feat(context): implement token budget management (Phase 2)

Add TokenCalculator with LLM Gateway integration for accurate token
counting with in-memory caching and fallback character-based estimation.
Implement TokenBudget for tracking allocations per context type with
budget enforcement, and BudgetAllocator for creating budgets based on
model context window sizes.

- TokenCalculator: MCP integration, caching, model-specific ratios
- TokenBudget: allocation tracking, can_fit/allocate/deallocate/reset
- BudgetAllocator: model context sizes, budget creation and adjustment
- 35 comprehensive tests covering all budget functionality

Part of #61 - Context Management Engine

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/services/context/budget/__init__.py

@@ -3,3 +3,12 @@ Token Budget Management Module.
 
 Provides token counting and budget allocation.
 """
+
+from .allocator import BudgetAllocator, TokenBudget
+from .calculator import TokenCalculator
+
+__all__ = [
+    "BudgetAllocator",
+    "TokenBudget",
+    "TokenCalculator",
+]