perf: cache ChromaDB PersistentClient instead of re-instantiating per call

The MCP server previously created a new PersistentClient on every tool
call via _get_collection(). This incurs HNSW index loading overhead
on each request.

Cache the client and collection at module level. The cache resets
naturally on process restart (MCP runs as a subprocess).

Also adds a _reset_mcp_cache fixture to conftest.py for test isolation.

Includes test infrastructure from PR #131.
92 tests pass.

tests/conftest.py

@@ -34,6 +34,19 @@ from mempalace.config import MempalaceConfig  # noqa: E402
 from mempalace.knowledge_graph import KnowledgeGraph  # noqa: E402
 
 
+@pytest.fixture(autouse=True)
+def _reset_mcp_cache():
+    """Reset the MCP server's cached ChromaDB client/collection between tests."""
+    yield
+    try:
+        from mempalace import mcp_server
+
+        mcp_server._client_cache = None
+        mcp_server._collection_cache = None
+    except (ImportError, AttributeError):
+        pass
+
+
 @pytest.fixture(scope="session", autouse=True)
 def _isolate_home():
     """Ensure HOME points to a temp dir for the entire test session.