feat: the menu suite (R1.1-R1.6, R1.10) and one shared log Konsole for every test run

Scripted menu input and Steamify's own status functions, journals free of duplicates,
--backend status as JSON, an older item shown as (update). The test scripts append to
$TEST_LOG and share one Konsole (common.sh view_start) instead of opening one each;
vmsuite.sh streams its output (sed -u). 36 checks pass.

.claude/skills/vm-install/SKILL.md

@@ -63,7 +63,7 @@ and wait with an until-loop on the log, e.g.
 
 - Refuses an existing `disk.qcow2` without `--force` (asks YES), and a
   running VM (port 2222).
-- Never edit `vminstall.sh` while it runs: bash reads it as it goes.
+- Never edit a script in place while it runs (bash reads it as it goes; Python `open(p,"w")` and editors that rewrite do this). `sed -i` or writing a copy and `mv` swaps the file: the running one keeps its old copy.
 - Don't match your own wait loop with `pgrep -f`/`pkill -f` on a pattern that
   is part of that loop's command line.
 - Mirror 404s during the install are normal for an older ISO (pacman moves

TODO.md

@@ -39,7 +39,7 @@ R2.2 (first desktop login look), H-Real (real Steam Machine).
 - [ ] S1. Framework: `scripts/vmtest.sh` takes suites, resets the VM per block, tallies PASS/FAIL/SKIP,
       prints the skipped manual rows; move the loader matrix under suite `boot`
 - [x] S2. Suite `cli` (55 checks pass): G1-G3, F1-F7 (exit codes, `features.state`, boot-desktop unit)
-- [ ] S3. Suite `menu`: R1.1-R1.6, R1.10 with scripted menu input (`vmrun.sh`) and `vmstate.sh` asserts
+- [x] S3. Suite `menu` (36 checks pass): R1.1-R1.6, R1.10 with scripted menu input (`vmrun.sh`) and `vmstate.sh` asserts
 - [ ] S4. Suite `hw`: H1, H3 (`WIZARD_BIOS_DRY_RUN=1`), H4, H5, R1.7 (`vmcec.sh --no-sleep`)
 - [ ] S5. Suite `installer`: R2.1 (`vminstallsim.sh`)
 - [ ] S6. R1.8 toggle matrix and R1.9 reboot checks (from the skill), as suite `toggles`

scripts/common.sh

@@ -19,3 +19,13 @@ if [[ -z "${VM_SSH_KEY:-}" && -f "$VM_DIR/ssh-key" ]]; then VM_SSH_KEY="$(cat "$
 [[ -n "${VM_SSH_KEY:-}" ]] && VM_SSH_OPTS+=(-i "$VM_SSH_KEY" -o IdentitiesOnly=yes)
 vm_ssh() { ssh -p "$VM_PORT" "${VM_SSH_OPTS[@]}" "$VM_USER@$VM_HOST" "$@"; }
 vm_scp() { scp -q -P "$VM_PORT" "${VM_SSH_OPTS[@]}" "$@"; }
+
+# One Konsole for every test run: it follows $TEST_LOG, which the test scripts append to.
+# Started only when there is a desktop, the run is headless and no such window exists.
+TEST_LOG="${TEST_LOG:-$HOME/vms/test.log}"
+view_start() {
+    [[ -n "${VM_HEADLESS:-}" && -z "${CI:-}" && -n "${WAYLAND_DISPLAY:-}${DISPLAY:-}" ]] && command -v konsole >/dev/null || return 0
+    systemctl --user is-active --quiet vmtest-view 2>/dev/null && return 0
+    mkdir -p "$(dirname "$TEST_LOG")"; touch "$TEST_LOG"
+    systemd-run --user -q --collect --unit=vmtest-view konsole --hold -e tail -n 60 -F "$TEST_LOG" >/dev/null 2>&1 || true
+}

scripts/vmbootloadertest.sh

@@ -42,14 +42,12 @@ stop_vm() {
 }
 start_vm() { stop_vm; cp "$repo/run.sh" "$VM_DIR/run.sh"; (cd "$VM_DIR" && REPO="${REPO:-$repo/../steamify-cachyos}" setsid nohup ./run.sh --fremont > vm.log 2>&1 &); }
 reboot_vm() { gssh 'sudo systemctl reboot' >/dev/null 2>&1; sleep 25; waitssh; }
-# Headless on a desktop: a Konsole following the log (vmtest.sh opens one for all loaders; CI has no desktop).
+view_start   # one shared Konsole (common.sh)
-if [[ -n "${VM_HEADLESS:-}" && -z "${CI:-}${VMTEST_NO_VIEW:-}" && -n "${WAYLAND_DISPLAY:-}${DISPLAY:-}" ]] && command -v konsole >/dev/null; then
-    systemd-run --user -q --collect --unit="vmtest-view-$loader-$$" konsole --hold -e tail -n +1 -F "$log" >/dev/null 2>&1 || true
-fi
 # The guest checks print PASS/FAIL lines; the summary at the end counts them in the log.
 check() { cat; }
 
