Restarting a compose stack usually means SSHing into a box and remembering the exact flags. This controller takes a stack name and an action from chat or an API call and runs the compose command for you.
Restarting a compose stack usually means SSHing into a box and remembering the exact flags. This controller takes a stack name and an action from chat or an API call and runs the compose command for you.
It reads the current container state first, recreates only the services that actually changed, then tails logs to confirm each one came up. You get a per-service health report back in the same channel, so nobody has to open a terminal to bounce a stack.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Read the running container state and pull the latest compose file before touching anything.
pending
Apply the action with compose, recreating only the services whose image or config changed.
pending
Tail the container logs for the first thirty seconds and report container health back to the caller.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given a stack name and an action, run the matching docker compose command and return a status object with each service's container state and a short log tail.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.