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

feat: add warning expiration and exclude moderated messages from context

Browse Source 
Warning flag now auto-expires after a configurable duration
(warning_expiration_minutes, default 30m). After expiry, the user must
be re-warned before a mute can be issued.

Messages that triggered moderation actions (warnings/mutes) are now
excluded from the LLM context window in both buffered analysis and
mention scans, preventing already-actioned content from influencing
future scoring. Uses in-memory tracking plus bot reaction fallback
for post-restart coverage.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
AJ Isaacs
2026-02-28 13:39:49 -05:00
parent 36df4cf5a6
commit eb7eb81621
6 changed files with 86 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
cogs/sentiment/__init__.py
View File

@@ -66,6 +66,7 @@ class SentimentCog(commands.Cog):
self._mention_scan_results: dict[int, str] = {} # {trigger_message_id: findings_summary}
self._analyzed_message_ids: set[int] = set() # Discord message IDs already analyzed
self._max_analyzed_ids = 500
self._moderated_message_ids: set[int] = set() # Message IDs that triggered moderation
async def cog_load(self):
@@ -206,21 +207,24 @@ class SentimentCog(commands.Cog):
thresholds: dict,
db_message_id: int | None,
violated_rules: list[int] | None = None,
) -> None:
"""Issue a warning or mute based on scores and thresholds."""
) -> bool:
"""Issue a warning or mute based on scores and thresholds.
Returns True if any moderation action was taken."""
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:
if self.bot.drama_tracker.is_warned(user_id):
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, violated_rules=violated_rules, rules_config=rules_config)
return True
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, violated_rules=violated_rules, rules_config=rules_config)
return True
return False
@staticmethod
def _build_rules_context() -> str:
@@ -484,10 +488,14 @@ class SentimentCog(commands.Cog):
# Moderation
if not dry_run:
await self._apply_moderation(
acted = await self._apply_moderation(
user_ref_msg, user_id, score, drama_score, categories, thresholds, db_message_id,
violated_rules=violated_rules,
)
if acted:
for m in user_msgs:
self._moderated_message_ids.add(m.id)
self._prune_moderated_ids()
return (username, score, drama_score, categories)
@@ -514,11 +522,13 @@ class SentimentCog(commands.Cog):
oldest_buffered = messages[0]
history_messages: list[discord.Message] = []
try:
async for msg in channel.history(limit=context_count + 5, before=oldest_buffered):
async for msg in channel.history(limit=context_count + 10, before=oldest_buffered):
if msg.author.bot:
continue
if not msg.content or not msg.content.strip():
continue
if self._was_moderated(msg):
continue
history_messages.append(msg)
if len(history_messages) >= context_count:
break
@@ -636,6 +646,19 @@ class SentimentCog(commands.Cog):
sorted_ids = sorted(self._analyzed_message_ids)
self._analyzed_message_ids = set(sorted_ids[len(sorted_ids) // 2:])
def _prune_moderated_ids(self):
"""Cap the moderated message ID set to avoid unbounded growth."""
if len(self._moderated_message_ids) > self._max_analyzed_ids:
sorted_ids = sorted(self._moderated_message_ids)
self._moderated_message_ids = set(sorted_ids[len(sorted_ids) // 2:])
def _was_moderated(self, msg: discord.Message) -> bool:
"""Check if a message already triggered moderation (in-memory or via reaction)."""
if msg.id in self._moderated_message_ids:
return True
# Fall back to checking for bot's warning reaction (survives restarts)
return any(str(r.emoji) == "\u26a0\ufe0f" and r.me for r in msg.reactions)
async def _maybe_start_mention_scan(
self, trigger_message: discord.Message, mention_config: dict
):
@@ -683,14 +706,16 @@ class SentimentCog(commands.Cog):
sentiment_config = config.get("sentiment", {})
game_channels = config.get("game_channels", {})
# Fetch recent messages (before the trigger, skip bots/empty)
# Fetch recent messages (before the trigger, skip bots/empty/moderated)
raw_messages: list[discord.Message] = []
try:
async for msg in channel.history(limit=scan_count + 10, before=trigger_message):
async for msg in channel.history(limit=scan_count + 20, before=trigger_message):
if msg.author.bot:
continue
if not msg.content or not msg.content.strip():
continue
if self._was_moderated(msg):
continue
raw_messages.append(msg)
if len(raw_messages) >= scan_count:
break

2
cogs/sentiment/state.py
View File

@@ -22,6 +22,7 @@ def save_user_state(bot, dirty_users: set[int], user_id: int) -> None:
warned=user_data.warned_since_reset,
last_offense_at=user_data.last_offense_time or None,
aliases=_aliases_csv(user_data),
warning_expires_at=user_data.warning_expires_at or None,
))
dirty_users.discard(user_id)
@@ -44,5 +45,6 @@ async def flush_dirty_states(bot, dirty_users: set[int]) -> None:
warned=user_data.warned_since_reset,
last_offense_at=user_data.last_offense_time or None,
aliases=_aliases_csv(user_data),
warning_expires_at=user_data.warning_expires_at or None,
)
logger.info("Flushed %d dirty user states to DB.", len(dirty))