Merge worktree: adds _extract_and_save_memories() method and fire-and-forget
extraction call after each chat reply. Combined with Task 4's memory
retrieval and injection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Display names like "Calm your tits" were causing the LLM to inflate toxicity
scores on completely benign messages. Usernames are now replaced with User1,
User2, etc. before sending to the LLM, then mapped back to real names in the
results.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Convert cogs/sentiment.py (1050 lines) into cogs/sentiment/ package:
- __init__.py (656 lines): core SentimentCog with new _process_finding()
that deduplicates the per-user finding loop from _process_buffered and
_run_mention_scan (~90 lines each → single shared method)
- actions.py: mute_user, warn_user
- topic_drift.py: handle_topic_drift
- channel_redirect.py: handle_channel_redirect, build_channel_context
- coherence.py: handle_coherence_alert
- log_utils.py: log_analysis, log_action, score_color
- state.py: save_user_state, flush_dirty_states
All extracted modules use plain async functions (not methods) receiving
bot/config as parameters. Named log_utils.py to avoid shadowing stdlib
logging. Also update CLAUDE.md with comprehensive project documentation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The conversation analysis was re-scoring old messages alongside new ones,
causing users to get penalized repeatedly for already-scored messages.
A "--- NEW MESSAGES ---" separator now marks which messages are new, and
the prompt instructs the LLM to score only those. Also fixes bot-mention
detection to require an explicit @mention in message text rather than
treating reply-pings as scans (so toxic replies to bot warnings aren't
silently skipped).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
last_offense_time was in-memory only — lost on restart, so the
offense_reset_minutes check never fired after a reboot. Now persisted
as LastOffenseAt FLOAT in UserState. On startup hydration, stale
offenses (and warned flag) are auto-cleared if the reset window has
passed. Bumped offense_reset_minutes from 2h to 24h.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gate mutes behind a prior warning — first offense always gets a warning,
mute only fires if warned_since_reset is True. Warned flag is persisted
to DB (new Warned column on UserState) and survives restarts.
Add post-warning escalation boost to drama_score: each high-scoring
message after a warning adds +0.04 (configurable) so sustained bad
behavior ramps toward the mute threshold instead of plateauing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Switch from per-user message batching to per-channel conversation
analysis. The LLM now sees the full interleaved conversation with
relative timestamps, reply chains, and consecutive message collapsing
instead of isolated flat text per user.
Key changes:
- Fix gpt-5-nano temperature incompatibility (conditional temp param)
- Add mention-triggered scan: users @mention bot to analyze recent chat
- Refactor debounce buffer from (channel_id, user_id) to channel_id
- Replace per-message analyze_message() with analyze_conversation()
returning per-user findings from a single LLM call
- Add CONVERSATION_TOOL schema with coherence, topic, and game fields
- Compact message format: relative timestamps, reply arrows (→),
consecutive same-user message collapsing
- Separate mention scan tasks from debounce tasks
- Remove _store_context/_get_context (conversation block IS the context)
- Escalation timeout config: [30, 60, 120, 240] minutes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add ignored_channels config to topic_drift section, supporting
channel names or IDs. General channel excluded from off-topic
warnings while still receiving full moderation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Slim down chat_roast.txt — remove anti-repetition rules that were
compensating for the local model (gpt-4o-mini handles this natively).
Remove disagreement detection from analysis prompt, tool schema, and
sentiment handler. Saves ~200 tokens per analysis call.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a separate llm_chat client so chat responses use a smarter model
(gpt-4o-mini) while analysis stays on the cheap local Qwen3-8B.
Falls back to llm_heavy if LLM_CHAT_MODEL is not set.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The model dumps paraphrased context and style labels in [brackets]
before its actual roast. Instead of just removing bracket lines
(which leaves the preamble text), split on them and keep only the
last non-empty segment — the real answer is always last.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The model paraphrases injected metadata in unpredictable ways, so
targeted regexes can't keep up. Replace them with a single rule: any
[bracketed block] on its own line gets removed, since real roasts
never use standalone brackets.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add frequency_penalty (0.8) and presence_penalty (0.6) to LLM chat
calls to discourage repeated tokens. Inject the bot's last 5 responses
into the system prompt so the model knows what to avoid. Strengthen
the roast prompt with explicit anti-repetition rules and remove example
lines the model was copying verbatim ("Real ___ energy", etc.).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When the bot replies (proactive or mentioned), it now fetches the
user's drama tracker notes and their last ~10 messages in the channel.
Gives the LLM real context for personalized replies instead of
generic roasts on bare pings.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Proactive replies used channel.send() which posted standalone messages
with no visual link to what triggered them. Now all replies use
message.reply() so the response is always attached to the source message.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Send as a channel message instead of message.reply() so it doesn't
look like the bot is talking to itself.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reply to any message + @bot to have the bot read and respond to it.
Also picks up image attachments from referenced messages so users
can reply to a photo with "@bot roast this".
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The prompt was scoreboard-only, so selfies got nonsensical stat-based
roasts. Now the LLM identifies what's in the image and roasts accordingly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. Broader regex to strip leaked metadata even when the LLM drops
the "Server context:" prefix but keeps the content.
2. Skip sentiment analysis for messages that mention or reply to
the bot. Users interacting with the bot in roast/chat modes
shouldn't have those messages inflate their drama score.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When someone reacts to the bot's message, there's a 50% chance it
fires back with a reply commenting on their emoji choice, in
character for the current mode.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The local LLM was echoing back [Server context: ...] metadata lines
in its responses despite prompt instructions not to. Now stripped
via regex before sending to Discord.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a user replies to the bot's message, the original bot message
text is now included in the context sent to the LLM. This prevents
the LLM from misinterpreting follow-up questions like "what does
this even mean?" since it can see what message is being referenced.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a BotSettings key-value table. The active mode is saved
when changed via /bcs-mode and restored on startup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
LLM analysis now detects when two users are in a genuine
disagreement. When detected, the bot creates a native Discord
poll with each user's position as an option.
- Disagreement detection added to LLM analysis tool schema
- Polls last 4 hours with 1 hour per-channel cooldown
- LLM extracts topic, both positions, and usernames
- Configurable via polls section in config.yaml
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a server-wide mode system with /bcs-mode command.
- Default: current hall-monitor behavior unchanged
- Chatty: friendly chat participant with proactive replies (~10% chance)
- Roast: savage roast mode with proactive replies
- Chatty/roast use relaxed moderation thresholds
- 5-message cooldown between proactive replies per channel
- Bot status updates to reflect active mode
- /bcs-status shows current mode and effective thresholds
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Only inject drama score/offense context when values are noteworthy
(score >= 0.2 or offenses > 0). Update personality prompt to avoid
harping on zero scores and vary responses more.
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>
- 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>
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>
