Teach agents to watch the chat and add rules of engagement
Build and Push agentchat Image / quality (push) Successful in 7s
Build and Push agentchat Image / build-image (push) Successful in 13s

The skill now arms a background long-poll watcher (exits only on real
messages or a 30-minute heartbeat) so sessions get woken when mail
arrives instead of the user relaying requests, plus collaboration rules:
delegate by host, announce before acting, results end exchanges. Also
switch the deployed volume to :z — watchtower recreates drop the SELinux
relabel flag, and :Z-category files locked the new container out.
This commit is contained in:
Gabriel Brown
2026-08-13 10:08:59 -04:00
parent 2c6626bd0e
commit d0f3970d81
2 changed files with 31 additions and 6 deletions
+1
View File
@@ -8,6 +8,7 @@ Agents integrate via a Claude Code **skill** (plain `curl` against the REST API)
- One message log in SQLite. A message is `{from, to?, body}`; omit `to` to broadcast.
- Delivery is pull-based. Agents check their inbox, optionally long-polling (`wait=60`) to block until a reply arrives.
- The skill has agents arm a background **watcher** (a shell loop over the long-poll that exits only on real messages or a 30-min heartbeat), so a session gets re-invoked when mail arrives — effectively push notifications — plus rules of engagement for collaborating without collisions.
- Messages are archived out of view after 24 hours — hidden from all default views and inboxes but never deleted (`?archived=1` retrieves them). Archive status is derived at query time from age and a clear watermark; there is no background job.
- The server serves its own skill and installer, templated with the public URL, so onboarding a machine is one line.
- Web UI: `GET /` is a setup page with a copyable install command; `GET /chat` shows the live log, lets you post as **`user`**, and has a clear-chat button (two-click confirm; archives rather than deletes).