Fixed ruff lint issues for src/contextual_retrieval

pyproject.toml

@@ -90,6 +90,24 @@ ignore = []
 fixable = ["ALL"]
 unfixable = []
 
+# Per-file ignores for special cases
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*.py" = [
+    "ANN",    # Ignore all missing type annotations (ANN001, ANN201, etc.)
+    "T201",   # Allow print statements
+]
+
+"src/models/request_models.py" = ["N815"]  # camelCase fields required for API contract
+"src/optimization/optimized_module_loader.py" = ["N815"]  # Pydantic model fields
+"src/optimization/optimizers/generator_optimizer.py" = ["N815"]  # Pydantic model fields
+"src/response_generator/response_generate.py" = ["N815", "ANN401"]  # Pydantic model fields + DSPy streamify Any type
+
+# Library interface patterns - legitimate Any usage
+"src/contextual_retrieval/contextual_retrieval_api_client.py" = ["ANN401"]  # httpx **kwargs pass-through
+"src/guardrails/dspy_nemo_adapter.py" = ["ANN401"]  # LangChain LLM interface + DSPy dynamic types
+"src/llm_orchestrator_config/context_manager.py" = ["ANN401"]  # MockResponse with dynamic attributes
+"src/optimization/metrics/*.py" = ["ANN401"]  # DSPy optimizer trace parameter (internal type)
+"byk-stack-setup/script.py" = ["T201"]  # CLI script uses print 
 
 [tool.ruff.format]
 # Like Black, use double quotes for strings.
@@ -123,4 +141,4 @@ exclude = [
 ]
 
 # --- Global strictness ---
-typeCheckingMode = "standard"      # Standard typechecking mode
+typeCheckingMode = "standard"      # Standard typechecking mode

src/contextual_retrieval/bm25_search.py

@@ -5,7 +5,7 @@
 when collection data changes.
 """
 
-from typing import List, Dict, Any, Optional, Set
+from typing import List, Dict, Any, Optional, Set, TYPE_CHECKING
 from loguru import logger
 from rank_bm25 import BM25Okapi
 import re
@@ -20,13 +20,16 @@
 )
 from contextual_retrieval.config import ConfigLoader, ContextualRetrievalConfig
 
+if TYPE_CHECKING:
+    from contextual_retrieval.contextual_retrieval_api_client import HTTPClientManager
+
 
 class SmartBM25Search:
     """In-memory BM25 search with smart refresh capabilities."""
 
     def __init__(
         self, qdrant_url: str, config: Optional["ContextualRetrievalConfig"] = None
-    ):
+    ) -> None:
         self.qdrant_url = qdrant_url
         self._config = config if config is not None else ConfigLoader.load_config()
         self._http_client_manager = None
@@ -40,7 +43,7 @@ def __init__(
         # Strong references to background tasks to prevent premature GC
         self._background_tasks: Set[asyncio.Task[None]] = set()
 
-    async def _get_http_client_manager(self):
+    async def _get_http_client_manager(self) -> "HTTPClientManager":
         """Get the HTTP client manager instance."""
         if self._http_client_manager is None:
             self._http_client_manager = await get_http_client_manager()
@@ -356,7 +359,7 @@ def _tokenize_text(self, text: str) -> List[str]:
         tokens = self.tokenizer_pattern.findall(text.lower())
         return tokens
 
-    async def close(self):
+    async def close(self) -> None:
         """Close HTTP client."""
         if self._http_client_manager:
             await self._http_client_manager.close()

src/contextual_retrieval/constants.py

@@ -15,7 +15,7 @@ class HttpClientConstants:
     DEFAULT_FAILURE_THRESHOLD = 5
     DEFAULT_RECOVERY_TIMEOUT = 60.0
 
-    # Timeouts (seconds)
+    # Timeouts in seconds
     DEFAULT_READ_TIMEOUT = 30.0
     DEFAULT_CONNECT_TIMEOUT = 10.0
     DEFAULT_WRITE_TIMEOUT = 10.0

src/contextual_retrieval/contextual_retrieval_api_client.py

@@ -24,7 +24,7 @@
 class ServiceResilienceManager:
     """Service resilience manager with circuit breaker functionality for HTTP requests."""
 
-    def __init__(self, config: Optional["ContextualRetrievalConfig"] = None):
+    def __init__(self, config: Optional["ContextualRetrievalConfig"] = None) -> None:
         # Load configuration if not provided
         if config is None:
             config = ConfigLoader.load_config()
@@ -81,7 +81,7 @@ class HTTPClientManager:
     _instance: Optional["HTTPClientManager"] = None
     _lock = asyncio.Lock()
 
-    def __init__(self, config: Optional["ContextualRetrievalConfig"] = None):
+    def __init__(self, config: Optional["ContextualRetrievalConfig"] = None) -> None:
         """Initialize HTTP client manager."""
         # Load configuration if not provided
         self._config = config if config is not None else ConfigLoader.load_config()
@@ -169,7 +169,7 @@ async def get_client(
                             SecureErrorHandler.sanitize_error_message(
                                 e, "HTTP client initialization"
                             )
-                        )
+                        ) from e
 
         return self._client
 

src/contextual_retrieval/contextual_retriever.py

@@ -43,7 +43,7 @@ def __init__(
         config_path: Optional[str] = None,
         llm_service: Optional["LLMOrchestrationService"] = None,
         shared_bm25: Optional[SmartBM25Search] = None,
-    ):
+    ) -> None:
         """
         Initialize contextual retriever.
 
