fix: resolve remaining CI issues - formatting and test assertion

- Fixed code formatting issues detected by ruff formatter
- Updated test assertion to handle actual error message format
- All CI checks now passing: ruff, mypy, bandit, formatting, and 173 tests

Author: Zvi Fried

examples/rate_limit_demo.py

@@ -36,6 +36,7 @@ async def demo_rate_limit_handling():
 
     # Mock response for successful case
     from unittest.mock import MagicMock
+
     mock_response = MagicMock()
     mock_response.choices = [MagicMock()]
     mock_response.choices[0].message.content = "Success after retries!"

scripts/test_dynamic_urls.py

@@ -24,7 +24,7 @@ def test_models():
         domain_specificity="specialized",
         implementation_scope="full_system",
         existing_knowledge="limited",
-        innovation_level="cutting_edge"
+        innovation_level="cutting_edge",
     )
     print(f"✅ ResearchComplexityFactors created: {factors.technical_complexity}")
 
@@ -34,9 +34,11 @@ def test_models():
         expected_url_count=5,
         minimum_url_count=3,
         reasoning="Complex authentication system requires multiple sources",
-        quality_criteria=["security best practices", "proven implementation patterns"]
+        quality_criteria=["security best practices", "proven implementation patterns"],
+    )
+    print(
+        f"✅ ResearchRequirementsAnalysis created: {analysis.expected_url_count} URLs expected"
     )
-    print(f"✅ ResearchRequirementsAnalysis created: {analysis.expected_url_count} URLs expected")
 
     # Test URLValidationResult
     validation = URLValidationResult(
@@ -45,7 +47,7 @@ def test_models():
         expected_count=5,
         minimum_count=3,
         adequacy_reasoning="Good coverage of security patterns, missing performance considerations",
-        quality_assessment="High quality sources from established authorities"
+        quality_assessment="High quality sources from established authorities",
     )
     print(f"✅ URLValidationResult created: adequate={validation.is_adequate}")
 
@@ -59,12 +61,15 @@ def test_models():
         expected_url_count=5,
         minimum_url_count=3,
         url_requirement_reasoning="Testing dynamic URLs",
-        research_complexity_analysis=analysis
+        research_complexity_analysis=analysis,
+    )
+    print(
+        f"✅ TaskMetadata with dynamic URLs: {metadata.expected_url_count}/{metadata.minimum_url_count}"
     )
-    print(f"✅ TaskMetadata with dynamic URLs: {metadata.expected_url_count}/{metadata.minimum_url_count}")
 
     print("🎉 All model tests passed!")
 
+
 async def test_analyzer_mock():
     """Test the ResearchRequirementsAnalyzer with a mock scenario."""
     print("\n🧪 Testing ResearchRequirementsAnalyzer...")
@@ -89,20 +94,27 @@ async def test_analyzer_mock():
                 domain_specificity="security",
                 implementation_scope="authentication_system",
                 existing_knowledge="moderate",
-                innovation_level="standard"
+                innovation_level="standard",
             ),
             expected_url_count=4,
             minimum_url_count=2,
             reasoning="Security-focused authentication requires multiple authoritative sources",
-            quality_criteria=["security best practices", "JWT standards", "authentication patterns"]
+            quality_criteria=[
+                "security best practices",
+                "JWT standards",
+                "authentication patterns",
+            ],
+        )
+        print(
+            f"✅ Fallback analysis: {fallback_analysis.expected_url_count} URLs expected"
         )
-        print(f"✅ Fallback analysis: {fallback_analysis.expected_url_count} URLs expected")
 
     except Exception as e:
         print(f"❌ Error in analyzer test: {e}")
 
     print("🎉 Analyzer structure test passed!")
 
+
 def test_url_validation():
     """Test URL validation logic."""
     print("\n🧪 Testing URL validation...")
@@ -111,34 +123,47 @@ def test_url_validation():
     test_cases = [
         {
             "name": "Adequate URLs",
-            "provided": ["https://auth0.com/blog", "https://jwt.io/introduction", "https://owasp.org/auth"],
+            "provided": [
+                "https://auth0.com/blog",
+                "https://jwt.io/introduction",
+                "https://owasp.org/auth",
+            ],
             "expected": 3,
-            "minimum": 2
+            "minimum": 2,
         },
         {
             "name": "Below minimum",
             "provided": ["https://auth0.com/blog"],
             "expected": 4,
-            "minimum": 2
+            "minimum": 2,
         },
         {
             "name": "Above expected",
-            "provided": ["https://auth0.com/blog", "https://jwt.io", "https://owasp.org", "https://security.com", "https://rfc7519.com"],
+            "provided": [
+                "https://auth0.com/blog",
+                "https://jwt.io",
+                "https://owasp.org",
+                "https://security.com",
+                "https://rfc7519.com",
+            ],
             "expected": 3,
-            "minimum": 2
-        }
+            "minimum": 2,
+        },
     ]
 
     for case in test_cases:
         provided_count = len(case["provided"])
         is_adequate = provided_count >= case["minimum"]
         meets_expected = provided_count >= case["expected"]
 
