feat(memory): implement caching layer for memory operations (#98)

Add comprehensive caching layer for the Agent Memory System:

- HotMemoryCache: LRU cache for frequently accessed memories
  - Python 3.12 type parameter syntax
  - Thread-safe operations with RLock
  - TTL-based expiration
  - Access count tracking for hot memory identification
  - Scoped invalidation by type, scope, or pattern

- EmbeddingCache: Cache embeddings by content hash
  - Content-hash based deduplication
  - Optional Redis backing for persistence
  - LRU eviction with configurable max size
  - CachedEmbeddingGenerator wrapper for transparent caching

- CacheManager: Unified cache management
  - Coordinates hot cache, embedding cache, and retrieval cache
  - Centralized invalidation across all caches
  - Aggregated statistics and hit rate tracking
  - Automatic cleanup scheduling
  - Cache warmup support

Performance targets:
- Cache hit rate > 80% for hot memories
- Cache operations < 1ms (memory), < 5ms (Redis)

83 new tests with comprehensive coverage.

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

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

backend/app/services/memory/cache/__init__.py

@@ -0,0 +1,21 @@
+# app/services/memory/cache/__init__.py
+"""
+Memory Caching Layer.
+
+Provides caching for memory operations:
+- Hot Memory Cache: LRU cache for frequently accessed memories
+- Embedding Cache: Cache embeddings by content hash
+- Cache Manager: Unified cache management with invalidation
+"""
+
+from .cache_manager import CacheManager, CacheStats, get_cache_manager
+from .embedding_cache import EmbeddingCache
+from .hot_cache import HotMemoryCache
+
+__all__ = [
+    "CacheManager",
+    "CacheStats",
+    "EmbeddingCache",
+    "HotMemoryCache",
+    "get_cache_manager",
+]