Assistant confirms a command from the values it set, without a second round

run_turn takes answer_tools: false ends the turn once the tools have
answered. The assistant node uses it and says what was set ("Kitchen light
off, living room light off."), which saves one model round, about 1.1 s on
the P100. A turn without a call still streams the model's own words.

rebuild-frontend keeps the running stack's FRONTEND_HOST, so the token
issuer no longer flips between the LAN address and app.localhost.

docs/reference/node-types.md

@@ -430,7 +430,7 @@ on what is wired to it.
 
 | Output | Type | Notes |
 |---|---|---|
-| `reply` | `str` | the answer, one sentence at a time while the model writes it |
+| `reply` | `str` | what was set, as "Kitchen light off.", or the answer, one sentence at a time while the model writes it |
 | `actions` | `list` | one record per value set: `message`, `value`, `applied`, `delay_s`, `call` |
 | any other | `bool`, `int`, `float` or `str` | a **target**: one tool, named after its port, taking a `value` of its type |
 
@@ -443,7 +443,8 @@ It asks the provider set under **Settings → Assistant**. As for Wren, the
 wiring is the allowlist: the model is offered the targets and nothing else,
 never the tools the chat's assistant uses. Its instructions list the context
 inputs and what each target holds now. A target is set the moment the model
-calls its tool, and a request may take three rounds of tool calls.
+calls its tool. The reply then names what was set ("Living room light on,
+living room setpoint to 22."), so the model is asked once per request.
 
 Every request ends in a reply: