{"version":"2.1.277","anchor":"mcp-tools-can-now-background-early-when-a-new-message-arrive","canonical_anchor":"mcp-tools-can-now-background-early-when-a-new-message-arrive","heading":"MCP tool calls can move to the background as soon as a new message arrives","tier":"notice","area":"Background Tasks","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.277\/e\/mcp-tools-can-now-background-early-when-a-new-message-arrive","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.277","markdown":"### MCP tool calls can move to the background as soon as a new message arrives\n\nLong-running MCP tool calls now background immediately when a new message needs the session, not just after a timeout, tracked via a new foregroundCalls registry\n\n**Unclear.** Nothing has been read yet about the `tengu_mcp_tool_auto_backgrounded` gate for this site's account.\n\n**What**\n\n- MCP (Model Context Protocol) tool calls that run long now move to the background as soon as a new message needs to reach the session, instead of waiting for the existing auto-background timeout. The notification shown to the user explains the call was backgrounded so a waiting message could get through, and that the tool call itself was not interrupted and keeps running.\n\n- A new `foregroundCalls` tracker, keyed by session, is registered when an MCP tool call starts (unless it's an inner\/nested call), giving the auto-backgrounding logic visibility into how many calls are currently in the foreground for that session.\n\n- Telemetry for auto-backgrounded MCP calls now records a `trigger` value distinguishing `deliver_message` from `timeout`.\n\n**Why** This keeps a session responsive to new messages even while an MCP tool is still working, instead of forcing a wait for a fixed timeout before the session can move on.\n\n- Area: Background Tasks\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}