Streaming stack is on-demand, not always-on

Measured rather than assumed: the compositor and Sunshine together hold
220 MiB on the 3060 — sway ~112, Sunshine ~108. That card also runs the
local LLM, and with an 11.3 GB model resident on a 12 GB card the free
headroom goes from 992 MiB to 772. Losing a fifth of what is left matters
for KV cache growth, so leaving it running was the wrong default.

sway-headless and sunshine no longer start at boot. `stream on` brings them
up, `stream status` reports state and VRAM, and sunshine-idle-stop.timer
checks every five minutes whether any Moonlight client still holds a
connection to 47984/47989/48010 — stopping the stack after 15 idle minutes
so a forgotten session does not sit on memory the inference stack wants.

Note for future edits: `systemctl --user disable` on a unit dotbot has
symlinked into ~/.config/systemd/user deletes the symlink itself, because
systemd treats it as a linked unit. Re-run ./install after disabling one.

hosts/mainframe/bin/stream

@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+# Start and stop the Moonlight streaming stack on demand.
+#
+# It is not left running because it costs ~220 MiB of VRAM on the 3060 (sway
+# ~112, Sunshine ~108) and that card also holds the local LLM. With an 11.3 GB
+# model resident on a 12 GB card, 220 MiB is roughly a fifth of the remaining
+# headroom — enough to matter for KV cache growth.
+set -euo pipefail
+
+UNIT=sway-headless.service
+IDLE_MINUTES="${STREAM_IDLE_MINUTES:-15}"
+STAMP="${XDG_RUNTIME_DIR:-/tmp}/stream.lastseen"
+
+# A Moonlight client holds connections to the control and RTSP ports.
+clients_connected() {
+  ss -Htn state established '( sport = :47984 or sport = :47989 or sport = :48010 )' 2>/dev/null | grep -q .
+}
+
+vram() {
+  local used total
+  read -r used total < <(nvidia-smi --query-gpu=memory.used,memory.total \
+    --format=csv,noheader,nounits 2>/dev/null | tr -d ',')
+  printf '%s MiB used of %s, %s free' "$used" "$total" "$((total - used))"
+}
+
+case "${1:-status}" in
+  on|start)
+    systemctl --user start "$UNIT"
+    sleep 6
+    date +%s > "$STAMP"
+    printf 'streaming up — pair or connect at https://%s:47990\n' "$(uname -n)"
+    printf 'GPU: %s\n' "$(vram)"
+    ;;
+  off|stop)
+    systemctl --user stop "$UNIT"
+    sleep 3
+    rm -f "$STAMP"
+    printf 'streaming down\nGPU: %s\n' "$(vram)"
+    ;;
+  status)
+    printf 'compositor: %s\nsunshine:   %s\nclients:    %s\nGPU:        %s\n' \
+      "$(systemctl --user is-active "$UNIT")" \
+      "$(systemctl --user is-active sunshine.service)" \
+      "$(clients_connected && echo connected || echo none)" \
+      "$(vram)"
+    ;;
+  --idle-check)
+    # Called from sunshine-idle-stop.timer. Releases the GPU when nobody has
+    # been connected for IDLE_MINUTES, so a forgotten session does not sit on
+    # VRAM the inference stack wants.
+    systemctl --user is-active --quiet "$UNIT" || exit 0
+    if clients_connected; then date +%s > "$STAMP"; exit 0; fi
+    last=$(cat "$STAMP" 2>/dev/null || echo 0)
+    if (( last == 0 )); then date +%s > "$STAMP"; exit 0; fi
+    if (( ($(date +%s) - last) >= IDLE_MINUTES * 60 )); then
+      echo "no Moonlight client for ${IDLE_MINUTES}m; stopping to free the GPU"
+      systemctl --user stop "$UNIT"
+      rm -f "$STAMP"
+    fi
+    ;;
+  *)
+    echo "usage: stream [on|off|status]" >&2; exit 2 ;;
+esac

hosts/mainframe/systemd/sunshine-idle-stop.service

@@ -0,0 +1,7 @@
+[Unit]
+Description=Release the GPU when no Moonlight client is connected
+ConditionHost=mainframe
+
+[Service]
+Type=oneshot
+ExecStart=%h/.dotfiles/hosts/mainframe/bin/stream --idle-check

hosts/mainframe/systemd/sunshine-idle-stop.timer

@@ -0,0 +1,11 @@
+[Unit]
+Description=Check every 5 minutes whether the streaming stack can be shut down
+ConditionHost=mainframe
+
+[Timer]
+OnBootSec=5min
+OnUnitActiveSec=5min
+AccuracySec=30s
+
+[Install]
+WantedBy=timers.target

hosts/mainframe/systemd/sway-headless.service

@@ -18,5 +18,6 @@ ExecStopPost=/usr/bin/systemctl --user stop sunshine.service
 Restart=on-failure
 RestartSec=5s
 
-[Install]
-WantedBy=default.target
+# Deliberately NOT WantedBy=default.target. The 3060 also holds the local LLM,
+# and this stack costs ~220 MiB of VRAM. Start it with `stream on`; the
+# idle-stop timer puts it away again.