Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.221 Home All releases olderv2.1.220 v2.1.222newer

MCP task restore dials lazily-cached servers instead of giving up

You'll notice
Useful3 Signal0
MCP

Resuming a long-running MCP task after a restart now reconnects cached servers instead of failing.

Feature flag
tengu_mcp_discovery_cache Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.221: off

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.221. It isn't a statement about your account. What a flag value here can and cannot tell you

What

Resuming a long-running MCP task after a restart now connects a server that is in the "cached" state on demand, rather than treating it as unavailable.

Details
  • the dial happens within the remaining restore budget, with distinct failure reasons when no session factory is wired and when the dial itself fails
  • restore also detects a server that reconnected on a modern-era protocol revision, which carries no tasks support, and reports the task as unresumable instead of hanging in the poll loop
  • the "cached" state comes from the new MCP discovery cache, gated on tengu_mcp_discovery_cache with an in-source fallback of true
Evidence

server '${e.serverName}' has no MCP session wired

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.221 →