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 ·

Local command output now records which command produced it, enabling live rendering

Output from local slash commands now carries the command and arguments that produced it, so it can render live instead of as static text

Group of 6 Under the hood Internal Changes
JSON All of v2.1.271
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
Local CommandsArea: what it touches
Internal ChangesKind: in v2.1.271,
Internal ChangesSection of the release

What

  • Local command result messages (local-command-stdout/local-command-stderr) and their internal/wrapper-level equivalents now carry a local_command_run (also called commandRun) field recording {command, args} — the command name and arguments that produced that output — with sensitive arguments redacted as ***.
  • This field round-trips through history replay (toInternalMessages), so it survives session resumption.
  • When this data is present, transcript rendering now uses a new CommandOutputSite/CommandOutput component instead of the static text renderer, enabling progressive, live display of a command's output as it runs.

Why Tracking which command produced a given output line lets Claude Code render that output live, updating as the command runs, instead of only showing it once the command finishes, and preserves that association through session history and replay.

See this entry in the whole of v2.1.271 →

Feedback