chore(context): refactor for consistency, optimize formatting, and simplify logic

- Cleaned up unnecessary comments in `__all__` definitions for better readability.
- Adjusted indentation and formatting across modules for improved clarity (e.g., long lines, logical grouping).
- Simplified conditional expressions and inline comments for context scoring and ranking.
- Replaced some hard-coded values with type-safe annotations (e.g., `ClassVar`).
- Removed unused imports and ensured consistent usage across test files.
- Updated `test_score_not_cached_on_context` to clarify caching behavior.
- Improved truncation strategy logic and marker handling.

backend/app/services/context/scoring/relevance.py

@@ -85,7 +85,10 @@ class RelevanceScorer(BaseScorer):
             Relevance score between 0.0 and 1.0
         """
         # 1. Check for pre-computed relevance score
-        if isinstance(context, KnowledgeContext) and context.relevance_score is not None:
+        if (
+            isinstance(context, KnowledgeContext)
+            and context.relevance_score is not None
+        ):
             return self.normalize_score(context.relevance_score)
 
         # 2. Check metadata for score
@@ -95,14 +98,19 @@ class RelevanceScorer(BaseScorer):
         if "score" in context.metadata:
             return self.normalize_score(context.metadata["score"])
 
-        # 3. Try MCP-based semantic similarity
+        # 3. Try MCP-based semantic similarity (if compute_similarity tool is available)
+        # Note: This requires the knowledge-base MCP server to implement compute_similarity
         if self._mcp is not None:
             try:
                 score = await self._compute_semantic_similarity(context, query)
                 if score is not None:
                     return score
             except Exception as e:
-                logger.debug(f"Semantic scoring failed, using fallback: {e}")
+                # Log at debug level since this is expected if compute_similarity
+                # tool is not implemented in the Knowledge Base server
+                logger.debug(
+                    f"Semantic scoring unavailable, using keyword fallback: {e}"
+                )
 
         # 4. Fall back to keyword matching
         return self._compute_keyword_score(context, query)
@@ -122,6 +130,9 @@ class RelevanceScorer(BaseScorer):
         Returns:
             Similarity score or None if unavailable
         """
+        if self._mcp is None:
+            return None
+
         try:
             # Use Knowledge Base's search capability to compute similarity
             result = await self._mcp.call_tool(
@@ -129,7 +140,9 @@ class RelevanceScorer(BaseScorer):
                 tool="compute_similarity",
                 args={
                     "text1": query,
-                    "text2": context.content[: self._semantic_max_chars],  # Limit content length
+                    "text2": context.content[
+                        : self._semantic_max_chars
+                    ],  # Limit content length
                 },
             )