Add two-tier LLM analysis with triage/escalation

Triage model (LLM_MODEL) handles every message cheaply. If toxicity
>= 0.25, off_topic, or coherence < 0.6, the message is re-analyzed
with the heavy model (LLM_ESCALATION_MODEL). Chat, image analysis,
/bcs-test, and /bcs-scan always use the heavy model.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

cogs/commands.py

@@ -126,9 +126,19 @@ class CommandsCog(commands.Cog):
             inline=True,
         )
         embed.add_field(
-            name="LLM",
-            value=f"`{self.bot.llm.model}` @ `{self.bot.llm.host}`",
-            inline=False,
+            name="Triage Model",
+            value=f"`{self.bot.llm.model}`",
+            inline=True,
+        )
+        embed.add_field(
+            name="Escalation Model",
+            value=f"`{self.bot.llm_heavy.model}`",
+            inline=True,
+        )
+        embed.add_field(
+            name="LLM Host",
+            value=f"`{self.bot.llm.host}`",
+            inline=True,
         )
 
         await interaction.response.send_message(embed=embed, ephemeral=True)
@@ -301,7 +311,7 @@ class CommandsCog(commands.Cog):
                 else "(no prior context)"
             )
 
-            result = await self.bot.llm.analyze_message(msg.content, context)
+            result = await self.bot.llm_heavy.analyze_message(msg.content, context)
             if result is None:
                 embed = discord.Embed(
                     title=f"Analysis: {msg.author.display_name}",
@@ -374,7 +384,7 @@ class CommandsCog(commands.Cog):
             channel_context = "\n".join(lines)
 
         user_notes = self.bot.drama_tracker.get_user_notes(interaction.user.id)
-        raw, parsed = await self.bot.llm.raw_analyze(
+        raw, parsed = await self.bot.llm_heavy.raw_analyze(
             message, user_notes=user_notes, channel_context=channel_context,
         )