AJ Isaacs b9bac899f9 Add two-tier LLM analysis with triage/escalation ...

Triage model (LLM_MODEL) handles every message cheaply. If toxicity
>= 0.25, off_topic, or coherence < 0.6, the message is re-analyzed
with the heavy model (LLM_ESCALATION_MODEL). Chat, image analysis,
/bcs-test, and /bcs-scan always use the heavy model.

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

2026-02-21 18:33:36 -05:00

..

__init__.py

Initial commit: Breehavior Monitor Discord bot

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

chat.py

Add two-tier LLM analysis with triage/escalation

2026-02-21 18:33:36 -05:00

commands.py

Add two-tier LLM analysis with triage/escalation

2026-02-21 18:33:36 -05:00

sentiment.py

Add two-tier LLM analysis with triage/escalation

2026-02-21 18:33:36 -05:00