feat(openmemory-py/minimax): upgrade default model to MiniMax-M3

Upgrade the MiniMax adapter default chat model from MiniMax-M2.7 to the new
MiniMax-M3 flagship. M2.7 and M2.7-highspeed remain available as explicit
alternatives via the `model=` argument or `OM_MINIMAX_MODEL` env.

- src/openmemory/ai/minimax.py: change fallback default to "MiniMax-M3"
- tests/test_minimax.py: update default-model assertion and switch the custom
  / integration test models to MiniMax-M2.7-highspeed (the still-supported
  fast variant)
- README.md: update the chat-model availability note for the minimax section

Author: octo-patch

packages/openmemory-py/README.md

@@ -180,7 +180,7 @@ embeddings={
 }
 ```
 
-> uses MiniMax's `embo-01` model (1536 dimensions). for chat completions, MiniMax supports `MiniMax-M2.7` and `MiniMax-M2.5-highspeed` via OpenAI-compatible API.
+> uses MiniMax's `embo-01` model (1536 dimensions). for chat completions, MiniMax supports `MiniMax-M3` (default), `MiniMax-M2.7`, and `MiniMax-M2.7-highspeed` via OpenAI-compatible API.
 
 #### aws bedrock
 ```python

packages/openmemory-py/src/openmemory/ai/minimax.py

@@ -19,7 +19,7 @@ def __init__(self, api_key: str = None, base_url: str = None):
         self.client = AsyncOpenAI(api_key=self.api_key, base_url=self.base_url)
 
     async def chat(self, messages: List[Dict[str, str]], model: str = None, **kwargs) -> str:
-        m = model or env.minimax_model or "MiniMax-M2.7"
+        m = model or env.minimax_model or "MiniMax-M3"
         temperature = kwargs.pop("temperature", None)
         if temperature is not None:
             temperature = max(0.0, min(float(temperature), 1.0))

packages/openmemory-py/tests/test_minimax.py

@@ -71,7 +71,7 @@ async def test_chat_default_model(self):
             await adapter.chat([{"role": "user", "content": "test"}])
 
         call_kwargs = adapter.client.chat.completions.create.call_args
-        assert call_kwargs.kwargs["model"] == "MiniMax-M2.7"
+        assert call_kwargs.kwargs["model"] == "MiniMax-M3"
 
     @pytest.mark.asyncio
     async def test_chat_custom_model(self):
@@ -87,10 +87,10 @@ async def test_chat_custom_model(self):
 
         await adapter.chat(
             [{"role": "user", "content": "test"}],
-            model="MiniMax-M2.5-highspeed",
+            model="MiniMax-M2.7-highspeed",
         )
         call_kwargs = adapter.client.chat.completions.create.call_args
-        assert call_kwargs.kwargs["model"] == "MiniMax-M2.5-highspeed"
+        assert call_kwargs.kwargs["model"] == "MiniMax-M2.7-highspeed"
 
     @pytest.mark.asyncio
     async def test_chat_temperature_clamping(self):
@@ -408,7 +408,7 @@ async def test_chat_real_api(self):
         adapter = MiniMaxAdapter(api_key=api_key)
         result = await adapter.chat(
             [{"role": "user", "content": "Say 'hello' and nothing else."}],
-            model="MiniMax-M2.5-highspeed",
+            model="MiniMax-M2.7-highspeed",
             temperature=0.0,
         )
         assert isinstance(result, str)