Cleanup

conf/custom_models.json

@@ -103,9 +103,27 @@
       "supports_function_calling": false,
       "description": "Meta's Llama 3 70B model"
     },
+    {
+      "model_name": "openai/gpt-4o",
+      "aliases": ["gpt4o", "4o", "gpt-4o"],
+      "context_window": 128000,
+      "supports_extended_thinking": false,
+      "supports_json_mode": true,
+      "supports_function_calling": true,
+      "description": "OpenAI's GPT-4o model"
+    },
+    {
+      "model_name": "deepseek/deepseek-coder",
+      "aliases": ["deepseek-coder", "deepseek", "coder"],
+      "context_window": 65536,
+      "supports_extended_thinking": false,
+      "supports_json_mode": true,
+      "supports_function_calling": true,
+      "description": "DeepSeek Coder model for programming tasks"
+    },
     {
       "model_name": "deepseek/deepseek-r1-0528",
-      "aliases": ["deepseek-r1", "deepseek", "r1", "deepseek-thinking"],
+      "aliases": ["deepseek-r1", "r1", "deepseek-thinking"],
       "context_window": 65536,
       "supports_extended_thinking": true,
       "supports_json_mode": true,

providers/base.py

@@ -212,9 +212,7 @@ class ModelProvider(ABC):
         # Validate temperature
         min_temp, max_temp = capabilities.temperature_range
         if not min_temp <= temperature <= max_temp:
-            raise ValueError(
-                f"Temperature {temperature} out of range [{min_temp}, {max_temp}] " f"for model {model_name}"
-            )
+            raise ValueError(f"Temperature {temperature} out of range [{min_temp}, {max_temp}] for model {model_name}")
 
     @abstractmethod
     def supports_thinking_mode(self, model_name: str) -> bool:

providers/openai_compatible.py

@@ -246,9 +246,7 @@ class OpenAICompatibleProvider(ModelProvider):
         """
         # Validate model name against allow-list
         if not self.validate_model_name(model_name):
-            raise ValueError(
-                f"Model '{model_name}' not in allowed models list. " f"Allowed models: {self.allowed_models}"
-            )
+            raise ValueError(f"Model '{model_name}' not in allowed models list. Allowed models: {self.allowed_models}")
 
         # Validate parameters
         self.validate_parameters(model_name, temperature)
@@ -367,7 +365,7 @@ class OpenAICompatibleProvider(ModelProvider):
             # Check if we're using generic capabilities
             if hasattr(capabilities, "_is_generic"):
                 logging.debug(
-                    f"Using generic parameter validation for {model_name}. " "Actual model constraints may differ."
+                    f"Using generic parameter validation for {model_name}. Actual model constraints may differ."
                 )
 
             # Validate temperature using parent class method

providers/openrouter_registry.py

@@ -154,7 +154,7 @@ class OpenRouterModelRegistry:
                 if alias_lower in alias_map:
                     existing_model = alias_map[alias_lower]
                     raise ValueError(
-                        f"Duplicate alias '{alias}' found for models " f"'{existing_model}' and '{config.model_name}'"
+                        f"Duplicate alias '{alias}' found for models '{existing_model}' and '{config.model_name}'"
                     )
                 alias_map[alias_lower] = config.model_name
 

simulator_tests/base_test.py

@@ -138,7 +138,11 @@ class Calculator:
 
             # Execute the command
             result = subprocess.run(
-                docker_cmd, input=input_data, text=True, capture_output=True, timeout=3600  # 1 hour timeout
+                docker_cmd,
+                input=input_data,
+                text=True,
+                capture_output=True,
+                timeout=3600,  # 1 hour timeout
             )
 
             if result.returncode != 0:

tests/test_claude_continuation.py

@@ -284,7 +284,7 @@ I'd be happy to examine the error handling patterns in more detail if that would
         turns = [
             ConversationTurn(
                 role="assistant" if i % 2 else "user",
-                content=f"Turn {i+1}",
+                content=f"Turn {i + 1}",
                 timestamp="2023-01-01T00:00:00Z",
                 tool_name="test_continuation",
             )

tests/test_collaboration.py

@@ -246,9 +246,9 @@ class TestCollaborationWorkflow:
         )
 
         response = json.loads(result[0].text)
-        assert (
-            response["status"] == "requires_clarification"
-        ), "Should request clarification when asked about dependencies without package files"
+        assert response["status"] == "requires_clarification", (
+            "Should request clarification when asked about dependencies without package files"
+        )
 
         clarification = json.loads(response["content"])
         assert "package.json" in str(clarification["files_needed"]), "Should specifically request package.json"

tests/test_custom_provider.py

@@ -95,7 +95,9 @@ class TestCustomProvider:
 
