aj/Breehavior-Monitor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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>
This commit is contained in:
AJ Isaacs
2026-02-23 16:04:55 -05:00
parent e4239b25c3
commit c258994a2e
2 changed files with 18 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
cogs/chat.py
View File

@@ -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,