Correct the network monitor's description of BLE adapter state

The module documentation said a BLE adapter coming or going was among
the medium changes this module catches, and that the BLE transport
pushes adapter state onto the network-change channel. Neither is true:
the detector is the only source of a network change, and nothing in
the BLE transport sends on that channel. The text now says so, and
names what does exist: on Android the app installs and clears its radio
through the slot the node hands it, which only the BLE transport
observes.

src/node/netmon/mod.rs

@@ -1,11 +1,10 @@
 //! Transport-medium change detection.
 //!
-//! A node that moves between media (WLAN → LAN, WLAN → 5G, a BLE adapter
+//! A node that moves between IP media (WLAN → LAN, WLAN → 5G) would otherwise
-//! coming or going) would otherwise learn about it only as *silence*: the peer
+//! learn about it only as *silence*: the peer sits in the table until
-//! sits in the table until `node.link_dead_timeout_secs` reaps it, and the
+//! `node.link_dead_timeout_secs` reaps it, and the reconnect then waits out
-//! reconnect then waits out whatever backoff the old medium had already
+//! whatever backoff the old medium had already accumulated. The host kernel
-//! accumulated. The host kernel knew within milliseconds; the node would find
+//! knew within milliseconds; the node would find out half a minute later.
-//! out half a minute later.
 //!
 //! This module closes that gap. It samples a coarse [`NetFingerprint`] of the
 //! host's network attachment and publishes a [`NetChange`] on the channel the
@@ -110,9 +109,13 @@
 //! is correct — there is nothing bound to the old path to repair.
 //!
 //! **A BLE adapter's state** is invisible here, as it was before: it is not an
-//! IP attachment at all. That signal comes from the radio (BlueZ properties,
+//! IP attachment at all, and nothing routes it onto this channel. The detector
-//! the Android callback) and belongs on this same channel, pushed by the BLE
+//! below is the only source of a [`NetChange`]; the BLE transport publishes
-//! transport rather than sampled here.
+//! none. On Android the embedder-facing half does exist: the app installs and
+//! clears its radio through the `BleRadioSlot` returned by
+//! `Node::enable_app_owned_ble_radio`, and the BLE transport re-resolves the
+//! slot when it changes. That reaches only the BLE transport. The rest of the
+//! node sees a radio going away as the loss of the links it carried.
 //!
 //! # Where the peer list comes from
 //!