From a55ed9cc04fcbe003adf9b89456538e0caae37f7 Mon Sep 17 00:00:00 2001
From: shokollm <270575765+shokollm@users.noreply.github.com>
Date: Fri, 10 Apr 2026 03:42:20 +0000
Subject: [PATCH] fix: use MiniMax text/chatcompletion_v2 endpoint instead of
 chat/completions

The /v1/chat/completions endpoint returns 529 (overloaded) while
/v1/text/chatcompletion_v2 works reliably.
---
 src/backend/app/services/ai_agent/llm_connector.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/backend/app/services/ai_agent/llm_connector.py b/src/backend/app/services/ai_agent/llm_connector.py
index 6d590a3..4698daf 100644
--- a/src/backend/app/services/ai_agent/llm_connector.py
+++ b/src/backend/app/services/ai_agent/llm_connector.py
@@ -21,7 +21,7 @@ class MiniMaxLLM:
         }
         with httpx.Client(timeout=60.0) as client:
             response = client.post(
-                f"{self.base_url}/chat/completions",
+                f"{self.base_url}/text/chatcompletion_v2",
                 headers=headers,
                 json=payload,
             )
-- 
2.49.1