New personality mode with 25% reply chance, very relaxed moderation
thresholds (0.85/0.90), suggestive but not explicit personality.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Queries Messages, AnalysisResults, and Actions tables to rank users by a
composite drama score (weighted avg toxicity, peak toxicity, and action rate).
Public command with configurable time period (7d/30d/90d/all-time).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
9-task step-by-step plan covering DB schema, LLM extraction tool, memory
retrieval/injection in chat, sentiment pipeline routing, background pruning,
and migration script.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Outlines persistent memory system for making the bot a real conversational
participant that knows people and remembers past interactions. Uses existing
UserNotes column for permanent profiles and a new UserMemory table for
expiring context with LLM-assigned lifetimes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
