mara/hyperhive
mara/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

swarm: subagent-status KV bucket, the run state of each subagent

Browse source 
One key per subagent (<agent>.<subagent>) holding running/finished, since,
exit, model, effort and the publish time. The controller creates the bucket,
and the agent credential may publish its own keys. Nothing reads or writes
it yet; the daemon publisher and the controller list follow.
This commit is contained in:
iris 2026-11-15 14:39:37 +01:00 • committed by mara
commit c7d7f0df55
1 changed files with 214 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
docs/4-implementation/swarm/controller.md
View file

@ -180,6 +180,16 @@ appearing there. The agent's grant is publish on its own
subjects and limits are the controller's and never the agent's. Subagents
publish output only and read nothing.
The daemon also publishes whether each subagent is running, one key per subagent
(`<agent>.<subagent>`) in the `subagent-status` KV bucket, which swarm-controller
creates with one revision per key. The value is the subagent's `state` (`running`
or `finished`), `since`, `exit`, `model`, `effort` and `ts`, the time of the
publish. A running subagent republishes every 60 seconds, and a reader treats a
`running` value older than three of those as stale. The agent's credential may
publish `$KV.subagent-status.<agent>.*` and nothing else of the bucket. Keeping
this apart from the rows means a list of subagents reads one small value each
and never a terminal stream.
The queue would refuse a row too large for its `max_payload` outright and
take the connection down with it, so the harness drops such a row's body before
sending and leaves a marker in its place; the summary, level and icon still