.gitignore

Initial commit: Breehavior Monitor Discord bot

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

bot.py

Use gpt-4o-mini for chat/roasts via dedicated LLM_CHAT_MODEL

2026-02-23 16:04:55 -05:00

CLAUDE.md

Add CLAUDE.md with deployment instructions

2026-02-21 17:09:19 -05:00

config.yaml

Tune english teacher to catch more errors, bump roast reply chance

2026-02-23 11:03:03 -05:00

docker-compose.yml

Initial commit: Breehavior Monitor Discord bot

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

Dockerfile

Fix missing libgssapi-krb5-2 dependency in Docker image

2026-02-20 22:48:15 -05:00

requirements.txt

Initial commit: Breehavior Monitor Discord bot

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