chore(MAT-13): Switch chunk summarization from claude-haiku to gemini-flash

Reduces cost for conversation chunk summarization in live indexing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 18:27:43 +02:00
parent 9d2e2ddcf7
commit fecf99ef60
1 changed files with 1 additions and 1 deletions
--- a/bot.py
+++ b/bot.py
@@ -1231,7 +1231,7 @@ class Bot:
        chunk_text = f"User: {user_message}\nAssistant: {ai_reply}"
        try:
            resp = await self.llm.chat.completions.create(
-                model="claude-haiku",
+                model="gemini-flash",
                messages=[
                    {"role": "system", "content": (
                        "Summarize this conversation exchange in 1-2 sentences for search indexing. "