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/__init__.py

@@ -14,11 +14,18 @@ Usage:
         ConversationContext,
         TaskContext,
         ToolContext,
+        TokenBudget,
+        BudgetAllocator,
+        TokenCalculator,
     )
 
     # Get settings
     settings = get_context_settings()
 
+    # Create budget for a model
+    allocator = BudgetAllocator(settings)
+    budget = allocator.create_budget_for_model("claude-3-sonnet")
+
     # Create context instances
     system_ctx = SystemContext.create_persona(
         name="Code Assistant",
@@ -27,6 +34,13 @@ Usage:
     )
 """
 
+# Budget Management
+from .budget import (
+    BudgetAllocator,
+    TokenBudget,
+    TokenCalculator,
+)
+
 # Configuration
 from .config import (
     ContextSettings,
@@ -67,6 +81,10 @@ from .types import (
 )
 
 __all__ = [
+    # Budget Management
+    "BudgetAllocator",
+    "TokenBudget",
+    "TokenCalculator",
     # Configuration
     "ContextSettings",
     "get_context_settings",