hive-bash-mcp: publish each task's status and output to the swarm queue

docs/4-implementation/agent-tools/bash.md

@@ -78,6 +78,29 @@ unread rooms. An inline `wait_seconds` / `status` observation that already
 delivered the result instead clears the keyed todo, so no redundant
 loose-end follows.
 
+### Status and output the swarm sees
+
+The daemon also tells the swarm about each task, so the swarm UI can list the
+running ones and read their output without calling the agent
+(`swarm_wire::bash_task`; the bucket, the stream and the grants are in
+[`controller.md`](../swarm/controller.md)). It publishes as the agent, over the
+connection `swarm_queue_client::agent_publisher` makes with the agent's own
+queue credential, and publishes nothing in a container without a queue address
+or a secret store. Everything is best-effort: a failed connect or publish is a
+log line, and a task never waits on the queue.
+
+- **Status.** The runner writes a task file at every state change, and each
+  write also publishes the task's state to `$KV.bash-task-status.<agent>.<task>`.
+  While a task is `pending` or `running`, the publish task repeats it every 60
+  seconds, so a daemon that died reads as stale. A finished task leaves that
+  repeat.
+- **Output.** A task's output goes to files, so while it runs the daemon reads
+  what the files gain twice a second and publishes it as rows on
+  `$SWARM.term.<agent>.bash.<task>`, each with the `Swarm-Stream` header
+  (`stdout` or `stderr`). A chunk never splits a character, and one larger than
+  the queue's payload limit goes out in pieces. When the process exits, the daemon
+  publishes what the files still hold before it writes the final status.
+
 ## Relationship to the `execution` permission
 
 `Permission::Execution` (in `Permission::DEFAULT`) is the real gate on bash:

docs/4-implementation/swarm/controller.md

@@ -202,8 +202,7 @@ goes to `$SWARM.term.<agent>.bash.<task>`, with a `Swarm-Stream` header of `stdo
 `stderr`, into the stream `term-bash-<agent>` that swarm-controller creates for every declared
 agent, for 24 hours or 64 MiB like the subagent rows. The agent's credential may publish
 `$KV.bash-task-status.<agent>.*` and `$SWARM.term.<agent>.bash.>` and nothing else of
-JetStream. Only the names, the grants and the two stores exist so far; the bash MCP doesn't
-publish yet.
+JetStream. The bash daemon publishes both (see [`bash.md`](../agent-tools/bash.md)).
 
 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