Follow Discord
Sweep 02 Oct 2026 · 18:55Z Build v2.1.288 509 read Stable v2.1.285 Latest v2.1.288 Next v2.1.288 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.288 ·

Account memory write refusals now rely on one server marker

Claude Code now uses a single marker for the account memory server when refusing writes from spawned agents

Under the hood Internal Changes
JSON All of v2.1.288
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
MemoryArea: what it touches
Internal ChangesKind: in v2.1.288,
Internal ChangesSection of the release
What

When 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.

Why

This changes how writes to account memory from spawned agents are refused.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not clear whether any writes are now allowed or refused differently.

See this entry in the whole of v2.1.288 →

Feedback