Suppai_NekoandDadBot 2001c25bb6 Merge dolphin-mistral: background model split, logging, semaphore, cooldowns, prompt updates
- Structured logging with timestamps and per-task prefixes ([agent], [dossier], etc.)
- Background LLM semaphore to prevent concurrent background calls
- 120s cooldown after background task failures
- 90s timeout on background LLM calls to prevent deadlocks
- BACKGROUND_MODEL env var to use a separate model for dossier/compaction tasks
- Strip <think> tags from model responses (Qwen compat)
- Prompt: read the room for dynamic mood adaptation
- Prompt: blunt one-line self-correction, no apologies
- Prompt: more aggressive stance, never fold under pressure
- Updated personality.txt: less people-pleasing, more authentic

Co-Authored-By: DadBot <dadbot@localhost>
2026-03-18 15:01:30 -07:00
S
Description
Discord bot running a LLM backend
132 KiB
0 Stars 1 Watchers 0 Forks
Languages
Python 99.6%
Dockerfile 0.4%