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/engine.py

@@ -78,12 +78,8 @@ class ContextEngine:
 
         # Initialize components
         self._calculator = TokenCalculator(mcp_manager=mcp_manager)
-        self._scorer = CompositeScorer(
-            mcp_manager=mcp_manager, settings=self._settings
-        )
-        self._ranker = ContextRanker(
-            scorer=self._scorer, calculator=self._calculator
-        )
+        self._scorer = CompositeScorer(mcp_manager=mcp_manager, settings=self._settings)
+        self._ranker = ContextRanker(scorer=self._scorer, calculator=self._calculator)
         self._compressor = ContextCompressor(calculator=self._calculator)
         self._allocator = BudgetAllocator(self._settings)
         self._cache = ContextCache(redis=redis, settings=self._settings)
@@ -274,8 +270,19 @@ class ContextEngine:
                 },
             )
 
+            # Check both ToolResult.success AND response success
+            if not result.success:
+                logger.warning(f"Knowledge search failed: {result.error}")
+                return []
+
+            if not isinstance(result.data, dict) or not result.data.get(
+                "success", True
+            ):
+                logger.warning("Knowledge search returned unsuccessful response")
+                return []
+
             contexts = []
-            results = result.data.get("results", []) if isinstance(result.data, dict) else []
+            results = result.data.get("results", [])
             for chunk in results:
                 contexts.append(
                     KnowledgeContext(
@@ -283,7 +290,9 @@ class ContextEngine:
                         source=chunk.get("source_path", "unknown"),
                         relevance_score=chunk.get("score", 0.0),
                         metadata={
-                            "chunk_id": chunk.get("chunk_id"),
+                            "chunk_id": chunk.get(
+                                "id"
+                            ),  # Server returns 'id' not 'chunk_id'
                             "document_id": chunk.get("document_id"),
                         },
                     )
@@ -312,7 +321,9 @@ class ContextEngine:
         contexts = []
         for i, turn in enumerate(history):
             role_str = turn.get("role", "user").lower()
-            role = MessageRole.ASSISTANT if role_str == "assistant" else MessageRole.USER
+            role = (
+                MessageRole.ASSISTANT if role_str == "assistant" else MessageRole.USER
+            )
 
             contexts.append(
                 ConversationContext(
@@ -346,6 +357,7 @@ class ContextEngine:
             # Handle dict content
             if isinstance(content, dict):
                 import json
+
                 content = json.dumps(content, indent=2)
 
             contexts.append(