ops: consistent rotated db backups + cron, consecutive-api-error staff alert

fjerkroa_bot/discord_bot.py

@@ -89,6 +89,7 @@ class FjerkroaBot(commands.Bot):
         self.tasks_enabled = True
         self.quiet_until = 0.0
         self._staff_alert_times: deque = deque()
+        self._consecutive_api_errors = 0  # OPS-16
 
         self.init_observer()
         self.init_aichannels()
@@ -498,6 +499,14 @@ class FjerkroaBot(commands.Bot):
             return True, False
         return False, bool(verdict.get("factual", False))
 
+    async def _note_api_error(self, err: Exception) -> None:
+        """Count consecutive failures; alert staff once at threshold (OPS-16)."""
+        self._consecutive_api_errors += 1
+        logging.warning(f"responder call failed ({self._consecutive_api_errors} in a row): {repr(err)}")
+        threshold = int(self.config.get("api-error-alert-threshold", 5))
+        if self._consecutive_api_errors == threshold:
+            await self.send_staff_alert(f"⚠️ {threshold} consecutive API errors — the bot may be down. Last: {str(err)[:200]}")
+
     async def send_message_with_typing(self, airesponder, channel, message):
         """Send the user message to the AI responder with typing animation in discord"""
         async with channel.typing():
@@ -603,8 +612,15 @@ class FjerkroaBot(commands.Bot):
         # Get the AI responder based on the channel name
         airesponder = self.get_ai_responder(channel_name)
 
-        # Send the user message to the AI responder, with typing indicators
-        response = await self.send_message_with_typing(airesponder, channel, message)
+        # Send the user message to the AI responder, with typing indicators.
+        # A raised call = a broken API path (cf. the gpt-5.6 tools incident):
+        # count it, alert staff at threshold, never crash the handler (OPS-16).
+        try:
+            response = await self.send_message_with_typing(airesponder, channel, message)
+        except Exception as err:
+            await self._note_api_error(err)
+            return
+        self._consecutive_api_errors = 0
 
         # SAF/OPS gates between model proposal and delivery
         await self._apply_response_gates(message, response)