Serve a machine's models from one shared llama-server

A llama.cpp session had its own `llama-server`: two sessions on one model
held two copies of it in memory, a model change bought a load only that
session benefited from, and the process was a session's to end. A machine's
models are now served by one `llama-server` in **router mode** -- no `-m`,
a preset file naming models and their flags, a child server per model asked
for, and each request routed by its `model` field. So one server per model
with that model's own settings is what a machine runs, while this backend
has one process, one port and one record per machine to keep track of.

The record is the mechanism every other driver already uses, so a restart
adopts it; a session records the same pid in its own directory as
`Detail::Shared`, and `process::signal` refuses to signal one of those --
which is what keeps stopping, deleting or cleaning up after one session
from unloading a model every other session is using. Nothing stops a router
on its own. That is deliberate (a loaded model is minutes of disk) and it is
why the machines tab now has a card per provider that opens its own screen:
how each model is loaded, how many stay in memory, Unload, and Stop.

How a model is *loaded* therefore belongs to the model on its machine rather
than to a session -- context size, GPU layers, threads, slots, speculative
decoding -- written into the preset as llama-server's own argument names.
Saving them re-reads that file, which unloads the model; that is the change
taking effect, and the dialog says so before you save. What stays a
session's is everything that rides on a request, including which tools it
offers: the router hosts one set for the machine and the choice is a filter
applied here, so it costs no reload (2,181 tokens of prompt with all seven,
698 with none).

Verified end to end against the scratch backend and the emulator: two
sessions sharing one loaded model with one child process, a second session
joining it with a 26ms prefill, a backend restart adopting the router and
answering with the prompt cache intact, the same over ssh to this VM, a
model's settings reaching the running server, Unload, and Stop leaving every
session `exited` with no error line.

app/androidApp/src/main/kotlin/com/example/aiapp/MainScreen.kt

@@ -51,6 +51,8 @@ fun MainScreen(
     onSpawn: () -> Unit,
     onImported: (SessionSummary) -> Unit,
     onSettings: () -> Unit,
+    /** One machine's provider, opened from the machines tab. */
+    onProvider: (String, String) -> Unit,
 ) {
     var tab by remember { mutableStateOf(MainTab.Sessions) }
     var refreshToken by remember { mutableIntStateOf(0) }
@@ -144,7 +146,8 @@ fun MainScreen(
             MainTab.Import ->
                 ImportScreen(settings = settings, reloadToken = token, onImported = onImported)
             MainTab.Models -> ModelsScreen(settings = settings, reloadToken = token)
-            MainTab.Machines -> MachinesScreen(settings = settings, reloadToken = token)
+            MainTab.Machines ->
+                MachinesScreen(settings = settings, reloadToken = token, onProvider = onProvider)
         }
     }
 }