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

26
utils/database.py
View File

@@ -144,6 +144,12 @@ class Database:
ALTER TABLE UserState ADD Aliases NVARCHAR(500) NULL
""")
# --- Schema migration for warning expiration ---
cursor.execute("""
IF COL_LENGTH('UserState', 'WarningExpiresAt') IS NULL
ALTER TABLE UserState ADD WarningExpiresAt FLOAT NULL
""")
cursor.execute("""
IF NOT EXISTS (SELECT * FROM sys.tables WHERE name = 'BotSettings')
CREATE TABLE BotSettings (
@@ -321,19 +327,20 @@ class Database:
warned: bool = False,
last_offense_at: float | None = None,
aliases: str | None = None,
warning_expires_at: float | None = None,
) -> None:
"""Upsert user state (offense count, immunity, off-topic count, coherence baseline, notes, warned, last offense time, aliases)."""
"""Upsert user state (offense count, immunity, off-topic count, coherence baseline, notes, warned, last offense time, aliases, warning expiration)."""
if not self._available:
return
try:
await asyncio.to_thread(
self._save_user_state_sync,
user_id, offense_count, immune, off_topic_count, baseline_coherence, user_notes, warned, last_offense_at, aliases,
user_id, offense_count, immune, off_topic_count, baseline_coherence, user_notes, warned, last_offense_at, aliases, warning_expires_at,
)
except Exception:
logger.exception("Failed to save user state")
def _save_user_state_sync(self, user_id, offense_count, immune, off_topic_count, baseline_coherence, user_notes, warned, last_offense_at, aliases):
def _save_user_state_sync(self, user_id, offense_count, immune, off_topic_count, baseline_coherence, user_notes, warned, last_offense_at, aliases, warning_expires_at):
conn = self._connect()
try:
cursor = conn.cursor()
@@ -344,14 +351,14 @@ class Database:
WHEN MATCHED THEN
UPDATE SET OffenseCount = ?, Immune = ?, OffTopicCount = ?,
BaselineCoherence = ?, UserNotes = ?, Warned = ?,
LastOffenseAt = ?, Aliases = ?,
LastOffenseAt = ?, Aliases = ?, WarningExpiresAt = ?,
UpdatedAt = SYSUTCDATETIME()
WHEN NOT MATCHED THEN
INSERT (UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes, Warned, LastOffenseAt, Aliases)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?);""",
INSERT (UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes, Warned, LastOffenseAt, Aliases, WarningExpiresAt)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?);""",
user_id,
offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes, 1 if warned else 0, last_offense_at, aliases,
user_id, offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes, 1 if warned else 0, last_offense_at, aliases,
offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes, 1 if warned else 0, last_offense_at, aliases, warning_expires_at,
user_id, offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes, 1 if warned else 0, last_offense_at, aliases, warning_expires_at,
)
cursor.close()
finally:
@@ -394,7 +401,7 @@ class Database:
try:
cursor = conn.cursor()
cursor.execute(
"SELECT UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes, Warned, LastOffenseAt, Aliases FROM UserState"
"SELECT UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes, Warned, LastOffenseAt, Aliases, WarningExpiresAt FROM UserState"
)
rows = cursor.fetchall()
cursor.close()
@@ -409,6 +416,7 @@ class Database:
"warned": bool(row[6]),
"last_offense_at": float(row[7]) if row[7] is not None else 0.0,
"aliases": row[8] or "",
"warning_expires_at": float(row[9]) if row[9] is not None else 0.0,
}
for row in rows
]

33
utils/drama_tracker.py
View File

@@ -19,6 +19,7 @@ class UserDrama:
last_warning_time: float = 0.0
last_analysis_time: float = 0.0
warned_since_reset: bool = False
warning_expires_at: float = 0.0
immune: bool = False
# Topic drift tracking
off_topic_count: int = 0
@@ -40,10 +41,12 @@ class DramaTracker:
window_size: int = 10,
window_minutes: int = 15,
offense_reset_minutes: int = 120,
warning_expiration_minutes: int = 30,
):
self.window_size = window_size
self.window_seconds = window_minutes * 60
self.offense_reset_seconds = offense_reset_minutes * 60
self.warning_expiration_seconds = warning_expiration_minutes * 60
self._users: dict[int, UserDrama] = {}
def get_user(self, user_id: int) -> UserDrama:
@@ -74,6 +77,7 @@ class DramaTracker:
def get_drama_score(self, user_id: int, escalation_boost: float = 0.04) -> float:
user = self.get_user(user_id)
self._expire_warning(user)
now = time.time()
self._prune_entries(user, now)
@@ -105,6 +109,7 @@ class DramaTracker:
def get_mute_threshold(self, user_id: int, base_threshold: float) -> float:
"""Lower the mute threshold if user was already warned."""
user = self.get_user(user_id)
self._expire_warning(user)
if user.warned_since_reset:
return base_threshold - 0.05
return base_threshold
@@ -123,12 +128,34 @@ class DramaTracker:
user.offense_count += 1
user.last_offense_time = now
user.warned_since_reset = False
user.warning_expires_at = 0.0
return user.offense_count
def record_warning(self, user_id: int) -> None:
user = self.get_user(user_id)
user.last_warning_time = time.time()
now = time.time()
user.last_warning_time = now
user.warned_since_reset = True
if self.warning_expiration_seconds > 0:
user.warning_expires_at = now + self.warning_expiration_seconds
else:
user.warning_expires_at = 0.0 # Never expires
def _expire_warning(self, user: UserDrama) -> None:
"""Clear warned flag if the warning has expired."""
if (
user.warned_since_reset
and user.warning_expires_at > 0
and time.time() >= user.warning_expires_at
):
user.warned_since_reset = False
user.warning_expires_at = 0.0
def is_warned(self, user_id: int) -> bool:
"""Check if user is currently warned (respects expiration)."""
user = self.get_user(user_id)
self._expire_warning(user)
return user.warned_since_reset
def can_warn(self, user_id: int, cooldown_minutes: int) -> bool:
user = self.get_user(user_id)
@@ -303,12 +330,16 @@ class DramaTracker:
user.notes = state["user_notes"]
if state.get("warned"):
user.warned_since_reset = True
user.warning_expires_at = state.get("warning_expires_at", 0.0) or 0.0
# Expire warning at load time if it's past due
self._expire_warning(user)
if state.get("last_offense_at"):
user.last_offense_time = state["last_offense_at"]
# Apply time-based offense reset at load time
if time.time() - user.last_offense_time > self.offense_reset_seconds:
user.offense_count = 0
user.warned_since_reset = False
user.warning_expires_at = 0.0
user.last_offense_time = 0.0
if state.get("aliases"):
user.aliases = [a.strip() for a in state["aliases"].split(",") if a.strip()]