Use gpt-4o-mini for chat/roasts via dedicated LLM_CHAT_MODEL

Add a separate llm_chat client so chat responses use a smarter model
(gpt-4o-mini) while analysis stays on the cheap local Qwen3-8B.
Falls back to llm_heavy if LLM_CHAT_MODEL is not set.

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

bot.py

@@ -78,7 +78,7 @@ class BCSBot(commands.Bot):
             no_think=is_local, concurrency=1 if is_local else 4,
         )
 
-        # Heavy/escalation LLM (OpenAI for re-analysis, chat, image roasts, commands)
+        # Heavy/escalation LLM (OpenAI for re-analysis, image roasts, commands)
         esc_base_url = os.getenv("LLM_ESCALATION_BASE_URL", "")
         esc_model = os.getenv("LLM_ESCALATION_MODEL", "gpt-4o")
         esc_api_key = os.getenv("LLM_ESCALATION_API_KEY", llm_api_key)
@@ -88,6 +88,19 @@ class BCSBot(commands.Bot):
             no_think=esc_is_local, concurrency=1 if esc_is_local else 4,
         )
 
+        # Chat LLM (dedicated model for chat/roasts — defaults to llm_heavy)
+        chat_model = os.getenv("LLM_CHAT_MODEL", "")
+        chat_api_key = os.getenv("LLM_CHAT_API_KEY", esc_api_key)
+        chat_base_url = os.getenv("LLM_CHAT_BASE_URL", esc_base_url)
+        if chat_model:
+            chat_is_local = bool(chat_base_url)
+            self.llm_chat = LLMClient(
+                chat_base_url, chat_model, chat_api_key, db=self.db,
+                no_think=chat_is_local, concurrency=4,
+            )
+        else:
+            self.llm_chat = self.llm_heavy
+
         # Active mode (server-wide)
         modes_config = config.get("modes", {})
         self.current_mode = modes_config.get("default_mode", "default")
@@ -199,6 +212,8 @@ class BCSBot(commands.Bot):
         await self.db.close()
         await self.llm.close()
         await self.llm_heavy.close()
+        if self.llm_chat is not self.llm_heavy:
+            await self.llm_chat.close()
         await super().close()
 
 

cogs/chat.py

@@ -194,7 +194,7 @@ class ChatCog(commands.Cog):
                 if m["role"] == "assistant"
             ][-5:]
 
-            response = await self.bot.llm.chat(
+            response = await self.bot.llm_chat.chat(
                 list(self._chat_history[ch_id]),
                 active_prompt,
                 on_first_token=start_typing,
@@ -312,7 +312,7 @@ class ChatCog(commands.Cog):
             if m["role"] == "assistant"
         ][-5:]
 
-        response = await self.bot.llm.chat(
+        response = await self.bot.llm_chat.chat(
             list(self._chat_history[ch_id]),
             active_prompt,
             recent_bot_replies=recent_bot_replies,