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

feat: require warning before mute + sustained toxicity escalation

Browse Source 
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>
This commit is contained in:
AJ Isaacs
2026-02-25 11:07:57 -05:00
parent f02a4ab49d
commit 71c7b45e9a
4 changed files with 56 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
cogs/sentiment.py
View File

@@ -292,7 +292,8 @@ class SentimentCog(commands.Cog):
# Track the result in DramaTracker
self.bot.drama_tracker.add_entry(user_id, score, categories, reasoning)
drama_score = self.bot.drama_tracker.get_drama_score(user_id)
escalation_boost = sentiment_config.get("escalation_boost", 0.04)
drama_score = self.bot.drama_tracker.get_drama_score(user_id, escalation_boost=escalation_boost)
logger.info(
"User %s (%d) | msg_score=%.2f | drama_score=%.2f | categories=%s | %s",
@@ -358,10 +359,16 @@ class SentimentCog(commands.Cog):
mute_threshold = self.bot.drama_tracker.get_mute_threshold(
user_id, base_mute_threshold
)
user_data = self.bot.drama_tracker.get_user(user_id)
# Mute: rolling average OR single message spike
if drama_score >= mute_threshold or score >= spike_mute:
effective_score = max(drama_score, score)
await self._mute_user(user_ref_msg, effective_score, categories, db_message_id)
if user_data.warned_since_reset:
await self._mute_user(user_ref_msg, effective_score, categories, db_message_id)
else:
# Downgrade to warning — require a warning before muting
logger.info("Downgrading mute to warning for %s (no prior warning)", user_ref_msg.author)
await self._warn_user(user_ref_msg, effective_score, db_message_id)
# Warn: rolling average OR single message spike
elif drama_score >= warning_threshold or score >= spike_warn:
effective_score = max(drama_score, score)
@@ -556,7 +563,8 @@ class SentimentCog(commands.Cog):
self._mark_analyzed(m.id)
self.bot.drama_tracker.add_entry(user_id, score, categories, reasoning)
drama_score = self.bot.drama_tracker.get_drama_score(user_id)
escalation_boost = sentiment_config.get("escalation_boost", 0.04)
drama_score = self.bot.drama_tracker.get_drama_score(user_id, escalation_boost=escalation_boost)
# Save to DB
content_summary = f"[Mention scan] {worst_msg}" if worst_msg else "[Mention scan] See conversation"
@@ -599,9 +607,14 @@ class SentimentCog(commands.Cog):
mute_threshold = self.bot.drama_tracker.get_mute_threshold(
user_id, base_mute_threshold
)
user_data = self.bot.drama_tracker.get_user(user_id)
if drama_score >= mute_threshold or score >= spike_mute:
effective_score = max(drama_score, score)
await self._mute_user(ref_msg, effective_score, categories, db_message_id)
if user_data.warned_since_reset:
await self._mute_user(ref_msg, effective_score, categories, db_message_id)
else:
logger.info("Downgrading mute to warning for %s (no prior warning)", ref_msg.author)
await self._warn_user(ref_msg, effective_score, db_message_id)
elif drama_score >= warning_threshold or score >= spike_warn:
effective_score = max(drama_score, score)
await self._warn_user(ref_msg, effective_score, db_message_id)
@@ -747,6 +760,8 @@ class SentimentCog(commands.Cog):
message_id=db_message_id,
details=f"score={score:.2f}",
))
# Persist warned flag immediately so it survives restarts
self._save_user_state(message.author.id)
async def _handle_topic_drift(
self, message: discord.Message, topic_category: str, topic_reasoning: str,
@@ -897,6 +912,7 @@ class SentimentCog(commands.Cog):
off_topic_count=user_data.off_topic_count,
baseline_coherence=user_data.baseline_coherence,
user_notes=user_data.notes or None,
warned=user_data.warned_since_reset,
))
self._dirty_users.discard(user_id)
@@ -923,6 +939,7 @@ class SentimentCog(commands.Cog):
off_topic_count=user_data.off_topic_count,
baseline_coherence=user_data.baseline_coherence,
user_notes=user_data.notes or None,
warned=user_data.warned_since_reset,
)
logger.info("Flushed %d dirty user states to DB.", len(dirty))