 {
+printf '\n===== vmbootloadertest.sh %s (%s) =====\n' "$loader" "$(date +%T)"
 if $install; then
     step "install $loader VM in $VM_DIR"
     stop_vm
@@ -112,7 +110,7 @@ b="$(gssh uname -r)"
 
 step "DONE"
 stop_vm
-} 2>&1 | tee "$log" | sed 's/\x1b\[[0-9;]*m//g'
+} 2>&1 | tee "$log" | tee -a "$TEST_LOG" | sed 's/\x1b\[[0-9;]*m//g'
 fails="$(grep -c '^FAIL' "$log")"
 echo; echo "== $loader: $(grep -c '^PASS' "$log") passed, $fails failed (log: $log)"
 grep '^FAIL' "$log"

scripts/vmsuite.sh

@@ -17,18 +17,16 @@ dir="$repo/share/vmtest/$suite"
 [[ -d "$dir" ]] || { echo "No suite $suite (folders in share/vmtest/)" >&2; exit 2; }
 . "$here/common.sh"
 log="$VM_DIR.$suite.log"
-# Headless on a desktop: a Konsole following the log (CI has no desktop; vmtest.sh opens its own).
+view_start   # one shared Konsole (common.sh), headless on a desktop
-if [[ -n "${VM_HEADLESS:-}" && -z "${CI:-}${VMTEST_NO_VIEW:-}" && -n "${WAYLAND_DISPLAY:-}${DISPLAY:-}" ]] && command -v konsole >/dev/null; then
-    systemd-run --user -q --collect --unit="vmsuite-view-$suite-$$" konsole --hold -e tail -n +1 -F "$log" >/dev/null 2>&1 || true
-fi
 {
+printf '\n===== vmsuite.sh %s (%s) =====\n' "$suite" "$(date +%T)"
 for block in "$dir"/*.sh; do
     [[ -z "${ONLY:-}" || "$(basename "$block")" == "$ONLY"* ]] || continue   # ONLY=50: just that block
     printf '\n##### %s %s\n' "$(date +%T)" "$(basename "$block" .sh)"
     "$here/vmreset.sh" --fremont > /tmp/vmsuite-reset.out 2>&1 || { echo "FAIL vmreset.sh failed: $(tail -n 1 /tmp/vmsuite-reset.out)"; continue; }
-    cat "$repo/share/vmtest/prelude.sh" "$block" | vm_ssh -o ConnectTimeout=6 -o LogLevel=ERROR bash -s 2>&1 | sed 's/\x1b\[[0-9;]*m//g'
+    cat "$repo/share/vmtest/prelude.sh" "$block" | vm_ssh -o ConnectTimeout=6 -o LogLevel=ERROR bash -s 2>&1 | sed -u 's/\x1b\[[0-9;]*m//g'
 done
-} 2>&1 | tee "$log"
+} 2>&1 | tee "$log" | tee -a "$TEST_LOG"
 fails="$(grep -c '^FAIL' "$log")"
 echo; echo "== $suite: $(grep -c '^PASS' "$log") passed, $fails failed, $(grep -c '^SKIP' "$log") skipped (log: $log)"
 grep '^FAIL' "$log"

scripts/vmtest.sh

@@ -27,12 +27,7 @@ for l in $advertised; do
     [[ " $tested " == *" $l "* ]] || { echo "FAIL the ISO advertises $l, but there is no test for it (scripts/vmbootloadertest.sh)"; missing=$((missing + 1)); }
 done
 total=$missing
-# No human is needed: headless. One Konsole for all the logs (the loader scripts open none).
+# No human is needed: headless; the scripts share one Konsole (common.sh, $TEST_LOG).
-export VMTEST_NO_VIEW=1
-if [[ -z "$window" && -z "${CI:-}" && -n "${WAYLAND_DISPLAY:-}${DISPLAY:-}" ]] && command -v konsole >/dev/null; then
-    logs=(); for l in "${loaders[@]}"; do logs+=("$HOME/vms/bl-$l.test.log"); done
-    systemd-run --user -q --collect --unit="vmtest-view-$$" konsole --hold -e tail -n +1 -F "${logs[@]}" >/dev/null 2>&1 || true
-fi
 for l in "${loaders[@]}"; do
     "$here/vmbootloadertest.sh" "$l" $install $window > "/tmp/vmtest-$l.out" 2>&1; rc=$?
     sed -n '/^== /,$p' "/tmp/vmtest-$l.out"

