AJ Isaacs b410200146 Add max_tokens=1024 to LLM analysis calls ...

The analyze_message and raw_analyze methods had no max_tokens limit,
causing thinking models (Qwen3-VL-32B-Thinking) to generate unlimited
reasoning tokens before responding — taking 5+ minutes per message.

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

2026-02-21 14:17:59 -05:00

..

__init__.py

Initial commit: Breehavior Monitor Discord bot

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

database.py

Initial commit: Breehavior Monitor Discord bot

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

drama_tracker.py

Initial commit: Breehavior Monitor Discord bot

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

llm_client.py

Add max_tokens=1024 to LLM analysis calls

2026-02-21 14:17:59 -05:00