Merge pull request 'fix: use MiniMax text/chatcompletion_v2 endpoint' (#46) from fix/minimax-endpoint-v2 into main

The /v1/chat/completions endpoint returns 529 (overloaded) while
/v1/text/chatcompletion_v2 works reliably.

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,
             )