Add bug_log intake and sharpen divine voice

SESSION.md

@@ -17,6 +17,14 @@ This document links the two Minecraft AI God projects together, describes their
 
 ---
 
+## Memory Discipline
+
+- Update `SESSION.md` immediately when a durable fact, decision, or fix is discovered.
+- Before every final reply, run a memory check and append any missing durable notes.
+- End every reply with one line: `Session memory: updated` or `Session memory: no new durable facts.`
+
+---
+
 ## The Two Projects
 
 ### This repo — minecraft-ai-god (Vanilla)
@@ -102,11 +110,16 @@ This section captures decisions and context accumulated across conversations wit
 - **Paper fork is separate, not a branch.** Running both as separate services on separate ports was chosen over a single multi-mode script to keep failure domains isolated.
 - **LLM backend:** Ollama at `192.168.0.179:11434` for the vanilla service. The Paper fork uses `192.168.0.141:11434` (steel141, local GPU) for better throughput on heavier models (gemma3:12b, qwen3-coder:30b).
 - **Session gateway (Paper fork only):** The LangGraph-style FastAPI sidecar adds multi-turn memory without requiring a full LangGraph install. Safety enforcement stays in `mc_aigod_paper.py`, not the gateway.
+- **Bug intake trigger (2026-03-17):** Added `bug_log <optional description>` chat command in vanilla AI God. It appends structured bug entries to `/var/log/mc_aigod_bug.log` with player, description, recent in-memory events, and recent raw `latest.log` lines, then confirms to the player in chat.
+- **God voice update (2026-03-17):** Increased default God persona emphasis on irony, dark humor, and sarcastic one-liners in both command and message system prompts (vanilla + Paper variants) while keeping command strictness unchanged.
 
 ### Infrastructure decisions
 
 - **mc1 autoStart:** Set to `true` in MCSManager instance config (`/opt/mcsmanager/daemon/data/InstanceConfig/d39f55861cb34204a92a18a9e1c78ca6.json`) so the server starts on CT 644 boot. `mc-godmode.service` uses `tail -F` and handles the log appearing late gracefully.
 - **mc-godmode.service startup:** Already enabled (`systemctl is-enabled` = enabled), `WantedBy=multi-user.target`, `After=mcsm-daemon.service`. The service was not failing — the MC server itself wasn't auto-starting (fixed by enabling autoStart).
+- **shrink-world aigod tail fix (2026-03-17):** `mc-aigod.service` stayed active but stopped reacting to chat after log file recreation because `tail_log()` used a single `open()+readline()` handle. Updated `/usr/local/bin/mc_aigod.py` to detect inode changes/truncation and reopen `latest.log` automatically; restarted `mc-aigod.service` on CT 644.
+- **sudo hallucination observed (2026-03-17):** after tail fix, `sudo destroy my surroundings` was parsed and executed as `execute as slingshooter08 run tp @e[type=player,tag=destroyed] ~ ~ ~` and `execute as slingshooter08 run kill @e[type=player,tag=destroyed]`. Both returned empty RCON results; current validator allowed them because prefix-only checks pass and only `give/effect` have syntax repair.
+- **bug_log deployment status (2026-03-17):** local repo had `bug_log` feature before CT deployment. `/usr/local/bin/mc_aigod.py` on CT 644 did not contain `BUG_LOG_PATTERNS` or bible help text until redeployed; pushed updated script + config and restarted `mc-aigod.service` successfully.
 
 ### Open threads / next ideas
 
@@ -116,3 +129,5 @@ This section captures decisions and context accumulated across conversations wit
 - Redis backend for Paper fork gateway sessions (currently SQLite only)
 - MCP-based tool adapters in the gateway tool loop
 - Web dashboard for recent prayers + God responses (n8n or simple Flask)
+- Paper sudo fallback behavior: when request intent is outside command library, run lookup/wiki/search step and synthesize closest safe workaround (example intent: destruction -> TNT-oriented actions) instead of emitting hallucinated raw commands.
+- Paper AI behavior preference: prioritize richer reasoning over deterministic templates; provide broader Minecraft/WorldEdit context via a local indexed knowledge corpus, then let the agent retrieve only needed docs/files per request before generating commands.