{"version":"2.1.288","anchor":"background-command-message-now-says-to-judge-completion-by-t","canonical_anchor":"background-command-message-now-says-to-judge-completion-by-t","heading":"Claude now judges a remote background command finished by its output file's last line","tier":"internal","area":"Sessions","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288\/e\/background-command-message-now-says-to-judge-completion-by-t","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288","markdown":"### Claude now judges a remote background command finished by its output file's last line\n\nFor remote background commands, Claude is now told a command is over when its output file ends with an exit or stop line\n\n**Unclear.** It is not confirmed that the remote host actually writes these closing lines.\n\n**What**\n\nWhen Claude starts a command that runs in the background on a remote machine, Claude Code gives it a note about how to follow it. That note used to say the host machine itself, not the output file, tells whether the command is still running. It now says the command is over when the last line of its output file reads `[exited with code N]` or `[stopped <who or what stopped it>]`. The note still tells Claude not to use `pgrep`, `ps` or `pkill` to check on it.\n\n**Why**\n\nThis changes how Claude decides that a remote background command has finished, so it can look at the output file instead of asking the host.\n\n- Area: Sessions\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}