@@ -120,7 +120,7 @@ async def initialize(self) -> bool:
             logger.error(f"Failed to initialize Contextual Retriever: {e}")
             return False
 
-    def _get_session_llm_service(self):
+    def _get_session_llm_service(self) -> "LLMOrchestrationService":
         """
         Get cached LLM service for current retrieval session.
         Uses injected service if available, creates new instance as fallback.
@@ -140,7 +140,7 @@ def _get_session_llm_service(self):
 
         return self._session_llm_service
 
-    def _clear_session_cache(self):
+    def _clear_session_cache(self) -> None:
         """Clear cached connections at end of retrieval session."""
         if self._session_llm_service is not None:
             logger.debug("Clearing session LLM service cache")
@@ -374,7 +374,9 @@ async def _execute_batch_query_searches(
                 self._search_single_query_with_embedding(
                     query, i, embedding, collections, limit
                 )
-                for i, (query, embedding) in enumerate(zip(queries, batch_embeddings))
+                for i, (query, embedding) in enumerate(
+                    zip(queries, batch_embeddings, strict=True)
+                )
             ]
 
             # Execute all searches in parallel
@@ -621,7 +623,7 @@ async def health_check(self) -> Dict[str, Any]:
 
         return health_status
 
-    async def close(self):
+    async def close(self) -> None:
         """Clean up resources."""
         try:
             await self.provider_detection.close()

src/contextual_retrieval/provider_detection.py

@@ -7,7 +7,7 @@
 - No hardcoded weights or preferences
 """
 
-from typing import List, Optional, Dict, Any
+from typing import List, Optional, Dict, Any, TYPE_CHECKING
 from loguru import logger
 from contextual_retrieval.contextual_retrieval_api_client import get_http_client_manager
 from contextual_retrieval.error_handler import SecureErrorHandler
@@ -18,18 +18,21 @@
 )
 from contextual_retrieval.config import ConfigLoader, ContextualRetrievalConfig
 
+if TYPE_CHECKING:
+    from contextual_retrieval.contextual_retrieval_api_client import HTTPClientManager
+
 
 class DynamicProviderDetection:
     """Dynamic collection selection without hardcoded preferences."""
 
     def __init__(
         self, qdrant_url: str, config: Optional["ContextualRetrievalConfig"] = None
-    ):
+    ) -> None:
         self.qdrant_url = qdrant_url
         self._config = config if config is not None else ConfigLoader.load_config()
         self._http_client_manager = None
 
-    async def _get_http_client_manager(self):
+    async def _get_http_client_manager(self) -> "HTTPClientManager":
         """Get the HTTP client manager instance."""
         if self._http_client_manager is None:
             self._http_client_manager = await get_http_client_manager()
@@ -212,7 +215,7 @@ async def get_collection_stats(self) -> Dict[str, Any]:
 
         return stats
 
-    async def close(self):
+    async def close(self) -> None:
         """Close HTTP client."""
         if self._http_client_manager:
             await self._http_client_manager.close()

src/contextual_retrieval/qdrant_search.py

@@ -5,7 +5,7 @@
 existing contextual embeddings created by the vector indexer.
 """
 
-from typing import List, Dict, Any, Optional, Protocol
+from typing import List, Dict, Any, Optional, Protocol, TYPE_CHECKING
 from loguru import logger
 import asyncio
 from contextual_retrieval.contextual_retrieval_api_client import get_http_client_manager
@@ -17,6 +17,9 @@
 )
 from contextual_retrieval.config import ConfigLoader, ContextualRetrievalConfig
 
+if TYPE_CHECKING:
+    from contextual_retrieval.contextual_retrieval_api_client import HTTPClientManager
+
 
 class LLMServiceProtocol(Protocol):
     """Protocol defining the interface required from LLM service for embedding operations."""
@@ -47,12 +50,12 @@ class QdrantContextualSearch:
 
     def __init__(
         self, qdrant_url: str, config: Optional["ContextualRetrievalConfig"] = None
-    ):
+    ) -> None:
         self.qdrant_url = qdrant_url
         self._config = config if config is not None else ConfigLoader.load_config()
         self._http_client_manager = None
 
-    async def _get_http_client_manager(self):
+    async def _get_http_client_manager(self) -> "HTTPClientManager":
         """Get the HTTP client manager instance."""
         if self._http_client_manager is None:
             self._http_client_manager = await get_http_client_manager()
@@ -345,7 +348,7 @@ def get_embeddings_for_queries_batch(
             logger.error(f"Failed to get batch embeddings: {e}")
             return None
 
-    async def close(self):
+    async def close(self) -> None:
         """Close HTTP client."""
         if self._http_client_manager:
             await self._http_client_manager.close()

src/contextual_retrieval/rank_fusion.py

@@ -14,7 +14,7 @@
 class DynamicRankFusion:
     """Dynamic score fusion without hardcoded collection weights."""
 
-    def __init__(self, config: Optional["ContextualRetrievalConfig"] = None):
+    def __init__(self, config: Optional["ContextualRetrievalConfig"] = None) -> None:
         """
         Initialize rank fusion with configuration.
 
@@ -184,7 +184,7 @@ def _reciprocal_rank_fusion(
 
         # Calculate final fused scores
         fused_results: List[Dict[str, Any]] = []
-        for chunk_id, data in chunk_scores.items():
+        for data in chunk_scores.values():
             chunk = data["chunk"].copy()
 
             # Calculate fused RRF score