corgi agent continue
corgi agent continue
Let the daemon continue a limited session when its limit is over
Synopsis
A session that hit a usage limit is waiting on a clock, not on you. With this on, the daemon plans a resume from the account's reset time (or the reset in the limit message when those numbers are older than the limit, or a few minutes after an overload), types "continue" once the window is back, and gives up after a few tries if the limit comes straight back.
corgi agent continue on corgi agent continue off corgi agent continue what is set now
The board shows the plan on the key ("continues 14:02"). It types into a terminal, a VS Code terminal or tmux, and into the Claude Code panel through the corgi VS Code extension (macOS: it fills the chat box and presses Return, so VS Code needs Accessibility once).
Typing needs a window in front and an unlocked screen, and a session the daemon runs (corgi agent) has no terminal at all, so on macOS "on" also sets Claude Code's unattended retry mode for every app started from now on (launchctl setenv CLAUDE_CODE_RETRY_WATCHDOG 1, with a five-minute early-lift check and a six-hour ceiling): a session at a usage limit waits out the reset inside the request and carries on, no typing needed. Restart VS Code and the terminals you start sessions from once, so they pick it up. "off" unsets it.
corgi agent continue [on|off] [flags]
Options
-h, --help help for continue
Options inherited from parent commands
--describe Describe contents of corgi-compose file
--dockerContext string Specify docker context to use, can be default,orbctl,colima (default "default")
-l, --exampleList List examples to choose from. Click on any example to download it
-f, --filename string Custom filepath for for corgi-compose
--fromScratch Clean the .corgi/corgi_services folder before running
-t, --fromTemplate string Create corgi service from template url
--fromTemplateName string Create corgi service from template name and url
-g, --global Use global path to one of the services
--interactive Force interactive prompts even when no TTY/agent detected
--isolate string Run this workspace under a named lease: own port block, own database names, own containers
--json Emit machine-readable JSON output
--privateToken string Private token for private repositories to download files
-o, --runOnce Run corgi once and exit
--silent Hide all welcome messages
SEE ALSO
- corgi agent - Keep Claude Code Remote Control running for your corgi workspaces