ci: retain bounded native platform process diagnostics in full candidate

docs/macos-native-diagnostic.md

@@ -20,7 +20,9 @@ Dependencies are the existing Linux/x64 runner, .NET 10 SDK, Git, Bash and Docke
 
 The helper clones Dockur commit `16a5b470cdd601bae8b05b02d748d7edfb36c12e`, verifies its exact Recovery patcher hash, and makes three narrowly verified source edits. The early `rc.cdrom.sh` hook only mounts the existing state share and returns. A same-length XML replacement makes the existing `com.apple.recoveryosd` LaunchDaemon execute `/bin/bash /Volumes/installstate/launch.sh` after boot tasks. The staged `launch.sh` is replaced entirely by the checked-in read-only readiness probe. All replacement counts are exact; an upstream mismatch fails. The two imported QEMU image digests are pinned and the final image/source/Recovery hashes are retained. Other upstream Dockerfile downloads are observed through the resulting image identity rather than asserted to be immutable.
 
-The VM uses TCG (`KVM=N`), slirp networking, a 4-GiB guest, two virtual CPUs and a sparse 64-GiB data disk. Its container has a 6-GiB memory/swap ceiling and a two-CPU limit. The existing Docker daemon must report at least two CPUs and 6 GiB total memory, the runner must have at least 5 GiB available memory, and the Docker filesystem must have at least 8 GiB free before Recovery downloads or boot. Its own native commands have per-command watchdogs and a ten-minute readiness phase; the host orchestrator has a 40-minute deadline and the workflow a 45-minute limit.
+The VM uses TCG (`KVM=N`), slirp networking, a 4-GiB guest, two virtual CPUs and a sparse 64-GiB data disk. Its container has a 6-GiB memory/swap ceiling and a two-CPU limit. The existing Docker daemon must report at least two CPUs and 6 GiB total memory, the runner must have at least 5 GiB available memory, and the Docker filesystem must have at least 8 GiB free before Recovery downloads or boot. Its own native commands retain 45-second watchdogs and a ten-minute readiness phase; the host orchestrator has a 40-minute deadline and the workflow a 45-minute limit.
+
+Actual remote run 4155 stopped at the first `sw_vers` with exit 143 before kernel, process or service probes ran. The updated hook collects native `uname`, root identity, bootargs, guest CPU features and process context first. It logs each child PID and builtin elapsed time, explicitly tags watchdog TERM, and takes two independently five-second-bounded CPU/state/command snapshots during each `sw_vers` attempt. After an initial platform failure it still collects native launchd context and repeats the identical `sw_vers` command once, with the same 45-second limit. A successful native `sw_vers`, native product version and all original identity/service/disk gates remain required. Process state or a retry alone does not establish whether initialization was slow or a service blocked. The upstream AVX2 warning reads host flags; the pinned TCG CPU path configures an Intel guest with AVX/AVX2, so the hook observes actual guest CPU flags without changing host or guest CPU settings.
 
