[Use Case] Memory-Powered Customer Support Agent with Short-Term + Long-Term AgentCore Memory

## Use Case Proposal

I'd like to contribute a **Memory-Powered Customer Support Agent** use case demonstrating AgentCore Memory in an end-to-end conversational agent.

### What it demonstrates:
- Short-term memory (session context via events)
- Long-term memory (semantic extraction with CustomerFacts and IssueHistory strategies)
- AgentCore Memory SDK (MemoryClient) with Strands Agents SDK
- Cross-session customer recognition and personalization
- Memory-backed tools for customer history recall, ticket creation, and order lookup

### Technical stack:
- Python + Strands Agents SDK
- AgentCore Memory (create_memory_and_wait, create_event, retrieve_memories)
- Semantic strategies: CustomerFacts, IssueHistory
- Unit tests with pytest

### Location:
02-use-cases/01-conversational-agents/memory-powered-customer-support/

### PR:
https://github.com/awslabs/agentcore-samples/pull/1734

I've followed the contributing guidelines and the 02-use-cases template format.

The proposed use case belongs in 02-use-cases/01-conversational-agents/memory-powered-customer-support/; start by reading the 02-use-cases template and the linked PR #1734. Confirm the example covers the stated short-term and long-term memory behavior, uses pytest as described, and follows the repository's contributing guidelines.

Written by the indexing model from the issue text.