share/vmtest/menu/10-r1-menu.sh

@@ -0,0 +1,42 @@
+# R1.1-R1.6, R1.10: the menu on an existing desktop, driven with scripted input (each row builds on the last).
+menu() { printf "$1" | bash /mnt/steamify.sh 2>&1 | sed 's/\x1b\[[0-9;]*m//g'; }
+# R1.1: first-run ticks: everything but Boot into desktop and BIOS
+out=$(menu 'q\n')
+for n in 1 3 4 5 6 7 8 9 10; do grep -qE "^ +$n +[a-z-]+ +\[x\]" <<< "$out" && pass "R1.1 row $n ticked" || fail "R1.1 row $n not ticked"; done
+grep -qE "^ +11 .*\[ \]" <<< "$out" && pass "R1.1 Update BIOS not ticked" || fail "R1.1 Update BIOS ticked"
+grep -q "Boot into: \[gamescope\]" <<< "$out" && pass "R1.1 boots into gamescope by default" || fail "R1.1 boot default is not gamescope"
+# R1.2: everything OK, back in the menu with all on
+out=$(menu '\ny\nm\nq\nn\n')
+grep -q '^\[ERROR\]' <<< "$out" && fail "R1.2 errors: $(grep -m1 '^\[ERROR\]' <<< "$out")" || pass "R1.2 no errors"
+grep -q "^\[OK\]" <<< "$out" && pass "R1.2 applied (the run printed [OK] lines)" || fail "R1.2 printed no [OK] line"
+expect_on gaming theme glyphs single launcher notify cec machine poweroff
+# R1.3: the state (what vmstate.sh prints)
+[[ "$(current_display_manager)" == sddm ]] && [[ -f /etc/sddm.conf.d/10-gamescope-autologin.conf ]] && pass "R1.3 SDDM with autologin" || fail "R1.3 no SDDM autologin"
+n=$(compgen -G "/sys/class/leds/valve-leds*" | wc -l); [[ $n -eq 17 ]] && pass "R1.3 17 LED nodes" || fail "R1.3 $n LED nodes"
+own=$(stat -c %U /sys/class/leds/valve-leds*/brightness 2>/dev/null | sort -u | tr '\n' ' '); [[ "$own" == "$(id -un) " ]] && pass "R1.3 LEDs owned by the user" || fail "R1.3 LED owner: $own"
+[[ $(dkms status | grep -c ': installed') -ge $((3 * $(ls /usr/lib/modules | wc -w))) ]] && pass "R1.3 DKMS installed for every kernel" || fail "R1.3 DKMS: $(dkms status | tr '\n' ';')"
+systemctl is-active --quiet steamos-manager && pass "R1.3 steamos-manager active" || systemctl --user is-active --quiet steamos-manager && pass "R1.3 steamos-manager active (user)" || fail "R1.3 steamos-manager not active"
+# R1.4: nothing to do
+out=$(menu '\nq\n'); grep -qi "already the way you want it" <<< "$out" && pass "R1.4 already the way you want it" || fail "R1.4 message missing"
+# R1.5: re-apply: no errors, no duplicates in the journals
+out=$(menu 'a\ny\nm\nq\nn\n')
+grep -q '^\[ERROR\]' <<< "$out" && fail "R1.5 errors: $(grep -m1 '^\[ERROR\]' <<< "$out")" || pass "R1.5 re-apply without errors"
+dup=""; for f in ~/.local/state/steamify/*; do [ -f "$f" ] && d=$(cut -f1-3 "$f" | sort | uniq -d) && [ -n "$d" ] && dup+="$(basename "$f"): $d; "; done
+[[ -z "$dup" ]] && pass "R1.5 no duplicates in the journals" || fail "R1.5 DUPLICATES $dup"
+# R1.6: --backend status
+ver=$(sed -n 's/^VERSION=//p' /mnt/steamify.sh | head -n 1)
+js=$(bash /mnt/steamify.sh --backend status 2>/dev/null)
+python3 - "$js" "$ver" <<'PY'
+import json, sys
+def r(ok, m): print(("PASS " if ok else "FAIL ") + m)
+try:
+    d = json.loads(sys.argv[1]); r(True, "R1.6 --backend status is valid JSON")
+except Exception as e:
+    r(False, f"R1.6 --backend status is not JSON: {e}"); sys.exit()
+r(sys.argv[2] in json.dumps(d), f"R1.6 the JSON has the current version {sys.argv[2]}")
+PY
+# R1.10: an item older in features.state shows as an update, and the run brings it up to date
+f=~/.local/state/steamify/features.state
+[[ -f "$f" ]] && sed -i 's/^cec=.*/cec=2.1.0/' "$f" && grep -q '^cec=2.1.0' "$f" && pass "R1.10 cec set to 2.1.0" || fail "R1.10 cannot set cec older in $f"
+out=$(menu 'q\n'); grep -q "HDMI-CEC.*(update)" <<< "$out" && pass "R1.10 the menu shows HDMI-CEC (update)" || fail "R1.10 no (update) on HDMI-CEC"
+out=$(menu '\ny\nm\nq\nn\n'); grep -q '^cec=2.1.0' "$f" && fail "R1.10 cec still 2.1.0 after the run" || pass "R1.10 cec brought up to date"