ci: capture native recovery startup context before platform probe

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