aj/Breehavior-Monitor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add server rule violation detection and compress prompts

Browse Source 
- LLM now evaluates messages against numbered server rules and reports
  violated_rules in analysis output
- Warnings and mutes cite the specific rule(s) broken
- Rules extracted to prompts/rules.txt for prompt injection
- Personality prompts moved to prompts/personalities/ and compressed
  (~63% reduction across all prompt files)
- All prompt files tightened: removed redundancy, consolidated Do NOT
  sections, trimmed examples while preserving behavioral instructions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
AJ Isaacs
2026-02-27 22:14:35 -05:00
parent ed51db527c
commit bf32a9536a
22 changed files with 230 additions and 293 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cogs/sentiment/__init__.py
+46 -3
View File
@@ -1,6 +1,7 @@
import asyncio
import logging
from datetime import datetime, timedelta, timezone
from pathlib import Path
import discord
@@ -18,6 +19,34 @@ logger = logging.getLogger("bcs.sentiment")
# How often to flush dirty user states to DB (seconds)
STATE_FLUSH_INTERVAL = 300 # 5 minutes
# Load server rules from prompt file (cached at import time)
_PROMPTS_DIR = Path(__file__).resolve().parent.parent.parent / "prompts"
def _load_rules() -> tuple[str, dict[int, str]]:
"""Load rules from prompts/rules.txt, returning (raw text, {num: text} dict)."""
path = _PROMPTS_DIR / "rules.txt"
if not path.exists():
return "", {}
text = path.read_text(encoding="utf-8").strip()
if not text:
return "", {}
rules_dict = {}
for line in text.splitlines():
line = line.strip()
if not line:
continue
parts = line.split(". ", 1)
if len(parts) == 2:
try:
rules_dict[int(parts[0])] = parts[1]
except ValueError:
pass
return text, rules_dict
_RULES_TEXT, _RULES_DICT = _load_rules()
class SentimentCog(commands.Cog):
def __init__(self, bot: commands.Bot):
@@ -176,20 +205,27 @@ class SentimentCog(commands.Cog):
categories: list[str],
thresholds: dict,
db_message_id: int | None,
violated_rules: list[int] | None = None,
) -> None:
"""Issue a warning or mute based on scores and thresholds."""
rules_config = _RULES_DICT
mute_threshold = self.bot.drama_tracker.get_mute_threshold(user_id, thresholds["mute"])
user_data = self.bot.drama_tracker.get_user(user_id)
if drama_score >= mute_threshold or score >= thresholds["spike_mute"]:
effective_score = max(drama_score, score)
if user_data.warned_since_reset:
await mute_user(self.bot, message, effective_score, categories, db_message_id, self._dirty_users)
await mute_user(self.bot, message, effective_score, categories, db_message_id, self._dirty_users, violated_rules=violated_rules, rules_config=rules_config)
else:
logger.info("Downgrading mute to warning for %s (no prior warning)", message.author)
await warn_user(self.bot, message, effective_score, db_message_id, self._dirty_users)
await warn_user(self.bot, message, effective_score, db_message_id, self._dirty_users, violated_rules=violated_rules, rules_config=rules_config)
elif drama_score >= thresholds["warning"] or score >= thresholds["spike_warn"]:
effective_score = max(drama_score, score)
await warn_user(self.bot, message, effective_score, db_message_id, self._dirty_users)
await warn_user(self.bot, message, effective_score, db_message_id, self._dirty_users, violated_rules=violated_rules, rules_config=rules_config)
@staticmethod
def _build_rules_context() -> str:
"""Return server rules text loaded from prompts/rules.txt."""
return _RULES_TEXT
@staticmethod
def _build_user_lookup(messages: list[discord.Message]) -> dict[str, tuple[int, discord.Message, list[discord.Message]]]:
@@ -359,6 +395,7 @@ class SentimentCog(commands.Cog):
categories = finding["categories"]
reasoning = finding["reasoning"]
off_topic = finding.get("off_topic", False)
violated_rules = finding.get("violated_rules", [])
note_update = finding.get("note_update")
# Track in DramaTracker
@@ -449,6 +486,7 @@ class SentimentCog(commands.Cog):
if not dry_run:
await self._apply_moderation(
user_ref_msg, user_id, score, drama_score, categories, thresholds, db_message_id,
violated_rules=violated_rules,
)
return (username, score, drama_score, categories)
@@ -507,6 +545,7 @@ class SentimentCog(commands.Cog):
alias_context = self._build_alias_context(all_messages, anon_map)
channel_context = build_channel_context(ref_message, game_channels)
rules_context = self._build_rules_context()
logger.info(
"Channel analysis: %d new messages (+%d context) in #%s",
@@ -521,6 +560,7 @@ class SentimentCog(commands.Cog):
user_notes_map=anon_notes,
new_message_start=new_message_start,
user_aliases=alias_context,
rules_context=rules_context,
)
if result is None:
@@ -541,6 +581,7 @@ class SentimentCog(commands.Cog):
user_notes_map=anon_notes,
new_message_start=new_message_start,
user_aliases=alias_context,
rules_context=rules_context,
)
if heavy_result is not None:
logger.info(
@@ -683,6 +724,7 @@ class SentimentCog(commands.Cog):
alias_context = self._build_alias_context(raw_messages, anon_map)
channel_context = build_channel_context(raw_messages[0], game_channels)
rules_context = self._build_rules_context()
mention_context = (
f"A user flagged this conversation and said: \"{mention_text}\"\n"
f"Pay special attention to whether this concern is valid."
@@ -695,6 +737,7 @@ class SentimentCog(commands.Cog):
channel_context=channel_context,
user_notes_map=anon_notes,
user_aliases=alias_context,
rules_context=rules_context,
)
if result is None: