feat: upgrade MiniMax default model to M2.7

- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to supported models list
- Update docstring to list M2.7 models before M2.5
- Update README/README_CHS model references
- Add unit tests for M2.7 and M2.7-highspeed models
- Keep all previous models as alternatives

README.md

@@ -240,7 +240,7 @@ provider_server_address = # Typically ignored or can be left blank when is_local
 | Hugging Face | `huggingface`   | No     | Use models from Hugging Face Inference API.       | [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) |
 | TogetherAI   | `togetherAI`    | No     | Use various open-source models via TogetherAI API.| [api.together.ai/settings/api-keys](https://api.together.ai/settings/api-keys) |
 | OpenRouter   | `openrouter`    | No     | Use OpenRouter Models| [https://openrouter.ai/](https://openrouter.ai/) |
-| MiniMax      | `minimax`       | No     | Use MiniMax M2.5 series models (e.g., MiniMax-M2.5).| [platform.minimax.io](https://platform.minimax.io/user-center/basic-information) |
+| MiniMax      | `minimax`       | No     | Use MiniMax models (e.g., MiniMax-M2.7, MiniMax-M2.5).| [platform.minimax.io](https://platform.minimax.io/user-center/basic-information) |
 
 *Note:*
 *   We advise against using `gpt-4o` or other OpenAI models for complex web browsing and task planning as current prompt optimizations are geared towards models like Deepseek.

README_CHS.md

@@ -230,7 +230,7 @@ provider_server_address = # 当 is_local = False 时，对于大多数 API 通
 | Hugging Face | `huggingface`   | 否     | 使用 Hugging Face Inference API 中的模型。       | [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) |
 | TogetherAI   | `togetherAI`    | 否     | 通过 TogetherAI API 使用各种开源模型。| [api.together.ai/settings/api-keys](https://api.together.ai/settings/api-keys) |
 | OpenRouter   | `openrouter`    | No     | 通过 OpenRouter 使用各种开源模型| [https://openrouter.ai/](https://openrouter.ai/) |
-| MiniMax      | `minimax`       | 否     | 使用 MiniMax 的 M2.5 系列模型（如 MiniMax-M2.5）。 | [platform.minimax.io](https://platform.minimax.io/user-center/basic-information) |
+| MiniMax      | `minimax`       | 否     | 使用 MiniMax 模型（如 MiniMax-M2.7、MiniMax-M2.5）。 | [platform.minimax.io](https://platform.minimax.io/user-center/basic-information) |
 
 *注意：*
 *   我们不建议将 `gpt-4o` 或其他 OpenAI 模型用于复杂的网页浏览和任务规划，因为当前的提示优化针对 Deepseek 等模型。

sources/llm_provider.py

@@ -416,11 +416,13 @@ class Provider:
     def minimax_fn(self, history, verbose=False):
         """
         Use MiniMax API to generate text via OpenAI-compatible interface.
-        
+
         Supported models:
+        - MiniMax-M2.7: Latest flagship model with enhanced reasoning and coding
+        - MiniMax-M2.7-highspeed: High-speed version of M2.7 for low-latency scenarios
         - MiniMax-M2.5: Peak performance model (~60 tps), 204,800 context window
         - MiniMax-M2.5-highspeed: Same performance, faster (~100 tps)
-        
+
         Note: temperature must be in range (0.0, 1.0], default is 1.0
         """
         load_dotenv()

tests/test_minimax_provider.py

@@ -155,6 +155,42 @@ class TestMiniMaxProvider(unittest.TestCase):
 class TestMiniMaxProviderModels(unittest.TestCase):
     """Test cases for MiniMax provider model configurations."""
 
+    @patch('sources.llm_provider.OpenAI')
+    @patch.dict(os.environ, {'MINIMAX_API_KEY': 'test-key'})
+    def test_minimax_m27_model(self, mock_openai_class):
+        """Test MiniMax-M2.7 model."""
+        mock_client = MagicMock()
+        mock_openai_class.return_value = mock_client
+        mock_response = MagicMock()
+        mock_response.choices = [MagicMock(message=MagicMock(content="Response"))]
+        mock_client.chat.completions.create.return_value = mock_response
+
+        with patch.object(Provider, 'get_api_key', return_value='test-key'):
+            provider = Provider("minimax", "MiniMax-M2.7", is_local=False)
+            history = [{"role": "user", "content": "Hello"}]
+            provider.minimax_fn(history)
+
+            call_kwargs = mock_client.chat.completions.create.call_args[1]
+            self.assertEqual(call_kwargs['model'], "MiniMax-M2.7")
+
+    @patch('sources.llm_provider.OpenAI')
+    @patch.dict(os.environ, {'MINIMAX_API_KEY': 'test-key'})
+    def test_minimax_m27_highspeed_model(self, mock_openai_class):
+        """Test MiniMax-M2.7-highspeed model."""
+        mock_client = MagicMock()
+        mock_openai_class.return_value = mock_client
+        mock_response = MagicMock()
+        mock_response.choices = [MagicMock(message=MagicMock(content="Response"))]
+        mock_client.chat.completions.create.return_value = mock_response
+
+        with patch.object(Provider, 'get_api_key', return_value='test-key'):
+            provider = Provider("minimax", "MiniMax-M2.7-highspeed", is_local=False)
+            history = [{"role": "user", "content": "Hello"}]
+            provider.minimax_fn(history)
+
+            call_kwargs = mock_client.chat.completions.create.call_args[1]
+            self.assertEqual(call_kwargs['model'], "MiniMax-M2.7-highspeed")
+
     @patch('sources.llm_provider.OpenAI')
     @patch.dict(os.environ, {'MINIMAX_API_KEY': 'test-key'})
     def test_minimax_m25_model(self, mock_openai_class):