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/allocator.py

@@ -215,9 +215,7 @@ class TokenBudget:
                 "buffer": self.buffer,
             },
             "used": dict(self.used),
-            "remaining": {
-                ct.value: self.remaining(ct) for ct in ContextType
-            },
+            "remaining": {ct.value: self.remaining(ct) for ct in ContextType},
             "total_used": self.total_used(),
             "total_remaining": self.total_remaining(),
             "utilization": round(self.utilization(), 3),
@@ -348,13 +346,11 @@ class BudgetAllocator:
         # Calculate total reclaimable (excluding prioritized types)
         prioritize_values = {ct.value for ct in prioritize}
         reclaimable = sum(
-            tokens for ct, tokens in unused.items()
-            if ct not in prioritize_values
+            tokens for ct, tokens in unused.items() if ct not in prioritize_values
         )
 
         # Redistribute to prioritized types that are near capacity
         for ct in prioritize:
-            ct_value = ct.value
             utilization = budget.utilization(ct)
 
             if utilization > 0.8:  # Near capacity

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,