Log every LLM call (analysis, chat, image, raw_analyze) to a new
LlmLog table with request type, model, token counts, duration,
success/failure, and truncated request/response payloads. Enables
debugging prompt issues and tracking usage.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When the LLM is offline, post to #bcs-log instead of sending
the "brain offline" message in chat.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- spike_mute: 0.8→0.7, mute: 0.75→0.65 so escalating users get
timed out after a warning instead of endlessly warned
- Skip debounce on @mentions so sentiment analysis fires immediately
- Chat cog awaits pending sentiment analysis before replying,
ensuring warnings/mutes appear before the personality response
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Send last ~8 messages from all users (not just others) as a
multi-line chat log with relative timestamps so the LLM can
better understand conversation flow and escalation patterns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
Buffer messages per user+channel and wait for a configurable window
(batch_window_seconds: 3) before analyzing. Combines burst messages
into a single LLM call instead of analyzing each one separately.
Replaces cooldown_between_analyses with the debounce approach.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Detect when users discuss a game in the wrong channel (e.g. GTA talk
in #warzone) and send a friendly redirect to the correct channel.
Also add sexual_vulgar category and scoring rules so crude sexual
remarks directed at someone aren't softened by "lmao".
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When @mentioned with an image attachment, the bot now roasts players
based on scoreboard screenshots using the vision model. Text-only
mentions continue to work as before.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sends a minimal 1-token completion during setup_hook so the model is
ready before Discord messages start arriving, avoiding connection
errors and slow first responses after a restart.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
- Serialize all LLM requests through an asyncio semaphore to prevent
overloading athena with concurrent requests
- Switch chat() to streaming so the typing indicator only appears once
the model starts generating (not during thinking/loading)
- Increase LLM timeout from 5 to 10 minutes for slow first loads
- Rename ollama_client.py to llm_client.py and self.ollama to self.llm
since the bot uses a generic OpenAI-compatible API
- Update embed labels from "Ollama" to "LLM"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move the analysis and chat personality system prompts from inline Python
strings to prompts/analysis.txt and prompts/chat_personality.txt for
easier editing. Also add a rule so users quoting/reporting what someone
else said are not penalized for the quoted words.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The ODBC driver failed to load at runtime because libgssapi_krb5.so.2
was not installed. Add it explicitly to the apt-get install step.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Discord bot for monitoring chat sentiment and tracking drama using
Ollama LLM on athena.lan. Includes sentiment analysis, slash commands,
drama tracking, and SQL Server persistence via Docker Compose.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