 ## Evidence and cleanup
 

tools/ci/macos-native-readiness.sh

@@ -45,28 +45,59 @@ finish() {
 run_command() {
   local name="$1"
   shift
-  local process timer sleeper exit_code
+  local process timer sleeper exit_code started observer=""
   LAST_OUTPUT="/tmp/native-diagnostic-$name.out"
   printf '\n[proof-command] %s:' "$name" >> "$PROOF_LOG"
   printf ' %s' "$@" >> "$PROOF_LOG"
   printf '\n' >> "$PROOF_LOG"
+  started=$SECONDS
   "$@" > "$LAST_OUTPUT" 2>&1 &
   process=$!
+  printf '[proof-start] %s child=%s shell=%s parent=%s seconds=%s\n' "$name" "$process" "$$" "$PPID" "$started" >> "$PROOF_LOG"
   (
     trap 'kill "$sleeper" 2>/dev/null || :; exit 0' TERM INT
     sleep 45 &
     sleeper=$!
     wait "$sleeper"
+    printf '[proof-timeout] %s child=%s elapsed=%ss signal=TERM\n' "$name" "$process" "$((SECONDS - started))" >> "$PROOF_LOG"
     kill -TERM "$process" 2>/dev/null || :
-    sleep 2
+    sleep 2 & sleeper=$!; wait "$sleeper"
     kill -KILL "$process" 2>/dev/null || :
   ) &
   timer=$!
+  if [[ "$name" = platform || "$name" = platform-warm ]]; then
+    # Observers never extend the independent 45-second command deadline.
+    (
+      local sample_pid="" sample_timer="" pause_pid="" pause sample_exit
+      trap 'kill -KILL "$sample_pid" 2>/dev/null || :; kill -TERM "$sample_timer" "$pause_pid" 2>/dev/null || :; exit 0' TERM INT
+      for pause in 10 15; do
+        sleep "$pause" & pause_pid=$!; wait "$pause_pid"
+        printf '[proof-process] %s child=%s elapsed=%ss fields=pid,ppid,stat,cpu-time,elapsed,cpu-percent,wchan,comm\n' "$name" "$process" "$((SECONDS - started))" >> "$PROOF_LOG"
+        /bin/ps -p "$process" -o pid=,ppid=,stat=,time=,etime=,pcpu=,wchan=,comm= >> "$PROOF_LOG" 2>&1 &
+        sample_pid=$!
+        (
+          local sample_sleeper=""
+          trap 'kill "$sample_sleeper" 2>/dev/null || :; exit 0' TERM INT
+          sleep 5 & sample_sleeper=$!; wait "$sample_sleeper"
+          kill -KILL "$sample_pid" 2>/dev/null || :
+        ) & sample_timer=$!
+        wait "$sample_pid"; sample_exit=$?
+        kill -TERM "$sample_timer" 2>/dev/null || :; wait "$sample_timer" 2>/dev/null || :
+        printf '[proof-process-exit] %s %s\n' "$name" "$sample_exit" >> "$PROOF_LOG"
+        sample_pid=""; sample_timer=""; pause_pid=""
+      done
+    ) & observer=$!
+  fi
   wait "$process"
   exit_code=$?
   kill -TERM "$timer" 2>/dev/null || :
   wait "$timer" 2>/dev/null || :
+  if [ -n "$observer" ]; then
+    kill -TERM "$observer" 2>/dev/null || :
+    wait "$observer" 2>/dev/null || :
+  fi
   /usr/bin/tail -c 524288 "$LAST_OUTPUT" >> "$PROOF_LOG"
+  printf '\n[proof-duration] %s child=%s elapsed=%ss\n' "$name" "$process" "$((SECONDS - started))" >> "$PROOF_LOG"
   printf '\n[proof-exit] %s\n' "$exit_code" >> "$PROOF_LOG"
   LAST_EXIT="$exit_code"
   local size
@@ -75,13 +106,7 @@ run_command() {
   return 0
 }
 
-run_command platform /usr/bin/sw_vers
-(( LAST_EXIT == 0 )) || finish false sw_vers_failed
-run_command version /usr/bin/sw_vers -productVersion
-(( LAST_EXIT == 0 )) || finish false product_version_failed
-os_version=$(cat "$LAST_OUTPUT")
-[[ "$os_version" =~ ^[0-9]+\.[0-9]+(\.[0-9]+)?$ ]] || finish false product_version_invalid
-(( ${os_version%%.*} >= 14 )) || finish false unsupported_macos_version
+# Collect cheap native identity/context before the first framework-dependent probe.
 run_command kernel /usr/bin/uname -a
 (( LAST_EXIT == 0 )) || finish false uname_failed
 run_command architecture /usr/bin/uname -m
@@ -94,14 +119,28 @@ run_command uid /usr/bin/id -u
 uid=$(cat "$LAST_OUTPUT")
 [ "$uid" = 0 ] || finish false recovery_account_not_root
 run_command bootargs /usr/sbin/sysctl kern.bootargs
+run_command cpu /usr/sbin/sysctl machdep.cpu.brand_string machdep.cpu.features machdep.cpu.leaf7_features
 run_command parent /bin/ps -p "$$" -p "$PPID" -o pid=,ppid=,comm=
 run_command processes /bin/ps -axo pid,ppid,comm
+run_command platform /usr/bin/sw_vers
+platform_exit="$LAST_EXIT"
 run_command system /bin/launchctl print system
 system_exit="$LAST_EXIT"
 run_command arbitration /bin/launchctl print system/com.apple.diskarbitrationd
 arbitration_exit="$LAST_EXIT"
 run_command recovery /bin/launchctl print system/com.apple.recoveryosd
 recovery_exit="$LAST_EXIT"
+if (( platform_exit != 0 )); then
+  printf '[proof-retry] sw_vers once after native service context; same 45-second deadline\n' >> "$PROOF_LOG"
+  run_command platform-warm /usr/bin/sw_vers
+  platform_exit="$LAST_EXIT"
+fi
+(( platform_exit == 0 )) || finish false sw_vers_failed
+run_command version /usr/bin/sw_vers -productVersion
+(( LAST_EXIT == 0 )) || finish false product_version_failed
+os_version=$(cat "$LAST_OUTPUT")
+[[ "$os_version" =~ ^[0-9]+\.[0-9]+(\.[0-9]+)?$ ]] || finish false product_version_invalid
+(( ${os_version%%.*} >= 14 )) || finish false unsupported_macos_version
 
 # Bound readiness independently of the host's 40-minute overall deadline.
 readiness_start=$SECONDS