Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.271 ·

Agent spawn now tracks whether a background output file can be read back

Spawned agents and subagents now carry an outputFileReadable flag based on which tools the session has available

Group of 2 Under the hood Internal Changes
JSON All of v2.1.271
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
SubagentsArea: what it touches
Internal ChangesKind: in v2.1.271,
Internal ChangesSection of the release

Unclear The finding does not say what condition on session tools makes outputFileReadable true or false, or what breaks if it is set wrong.

What

Agent-spawn call sites now pass a new outputFileReadable field, computed from the session's available tool options, when creating a spawned agent or subagent task. A related caller also sets outputFileUnreadable: true when a corresponding flag is false. This is new state that did not exist before.

Why

This lets Claude Code know upfront whether a spawned agent's background output file can be read back later, rather than discovering it only when the read is attempted.

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 doubtThe finding does not say what condition on session tools makes outputFileReadable true or false, or what breaks if it is set wrong.

See this entry in the whole of v2.1.271 →

Feedback