fix: align default model names with SDK defaults (#6704)

mem0/configs/llms/base.py

@@ -31,7 +31,7 @@ class BaseLlmConfig(ABC):
         Initialize a base configuration class instance for the LLM.
 
         Args:
-            model: The model identifier to use (e.g., "gpt-4.1-nano-2025-04-14", "claude-3-5-sonnet-20240620")
+            model: The model identifier to use (e.g., "gpt-5-mini", "claude-3-5-sonnet-20240620")
                 Defaults to None (will be set by provider-specific configs)
             temperature: Controls the randomness of the model's output.
                 Higher values (closer to 1) make output more random, lower values make it more deterministic.

mem0/exceptions.py

@@ -353,7 +353,7 @@ class LLMError(MemoryError):
         raise LLMError(
             message="LLM operation failed",
             error_code="LLM_001",
-            details={"model": "gpt-4", "prompt_length": 500},
+            details={"model": "gpt-5-mini", "prompt_length": 500},
             suggestion="Please check your LLM configuration and API key"
         )
     """