         # Call with an alias
         result = provider.generate_content(
-            prompt="test prompt", model_name="llama", temperature=0.7  # This is an alias
+            prompt="test prompt",
+            model_name="llama",
+            temperature=0.7,  # This is an alias
         )
 
         # Verify parent method was called with resolved model name

tests/test_intelligent_fallback.py

@@ -76,7 +76,6 @@ class TestIntelligentFallback:
             patch("config.DEFAULT_MODEL", "auto"),
             patch.dict(os.environ, {"OPENAI_API_KEY": "sk-test-key", "GEMINI_API_KEY": ""}, clear=False),
         ):
-
             ModelProviderRegistry.clear_cache()
 
             # Create a context with at least one turn so it doesn't exit early
@@ -115,7 +114,6 @@ class TestIntelligentFallback:
             patch("config.DEFAULT_MODEL", "auto"),
             patch.dict(os.environ, {"OPENAI_API_KEY": "", "GEMINI_API_KEY": "test-key"}, clear=False),
         ):
-
             ModelProviderRegistry.clear_cache()
 
             from utils.conversation_memory import ConversationTurn
@@ -148,7 +146,6 @@ class TestIntelligentFallback:
         from utils.conversation_memory import ThreadContext, build_conversation_history
 
         with patch("config.IS_AUTO_MODE", False), patch("config.DEFAULT_MODEL", "gemini-2.5-pro-preview-06-05"):
-
             from utils.conversation_memory import ConversationTurn
 
             context = ThreadContext(

tests/test_precommit_with_mock_store.py

@@ -233,7 +233,11 @@ TEMPERATURE_ANALYTICAL = 0.2  # For code review, debugging
 
         # Test the centralized file preparation method directly
         file_content = tool._prepare_file_content_for_prompt(
-            [config_path], None, "Test files", max_tokens=100000, reserve_tokens=1000  # No continuation
+            [config_path],
+            None,
+            "Test files",
+            max_tokens=100000,
+            reserve_tokens=1000,  # No continuation
         )
 
         # Should contain file markers

tests/test_thinking_modes.py

@@ -34,9 +34,9 @@ class TestThinkingModes:
         ]
 
         for tool, expected_default in tools:
-            assert (
-                tool.get_default_thinking_mode() == expected_default
-            ), f"{tool.__class__.__name__} should default to {expected_default}"
+            assert tool.get_default_thinking_mode() == expected_default, (
+                f"{tool.__class__.__name__} should default to {expected_default}"
+            )
 
     @pytest.mark.asyncio
     @patch("tools.base.BaseTool.get_model_provider")

tools/base.py

@@ -58,8 +58,7 @@ class ToolRequest(BaseModel):
     thinking_mode: Optional[Literal["minimal", "low", "medium", "high", "max"]] = Field(
         None,
         description=(
-            "Thinking depth: minimal (0.5% of model max), low (8%), medium (33%), high (67%), "
-            "max (100% of model max)"
+            "Thinking depth: minimal (0.5% of model max), low (8%), medium (33%), high (67%), max (100% of model max)"
         ),
     )
     use_websearch: Optional[bool] = Field(

utils/conversation_memory.py

@@ -372,7 +372,7 @@ def get_conversation_file_list(context: ThreadContext) -> list[str]:
 
     for i, turn in enumerate(context.turns):
         if turn.files:
-            logger.debug(f"[FILES] Turn {i+1} has {len(turn.files)} files: {turn.files}")
+            logger.debug(f"[FILES] Turn {i + 1} has {len(turn.files)} files: {turn.files}")
             for file_path in turn.files:
                 if file_path not in seen_files:
                     seen_files.add(file_path)
@@ -381,7 +381,7 @@ def get_conversation_file_list(context: ThreadContext) -> list[str]:
                 else:
                     logger.debug(f"[FILES] Duplicate file skipped: {file_path}")
         else:
-            logger.debug(f"[FILES] Turn {i+1} has no files")
+            logger.debug(f"[FILES] Turn {i + 1} has no files")
 
     logger.debug(f"[FILES] Final unique file list ({len(unique_files)}): {unique_files}")
     return unique_files