feat: require warning before mute + sustained toxicity escalation

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>

utils/database.py

@@ -126,6 +126,12 @@ class Database:
                 ALTER TABLE UserState ADD UserNotes NVARCHAR(MAX) NULL
         """)
 
+        # --- Schema migration for warned flag (require warning before mute) ---
+        cursor.execute("""
+            IF COL_LENGTH('UserState', 'Warned') IS NULL
+                ALTER TABLE UserState ADD Warned BIT NOT NULL DEFAULT 0
+        """)
+
         cursor.execute("""
             IF NOT EXISTS (SELECT * FROM sys.tables WHERE name = 'BotSettings')
             CREATE TABLE BotSettings (
@@ -284,19 +290,20 @@ class Database:
         off_topic_count: int,
         baseline_coherence: float = 0.85,
         user_notes: str | None = None,
+        warned: bool = False,
     ) -> None:
-        """Upsert user state (offense count, immunity, off-topic count, coherence baseline, notes)."""
+        """Upsert user state (offense count, immunity, off-topic count, coherence baseline, notes, warned)."""
         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,
+                user_id, offense_count, immune, off_topic_count, baseline_coherence, user_notes, warned,
             )
         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):
+    def _save_user_state_sync(self, user_id, offense_count, immune, off_topic_count, baseline_coherence, user_notes, warned):
         conn = self._connect()
         try:
             cursor = conn.cursor()
@@ -306,14 +313,14 @@ class Database:
                    ON target.UserId = source.UserId
                    WHEN MATCHED THEN
                        UPDATE SET OffenseCount = ?, Immune = ?, OffTopicCount = ?,
-                                  BaselineCoherence = ?, UserNotes = ?,
+                                  BaselineCoherence = ?, UserNotes = ?, Warned = ?,
                                   UpdatedAt = SYSUTCDATETIME()
                    WHEN NOT MATCHED THEN
-                       INSERT (UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes)
-                       VALUES (?, ?, ?, ?, ?, ?);""",
+                       INSERT (UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes, Warned)
+                       VALUES (?, ?, ?, ?, ?, ?, ?);""",
                 user_id,
-                offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes,
-                user_id, offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes,
+                offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes, 1 if warned else 0,
+                user_id, offense_count, 1 if immune else 0, off_topic_count, baseline_coherence, user_notes, 1 if warned else 0,
             )
             cursor.close()
         finally:
@@ -356,7 +363,7 @@ class Database:
         try:
             cursor = conn.cursor()
             cursor.execute(
-                "SELECT UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes FROM UserState"
+                "SELECT UserId, OffenseCount, Immune, OffTopicCount, BaselineCoherence, UserNotes, Warned FROM UserState"
             )
             rows = cursor.fetchall()
             cursor.close()
@@ -368,6 +375,7 @@ class Database:
                     "off_topic_count": row[3],
                     "baseline_coherence": float(row[4]),
                     "user_notes": row[5] or "",
+                    "warned": bool(row[6]),
                 }
                 for row in rows
             ]

utils/drama_tracker.py

@@ -70,7 +70,7 @@ class DramaTracker:
         user.last_analysis_time = now
         self._prune_entries(user, now)
 
-    def get_drama_score(self, user_id: int) -> float:
+    def get_drama_score(self, user_id: int, escalation_boost: float = 0.04) -> float:
         user = self.get_user(user_id)
         now = time.time()
         self._prune_entries(user, now)
@@ -86,7 +86,19 @@ class DramaTracker:
             weighted_sum += entry.toxicity_score * weight
             total_weight += weight
 
-        return weighted_sum / total_weight if total_weight > 0 else 0.0
+        base_score = weighted_sum / total_weight if total_weight > 0 else 0.0
+
+        # Escalation: if warned, each high-scoring message AFTER the warning
+        # adds a boost so sustained bad behavior ramps toward mute threshold
+        if user.warned_since_reset and user.last_warning_time > 0:
+            post_warn_high = sum(
+                1 for e in user.entries
+                if e.timestamp > user.last_warning_time and e.toxicity_score >= 0.5
+            )
+            if post_warn_high > 0:
+                base_score += escalation_boost * post_warn_high
+
+        return min(base_score, 1.0)
 
     def get_mute_threshold(self, user_id: int, base_threshold: float) -> float:
         """Lower the mute threshold if user was already warned."""
@@ -272,6 +284,8 @@ class DramaTracker:
                 user.baseline_coherence = state["baseline_coherence"]
             if "user_notes" in state and state["user_notes"]:
                 user.notes = state["user_notes"]
+            if state.get("warned"):
+                user.warned_since_reset = True
             count += 1
         return count