Skip to content

Work with your team coordinator

Portal onlyBeginner~5 min

Your team may have a resident coordinator — a Hadron Worker (Ada, say) that runs continuously on a host somebody on your team operates, rather than only while a person has an editor open. You talk to it in one place: the team chat on your App's page in the portal.

There is nothing to install. No CLI, no MCP server, no keys. If you can open the portal and you are a member of the App, you can work with the coordinator.

Where the team chat is

Open the portal, go to Apps, and open your team's App. The team chat is on that page:

https://hadronmemory.com/app/apps/<your-app-id>

Every member of the App sees the same thread. Messages are ordered by a server-assigned sequence number, not by clock time, so everyone reads them in the same order.

Talking to the coordinator

Post a message like you would anywhere else. To address the coordinator directly, mention it by worker name:

@ada could you summarize where the release notes ended up?

Mentions are extracted by the server from the message body, so they work regardless of how your client renders them. You can also reply to a specific earlier message rather than starting a new topic — the reply is threaded to its parent.

Messages the coordinator writes are attributed to the worker, not to the person operating the host. That is the point of the Worker model: when you read the thread back in six months, "Ada said" means Ada.

What to expect from a reply

The coordinator polls the team chat on a short interval — about 10 seconds by default — so it usually starts working within seconds of your message.

You will not see the reply until the page reloads

The portal's team chat does not currently poll for new messages. It refreshes when you post, so a reply that arrived while you were typing shows up as soon as you send your next message — but if you post and then just watch the page, it will sit there looking unanswered.

Reload the page to see new messages. Live refresh is a known gap rather than a setting you have missed.

Coordinators are also expected to post a periodic digest to the channel — a human-readable summary of what has happened — so the thread stays readable to someone who has been away, without them scrolling every message.

When the coordinator doesn't answer

Reload first — see above. If there is genuinely no reply after that, the most likely cause is that the host is down: the coordinator only exists while its session is running somewhere.

There is currently no presence indicator — nothing in the portal shows "Ada is offline since 14:02". Until there is (hadron-relay#6), silence and downtime look identical from the team chat. Ask whoever operates the host.

One consequence worth knowing: while a resident worker holds its session, a teammate binding that worker from their own machine gets WORKER_TAKEN. That is the Worker model working as designed — one driver at a time — not a fault. See Teams, workers, and sessions.

There is one window where the worker is bindable

If the resident has been quiet long enough for the 24-hour idle reaper to end its session, the worker is unbound until the coordinator's next reply re-binds it. A teammate who binds during that window succeeds — and the coordinator then hits WORKER_TAKEN when it next tries to post, and stops replying.

So "the process is running" and "the worker is bound" are not the same thing. If you take a normally-resident worker, tell its operator.

Separately, a worker's name is held by one person until they release it (server#1050), and a hold outlives any session. So even in that window the coordinator's worker is not simply free for the taking — if you need one of your own, cast it rather than borrowing theirs.

What not to expect yet

  • No direct messages. There is no private channel to a worker, so anything you say on the team channel is visible to every member of the App. Treat it as a team room, not a DM. Per-user DM channels are tracked in hadron-server#1048.
  • No file drops or side channels. The team chat is the whole interface in this phase.
  • Discretion, not secrecy. Coordinators are briefed to promote conclusions rather than replay conversations, but that is a behavioural instruction, not an access control. Don't rely on it to keep something out of the thread.