Add comprehensive tests for vector/semantic search functionality

- Implement full coverage tests for Embedder model loading and embedding generation
- Add CRUD operations and caching tests for VectorStore
- Include cosine similarity computation tests
- Validate semantic search accuracy and relevance through various queries
- Establish performance benchmarks for embedding and search operations
- Ensure edge cases and error handling are covered
- Test thread safety and concurrent access scenarios
- Verify availability of semantic search dependencies

codex-lens/src/codexlens/config.py

@@ -78,6 +78,11 @@ class Config:
         }
     )
 
+    llm_enabled: bool = False
+    llm_tool: str = "gemini"
+    llm_timeout_ms: int = 300000
+    llm_batch_size: int = 5
+
     def __post_init__(self) -> None:
         try:
             self.data_dir = self.data_dir.expanduser().resolve()