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/budget/calculator.py

@@ -7,7 +7,7 @@ Integrates with LLM Gateway for accurate counts.
 
 import hashlib
 import logging
-from typing import TYPE_CHECKING, Any, Protocol
+from typing import TYPE_CHECKING, Any, ClassVar, Protocol
 
 if TYPE_CHECKING:
     from app.services.mcp.client_manager import MCPClientManager
@@ -42,10 +42,10 @@ class TokenCalculator:
     """
 
     # Default characters per token ratio for estimation
-    DEFAULT_CHARS_PER_TOKEN = 4.0
+    DEFAULT_CHARS_PER_TOKEN: ClassVar[float] = 4.0
 
     # Model-specific ratios (more accurate estimation)
-    MODEL_CHAR_RATIOS: dict[str, float] = {
+    MODEL_CHAR_RATIOS: ClassVar[dict[str, float]] = {
         "claude": 3.5,
         "gpt-4": 4.0,
         "gpt-3.5": 4.0,