{"version":"2.1.288","anchor":"account-memory-write-refusal-flag-renamedrewired-to-account","canonical_anchor":"account-memory-write-refusal-flag-renamedrewired-to-account","heading":"Account memory write refusals now rely on one server marker","tier":"internal","area":"Memory","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288\/e\/account-memory-write-refusal-flag-renamedrewired-to-account","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288","markdown":"### Account memory write refusals now rely on one server marker\n\nClaude Code now uses a single marker for the account memory server when refusing writes from spawned agents\n\n**Unclear.** It is not clear whether any writes are now allowed or refused differently.\n\n**What**\n\nWhen Claude Code sets up tools from MCP servers (Model Context Protocol, a way to connect external tools), it used two separate settings to refuse writes to account memory from spawned agents. It now uses one marker that identifies the account memory server. Refused writes are still recorded in usage data.\n\n**Why**\n\nThis changes how writes to account memory from spawned agents are refused.\n\n- Area: Memory\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}