-        print(f"📊 {case['name']}: {provided_count} URLs (min: {case['minimum']}, expected: {case['expected']})")
+        print(
+            f"📊 {case['name']}: {provided_count} URLs (min: {case['minimum']}, expected: {case['expected']})"
+        )
         print(f"   Adequate: {is_adequate}, Meets Expected: {meets_expected}")
 
     print("✅ URL validation logic tests passed!")
 
+
 def main():
     """Run all tests."""
     print("🚀 Testing Dynamic URL Validation System")
@@ -156,7 +181,9 @@ def main():
     except Exception as e:
         print(f"\n❌ TEST FAILED: {e}")
         import traceback
+
         traceback.print_exc()
 
+
 if __name__ == "__main__":
     main()

src/mcp_as_a_judge/elicitation/factory.py

@@ -76,7 +76,7 @@ def get_available_providers(self, ctx: Context) -> dict[str, dict[str, object]]:
             "fallback_elicitation": {
                 "available": True,  # Always available
                 "provider_type": self._fallback_provider.provider_type,
-            }
+            },
         }
 
 

src/mcp_as_a_judge/models/__init__.py

@@ -107,6 +107,7 @@ class JudgeCodingPlanUserVars(BaseModel):
         expected_url_count: int = 0
         minimum_url_count: int = 0
         url_requirement_reasoning: str = ""
+
     conversation_history: list[_Any] = Field(default_factory=list)
     # Conditional research fields
     research_required: bool = False

src/mcp_as_a_judge/models/enhanced_responses.py

@@ -1,5 +1,3 @@
-
-
 from typing import Any
 
 from pydantic import BaseModel, Field, model_serializer
@@ -9,7 +7,6 @@
 
 
 class TrimmedBaseModel(BaseModel):
-
     @model_serializer(mode="wrap")
     def _serialize_trimmed(self, serializer: Any) -> dict:
         # Common Pydantic v2 approach: exclude unset, None, and defaults
@@ -28,7 +25,6 @@ def _serialize_trimmed(self, serializer: Any) -> dict:
 
 
 class JudgeResponse(TrimmedBaseModel):
-
     approved: bool = Field(description="Whether the validation passed")
     required_improvements: list[str] = Field(
         default_factory=list,
@@ -80,7 +76,6 @@ class FileReview(TrimmedBaseModel):
 
 
 class TaskAnalysisResult(TrimmedBaseModel):
-
     action: str = Field(description="Action taken: 'created' or 'updated'")
     context_summary: str = Field(
         description="Summary of the task context and current state"
@@ -95,7 +90,6 @@ class TaskAnalysisResult(TrimmedBaseModel):
 
 
 class TaskCompletionResult(TrimmedBaseModel):
-
     approved: bool = Field(description="Whether the task completion is approved")
     feedback: str = Field(
         description="Detailed feedback about the completion validation"
@@ -113,7 +107,6 @@ class TaskCompletionResult(TrimmedBaseModel):
 
 
 class ObstacleResult(TrimmedBaseModel):
-
     obstacle_acknowledged: bool = Field(
         description="Whether the obstacle has been acknowledged"
     )
@@ -130,7 +123,6 @@ class ObstacleResult(TrimmedBaseModel):
 
 
 class MissingRequirementsResult(TrimmedBaseModel):
-
     clarification_needed: bool = Field(description="Whether clarification is needed")
     missing_information: list[str] = Field(
         default_factory=list,
@@ -152,7 +144,6 @@ class MissingRequirementsResult(TrimmedBaseModel):
 
 
 class EnhancedResponseFactory:
-
     @staticmethod
     def create_judge_response(
         approved: bool,

src/mcp_as_a_judge/models/task_metadata.py

@@ -100,8 +100,6 @@ class RequirementsVersion(BaseModel):
     timestamp: int = Field(default_factory=lambda: int(time.time()))
 
 
-
-
 class TaskMetadata(BaseModel):
     """
     Lightweight metadata for coding tasks that flows with memory layer.