fix: preserve tester session identity through cleanup (#1873)

packages/cli/tests/case-cleanup-time.test.mjs

@@ -55,8 +55,8 @@ for(const name of scripts)test(`cleanup timing ${name}: inner timeout kills desc
   assert.equal(result.stdout,'');
   assert.equal(result.stderr,'');
   const pairs=result.pairs;
-  assert.equal(pairs.length,2,'the session leader and its live descendant both started');
+  assert.equal(pairs.length,2,'the command and its live descendant both started');
-  assert.equal(pairs[0][0],pairs[0][1],'the command leads its kernel session');
+  assert.notEqual(pairs[0][0],pairs[0][1],'the trusted parent leads the command session');
   assert.notEqual(pairs[1][0],pairs[0][0]);
   assert.equal(pairs[1][1],pairs[0][1],'the descendant belongs to the supervised session');
   assert.deepEqual(result.live,[],'cleanup must kill the whole process tree before namespace teardown');

packages/cli/tests/case-session-identity.test.mjs

@@ -0,0 +1,34 @@
+// No real process is signalled. These hostile kernel-boundary controls expose
+// a new session reusing the old SID after the original leader disappears.
+import {test} from 'node:test';
+import assert from 'node:assert/strict';
+import {readFileSync} from 'node:fs';
+import {spawnSync} from 'node:child_process';
+for(const name of ['case1-accept.sh','case2-unit.sh'])for(const mode of ['already-dead','dies-before-signal'])test(`${name}: ${mode} original session never signals a recycled SID`,()=>{
+ const source=readFileSync(new URL(`../../../scripts/${name}`,import.meta.url),'utf8');
+ const program=/\/usr\/bin\/python3 -I -S -c '\n([\s\S]*?)\n' "\$child"/.exec(source)?.[1];
+ assert.ok(program,'the shipped cleanup program exists');
+ const anchor='\ntry:\n';assert.equal(program.split(anchor).length,2);
+ const control=`
+import atexit, json
+from types import SimpleNamespace
+attempts = []
+checks = 0
+atexit.register(lambda: print(json.dumps(attempts)))
+def observed(pid):
+    global checks
+    if pid == "self/fd/42":
+        checks += 1
+        return (b"T", session) if ${mode==='already-dead'?'False':'checks < 3'} else None
+    return (b"R", session)
+def send(fd, sig):
+    attempts.append([fd, sig])
+    raise PermissionError("never signal a real task")
+fields = observed
+os = SimpleNamespace(listdir=lambda path: ["999"], pidfd_open=lambda pid: 17 if pid == session else 99, close=lambda fd: None)
+signal = SimpleNamespace(SIGKILL=9, SIGCONT=18, pidfd_send_signal=send)
+`;
+ const r=spawnSync('/usr/bin/python3',['-I','-S','-c',program.replace(anchor,'\n'+control+anchor),'424242','42'],{encoding:'utf8'});
+ assert.equal(r.status,1,r.stderr);assert.equal(r.stderr,'');
+ assert.deepEqual(JSON.parse(r.stdout),[],'a stale SID must never authorize a signal');
+});

packages/cli/tests/case-supervisor-cost.test.mjs

@@ -45,24 +45,27 @@ import {mkdtempSync,rmSync} from 'node:fs';
 import {tmpdir} from 'node:os';
 import {join} from 'node:path';
 import {fileURLToPath} from 'node:url';
-for(const name of names)for(const mode of ['reparent','escape','fork','unreadable','unkillable'])test(`${name}: namespace cleanup ${mode}`,t=>{
+for(const name of names)for(const mode of ['reparent','escape','fork','unreadable','unkillable','anchor-death'])test(`${name}: namespace cleanup ${mode}`,t=>{
  const dir=mkdtempSync(join(tmpdir(),'sc-'));t.after(()=>rmSync(dir,{recursive:true,force:true}));
  const r=spawnSync('/usr/bin/unshare',['--user','--map-root-user','--pid','--fork','--kill-child=KILL','--mount-proc',process.execPath,fileURLToPath(new URL('./case-supervisor-session-fixture.mjs',import.meta.url)),fileURLToPath(new URL(`../../../scripts/${name}`,import.meta.url)),dir,mode],{encoding:'utf8',timeout:12000,killSignal:'SIGKILL'});
  assert.equal(r.status,0,r.stderr);assert.equal(r.stderr,'');
  const result=JSON.parse(r.stdout);assert.equal(result.error,undefined);assert.equal(result.signal,null);
- assert.equal(result.status,['unreadable','unkillable'].includes(mode)?86:81,JSON.stringify(result));
+ assert.equal(result.status,['unreadable','unkillable','anchor-death'].includes(mode)?86:81,JSON.stringify(result));
- assert.equal(result.stdout,'');assert.equal(result.stderr,'');
+ assert.equal(result.stdout,'');
- if(!['unreadable','unkillable'].includes(mode))assert.deepEqual(result.sessionLive,[],'no unrecorded live session member may survive');
+ if(mode==='anchor-death')assert.match(result.stderr,/Killed/);else assert.equal(result.stderr,'');
+ if(!['unreadable','unkillable','anchor-death'].includes(mode))assert.deepEqual(result.sessionLive,[],'no unrecorded live session member may survive');
  if(mode==='fork'){assert.ok(result.pairs.length>10);assert.deepEqual(result.live,[],'fast forks must not survive confirmation scans');return;}
  assert.equal(result.pairs.length,2);
  const [leader,descendant]=result.pairs;
- assert.equal(leader[0],leader[1]);
+ assert.notEqual(leader[0],leader[1]);
+ assert.equal(result.anchor,leader[1],'the trusted command parent reserves the SID');
  if(mode==='escape'){
   assert.equal(descendant[0],descendant[1]);assert.notEqual(descendant[1],leader[1]);
   assert.deepEqual(result.live,[descendant[0]],'recorded gap: a new session survives; namespace fixture removes it');
  }else{
   assert.equal(descendant[1],leader[1]);
-  if(mode==='reparent'){assert.equal(result.parent,1,'the intermediate parent exited before cleanup');assert.deepEqual(result.live,[],'reparenting must not hide a session member');}
+  if(mode==='anchor-death'){assert.ok(result.live.includes(leader[0]),'lost anchor refuses before signalling a bare SID');}
+  else if(mode==='reparent'){assert.equal(result.parent,1,'the intermediate parent exited before cleanup');assert.deepEqual(result.live,[],'reparenting must not hide a session member');}
   else assert.ok(result.live.includes(descendant[0]),'the refusal control leaves a live member before fixture cleanup');
  }
 });

packages/cli/tests/case-supervisor-session-fixture.mjs

@@ -1,5 +1,5 @@
 // Namespace-local evidence and cleanup. The JSON observation precedes teardown.
-import {readFileSync,writeFileSync,readdirSync} from 'node:fs';
+import {readFileSync,writeFileSync,readdirSync,openSync,closeSync} from 'node:fs';
 import {spawnSync} from 'node:child_process';
 const [script,dir,mode]=process.argv.slice(2),records=dir+'/pids',worker=dir+'/worker.mjs';
 const source=readFileSync(script,'utf8');
@@ -27,11 +27,16 @@ setTimeout(()=>{
  const pid=${mode==='escape'?'child.pid':"Number(readFileSync(record+'.child','utf8').trim())"};
  const sid=p=>Number(readFileSync('/proc/'+p+'/stat','utf8').split(') ').at(-1).split(' ')[3]);
  writeFileSync(record,JSON.stringify([[process.pid,sid(process.pid)],[pid,sid(pid)]]));
+ writeFileSync(record+'.anchor',String(process.ppid));
  writeFileSync(record+'.parent',readFileSync('/proc/'+pid+'/stat','utf8').split(') ').at(-1).split(' ')[1]);
+ if(${JSON.stringify(mode)} === "anchor-death")process.kill(process.ppid,"SIGKILL");
 },100);
 setInterval(()=>{},1000);
 `);
-const result=spawnSync('/bin/bash',['-c',body+'\nexec /bin/bash -c "$TESTER_SUPERVISOR" -- 1 /usr/bin/setsid /usr/bin/sleep "$@"','--','/bin/bash','-c','exec "$@" >/dev/null 2>&1','--',process.execPath,worker],{encoding:'utf8',timeout:8000,killSignal:'SIGKILL'});
+const out=openSync(dir+'/out','w'),err=openSync(dir+'/err','w');
+const result=spawnSync('/bin/bash',['-c',body+'\nexec /bin/bash -c "$TESTER_SUPERVISOR" -- 1 /usr/bin/setsid /usr/bin/sleep "$@"','--','/bin/bash','-c','exec "$@" >/dev/null 2>&1','--',process.execPath,worker],{encoding:'utf8',stdio:['ignore',out,err],timeout:8000,killSignal:'SIGKILL'});
+closeSync(out);closeSync(err);
+result.stdout=readFileSync(dir+'/out','utf8');result.stderr=readFileSync(dir+'/err','utf8');
 let pairs=[];
 try{const text=readFileSync(records,'utf8');pairs=mode==='fork'?text.trim().split('\n').map(JSON.parse):JSON.parse(text);}catch{}
 const live=[];
@@ -45,8 +50,9 @@ for(const pid of readdirSync('/proc').filter(p=>/^[0-9]+$/.test(p))){
   if(Number(words[3])===pairs[0]?.[1]&&!['Z','X'].includes(words[0]))sessionLive.push(Number(pid));
  }catch{}
 }
-let parent;
+let parent,anchor;
+try{anchor=Number(readFileSync(records+".anchor","utf8"));}catch{}
 try{parent=Number(readFileSync(records+'.parent','utf8'));}catch{}
-process.stdout.write(JSON.stringify({sessionLive,parent,status:result.status,signal:result.signal,error:result.error?.message,stdout:result.stdout,stderr:result.stderr,pairs,live}));
+process.stdout.write(JSON.stringify({sessionLive,parent,anchor,status:result.status,signal:result.signal,error:result.error?.message,stdout:result.stdout,stderr:result.stderr,pairs,live}));
 // These PIDs exist only in the private namespace. Never signal them on the host.
 for(const [pid] of pairs)try{process.kill(pid,'SIGKILL');}catch{}

packages/cli/tests/case1-accept.test.mjs

@@ -938,7 +938,7 @@ test("row 195 accept: every in-instance call goes through sudo -u mosaic -H env
   // mos-1326: assert every argv element, not flattened/substr command detection.
   const source=read(SCRIPT);
   const supervisor=source.split("<<'MOSAIC_TESTER_SUPERVISOR'")[1].split('\n').slice(1).join('\n').split('\nMOSAIC_TESTER_SUPERVISOR')[0]+'\n';
-  assert.equal(createHash('sha256').update(supervisor).digest('hex'),'9158cc66c027a901e6751f01de56b92311f08ab804d64f14ec571c9c332642e1');
+  assert.equal(createHash('sha256').update(supervisor).digest('hex'),'52509773fa2bb0701402b8d2454816153e18323cfaa75cb72418b46c4dbb2d34');
   const runner=/LEGACY_COMMAND_RUNNER='([\s\S]*?)'\nlegacy_display_rc/.exec(source)[1];
   const f7=/F7_JS='([\s\S]*?)'\ncheck_f7/.exec(source)[1];
   const raw=read(join(h.hc,'sudo-argv.jsonl')).trim().split('\n').map(line=>JSON.parse(line));

packages/cli/tests/case2-unit.test.mjs

@@ -215,7 +215,7 @@ for(const kind of ['sleep','signals','member']) test(`row253 C4 ${kind} query ha
   refuses(r,/^case2-unit: tester config query inner-timeout\n$/);
   const seconds=readProbeSeconds(read(clock));
   const [queryPid,querySid]=read(queries).trim().split('\n')[0].trim().split(/\s+/).map(Number);
-  assert.equal(queryPid,querySid,`${kind}/${mode}: direct query PID must equal its kernel SID`);
+  assert.notEqual(queryPid,querySid,`${kind}/${mode}: query runs below the trusted session leader`);
   assert.ok(seconds>=4.25&&seconds<5.75,`${kind}/${mode}: inner timer ${seconds}s (wall ${wall}s)`);
   assert.ok(wall>=seconds,`${mode}: the call contains its timer interval`);
   t.diagnostic(`${kind}/${mode}: inner ${seconds}s; wall ${wall}s`);
@@ -261,7 +261,7 @@ test('row253 C4 cleanup budget starts after inventory pass one',()=>{
  const source=read(UNIT);
  const program=/\/usr\/bin\/python3 -I -S -c '\n([\s\S]*?)\n' "\$child"/.exec(source)?.[1];
  assert.ok(program,'fixed cleanup program exists');
- const anchor='try:\n    while True:';
+ const anchor='\ntry:\n';
  assert.equal(program.split(anchor).length,2,'cleanup loop anchor is unique');
  const standins=`
 from types import SimpleNamespace
@@ -272,22 +272,23 @@ clock = time.monotonic()
 def inventory(path):
     global clock
     clock += 1000
-    return ["424242"]
+    return ["999"]
 
 def fake_fields(pid):
-    return (b"R", session) if alive else None
+    return (b"T", session) if pid == "self/fd/42" else ((b"R", session) if alive else None)
 
 def send(fd, sig):
     global alive, kills
-    alive = False
+    if sig == 9:
-    kills += 1
+        alive = False
+        kills += 1
 
 fields = fake_fields
 os = SimpleNamespace(listdir=inventory, pidfd_open=lambda pid: 17, close=lambda fd: None)
-signal = SimpleNamespace(SIGKILL=9, pidfd_send_signal=send)
+signal = SimpleNamespace(SIGKILL=9, SIGCONT=18, pidfd_send_signal=send)
 time = SimpleNamespace(monotonic=lambda: clock, sleep=lambda seconds: None)
 `;
- const r=spawnSync('/usr/bin/python3',['-I','-S','-c',program.replace(anchor,standins+'\n'+anchor)+'\nprint(kills,end="")','424242'],{encoding:'utf8'});
+ const r=spawnSync('/usr/bin/python3',['-I','-S','-c',program.replace(anchor,standins+'\n'+anchor)+'\nprint(kills,end="")','424242','42'],{encoding:'utf8'});
  assert.equal(r.status,0,r.stderr);assert.equal(r.stdout,'1');
 });
 

scripts/case1-accept.sh

@@ -136,12 +136,15 @@ trap 'rm -rf -- "$WORK"' EXIT
 IFS= read -r -d '' TESTER_SUPERVISOR <<'MOSAIC_TESTER_SUPERVISOR' || :
 set +m
 seconds="$1" setsid_bin="$2" sleep_bin="$3"; shift 3
-child="" timer="" verified=0
+child="" timer="" session_ref="" verified=0
 stat_fields() {
-    local pid="$1" raw="" rest
+    local pid="$1" raw="" rest file="/proc/$1/stat"
+    if [ "$pid" = "${child:-}" ] && [ -n "${session_ref:-}" ]; then
+        file="/proc/self/fd/$session_ref/stat"
+    fi
     # EOF is expected: stat has no NUL. Decide on content, not read's status.
-    IFS= read -r -d '' raw 2>/dev/null < "/proc/$pid/stat" || :
+    IFS= read -r -d '' raw 2>/dev/null < "$file" || :
-    [ -n "$raw" ] || { [ -e "/proc/$pid/stat" ] && return 1; return 3; }
+    [ -n "$raw" ] || { [ -e "$file" ] && return 1; return 3; }
     rest="${raw##*) }"
     [ "$rest" != "$raw" ] || return 1
     read -r ST_STATE ST_PARENT ST_GROUP ST_SESSION _ <<< "$rest"
@@ -154,6 +157,7 @@ clean_session() {
 import os, signal, sys, time
 session = int(sys.argv[1])
 until = None
+anchor_fd = None
 
 def fields(pid):
     try:
@@ -177,11 +181,22 @@ def fields(pid):
         raise ValueError("stat")
     return words[0], int(words[3])
 
+def original_leader():
+    # The inherited proc directory refers to the original task, even if its
+    # numeric PID is reused. A live trusted leader keeps this SID allocated.
+    info = fields("self/fd/" + sys.argv[2])
+    if info is None or info[1] != session or info[0] in (b"Z", b"X"):
+        raise ValueError("lost session anchor")
+    return info
+
 try:
+    anchor_fd = os.pidfd_open(session)
+    original_leader()
     while True:
+        original_leader()
         live = False
         for pid in os.listdir("/proc"):
-            if not pid.isdecimal():
+            if not pid.isdecimal() or int(pid) == session:
                 continue
             info = fields(pid)
             if info is None or info[1] != session or info[0] in (b"Z", b"X"):
@@ -194,6 +209,10 @@ try:
                 try:
                     current = fields(pid)
                     if current is not None and current[1] == session and current[0] not in (b"Z", b"X"):
+                        # Check AFTER membership: while the original anchor is
+                        # alive, this SID cannot name a later session. The pidfd
+                        # then prevents task reuse between this check and kill.
+                        original_leader()
                         signal.pidfd_send_signal(fd, signal.SIGKILL)
                 finally:
                     os.close(fd)
@@ -203,7 +222,10 @@ try:
                 info = fields(pid)
                 if info is not None and info[0] not in (b"Z", b"X"):
                     raise
-        if not live:
+        if not live and original_leader()[0] == b"T":
+            # The trusted leader is stopped after waiting for the command.
+            # With all other members dead it may return the saved command code.
+            signal.pidfd_send_signal(anchor_fd, signal.SIGCONT)
             break
         now = time.monotonic()
         # Inventory pass 1 remains outside the 250 ms confirmation budget.
@@ -214,7 +236,10 @@ try:
         time.sleep(0.01)
 except Exception:
     sys.exit(1)
-' "$child"
+finally:
+    if anchor_fd is not None:
+        os.close(anchor_fd)
+' "$child" "$session_ref"
 }
 finish() {
     local rc="$?"
@@ -226,22 +251,35 @@ finish() {
     fi
     # A refused cleanup may leave an unkillable member. Do not hide rc 86
     # behind an unbounded wait; the caller retains its existing outer guard.
-    [ "$rc" = 86 ] || [ -z "$child" ] || wait "$child" 2>/dev/null || :
+    if [ "$rc" != 86 ] && [ -n "$child" ]; then
+        local command_rc=0
+        wait "$child" 2>/dev/null || command_rc=$?
+        [ "$rc" != 0 ] || [ "$command_rc" = 0 ] || rc=87
+    fi
+    [ -z "$session_ref" ] || exec {session_ref}<&-
     if [ -n "$timer" ]; then kill -KILL "$timer" 2>/dev/null || :; wait "$timer" 2>/dev/null || :; fi
     exit "$rc"
 }
 trap finish EXIT
 trap 'exit 88' HUP INT TERM
 "$sleep_bin" "$seconds" & timer=$!
-# Hold the trusted launcher until its session is observed. Even /bin/true
+# The trusted session leader stays alive through cleanup. Copy code runs as
-# cannot exit (and be reaped by bash) before verification. No copy code runs
+# its child; only after cleanup continues the stopped leader does it return
-# in this handshake; set +m ensures setsid need not fork away from child.
+# the saved command status. An open proc directory pins its task identity.
-"$setsid_bin" /bin/bash -c 'kill -STOP "$BASHPID"; exec "$@"' -- "$@" & child=$!
+"$setsid_bin" /bin/bash -c '
+    set +m
+    kill -STOP "$BASHPID"
+    "$@" & command=$!
+    rc=0; wait "$command" 2>/dev/null || rc=$?
+    kill -STOP "$BASHPID"
+    exit "${rc}"
+' -- "$@" & child=$!
+{ exec {session_ref}<"/proc/$child"; } 2>/dev/null || exit 85
 # Allow session creation the whole inner budget, rather than a 200 ms margin.
 while :; do
     rc=0; stat_fields "$child" || rc=$?
     [ "$rc" != 3 ] || exit 85
-    if [ "$rc" = 0 ] && [ "$ST_SESSION" = "$child" ] && [ "$ST_STATE" = T ]; then
+    if [ "$rc" = 0 ] && [ "$ST_SESSION" = "$child" ] && [ "$ST_STATE" = T ] && [ "$ST_PARENT" = "$$" ]; then
         verified=1
         kill -CONT "$child" 2>/dev/null || exit 85
         break
@@ -255,13 +293,15 @@ while :; do
     "$sleep_bin" 0.002
 done
 [ "$verified" = 1 ] || exit 85
-while kill -0 "$child" 2>/dev/null; do
+while :; do
+    rc=0; stat_fields "$child" || rc=$?
+    [ "$rc" = 0 ] || exit 86
+    case "$ST_STATE" in Z|X) exit 86 ;; esac
+    [ "$ST_STATE" != T ] || break
     kill -0 "$timer" 2>/dev/null || exit 81
     "$sleep_bin" 0.01
 done
 kill -0 "$timer" 2>/dev/null || exit 81
-rc=0; wait "$child" || rc=$?
-[ "$rc" = 0 ] || exit 87
 exit 0
 MOSAIC_TESTER_SUPERVISOR
 # row253-supervisor-end

scripts/case2-unit.sh

@@ -228,12 +228,15 @@ fi
 IFS= read -r -d '' TESTER_SUPERVISOR <<'MOSAIC_TESTER_SUPERVISOR' || :
 set +m
 seconds="$1" setsid_bin="$2" sleep_bin="$3"; shift 3
-child="" timer="" verified=0
+child="" timer="" session_ref="" verified=0
 stat_fields() {
-    local pid="$1" raw="" rest
+    local pid="$1" raw="" rest file="/proc/$1/stat"
+    if [ "$pid" = "${child:-}" ] && [ -n "${session_ref:-}" ]; then
+        file="/proc/self/fd/$session_ref/stat"
+    fi
     # EOF is expected: stat has no NUL. Decide on content, not read's status.
-    IFS= read -r -d '' raw 2>/dev/null < "/proc/$pid/stat" || :
+    IFS= read -r -d '' raw 2>/dev/null < "$file" || :
-    [ -n "$raw" ] || { [ -e "/proc/$pid/stat" ] && return 1; return 3; }
+    [ -n "$raw" ] || { [ -e "$file" ] && return 1; return 3; }
     rest="${raw##*) }"
     [ "$rest" != "$raw" ] || return 1
     read -r ST_STATE ST_PARENT ST_GROUP ST_SESSION _ <<< "$rest"
@@ -246,6 +249,7 @@ clean_session() {
 import os, signal, sys, time
 session = int(sys.argv[1])
 until = None
+anchor_fd = None
 
 def fields(pid):
     try:
@@ -269,11 +273,22 @@ def fields(pid):
         raise ValueError("stat")
     return words[0], int(words[3])
 
+def original_leader():
+    # The inherited proc directory refers to the original task, even if its
+    # numeric PID is reused. A live trusted leader keeps this SID allocated.
+    info = fields("self/fd/" + sys.argv[2])
+    if info is None or info[1] != session or info[0] in (b"Z", b"X"):
+        raise ValueError("lost session anchor")
+    return info
+
 try:
+    anchor_fd = os.pidfd_open(session)
+    original_leader()
     while True:
+        original_leader()
         live = False
         for pid in os.listdir("/proc"):
-            if not pid.isdecimal():
+            if not pid.isdecimal() or int(pid) == session:
                 continue
             info = fields(pid)
             if info is None or info[1] != session or info[0] in (b"Z", b"X"):
@@ -286,6 +301,10 @@ try:
                 try:
                     current = fields(pid)
                     if current is not None and current[1] == session and current[0] not in (b"Z", b"X"):
+                        # Check AFTER membership: while the original anchor is
+                        # alive, this SID cannot name a later session. The pidfd
+                        # then prevents task reuse between this check and kill.
+                        original_leader()
                         signal.pidfd_send_signal(fd, signal.SIGKILL)
                 finally:
                     os.close(fd)
@@ -295,7 +314,10 @@ try:
                 info = fields(pid)
                 if info is not None and info[0] not in (b"Z", b"X"):
                     raise
-        if not live:
+        if not live and original_leader()[0] == b"T":
+            # The trusted leader is stopped after waiting for the command.
+            # With all other members dead it may return the saved command code.
+            signal.pidfd_send_signal(anchor_fd, signal.SIGCONT)
             break
         now = time.monotonic()
         # Inventory pass 1 remains outside the 250 ms confirmation budget.
@@ -306,7 +328,10 @@ try:
         time.sleep(0.01)
 except Exception:
     sys.exit(1)
-' "$child"
+finally:
+    if anchor_fd is not None:
+        os.close(anchor_fd)
+' "$child" "$session_ref"
 }
 finish() {
     local rc="$?"
@@ -318,22 +343,35 @@ finish() {
     fi
     # A refused cleanup may leave an unkillable member. Do not hide rc 86
     # behind an unbounded wait; the caller retains its existing outer guard.
-    [ "$rc" = 86 ] || [ -z "$child" ] || wait "$child" 2>/dev/null || :
+    if [ "$rc" != 86 ] && [ -n "$child" ]; then
+        local command_rc=0
+        wait "$child" 2>/dev/null || command_rc=$?
+        [ "$rc" != 0 ] || [ "$command_rc" = 0 ] || rc=87
+    fi
+    [ -z "$session_ref" ] || exec {session_ref}<&-
     if [ -n "$timer" ]; then kill -KILL "$timer" 2>/dev/null || :; wait "$timer" 2>/dev/null || :; fi
     exit "$rc"
 }
 trap finish EXIT
 trap 'exit 88' HUP INT TERM
 "$sleep_bin" "$seconds" & timer=$!
-# Hold the trusted launcher until its session is observed. Even /bin/true
+# The trusted session leader stays alive through cleanup. Copy code runs as
-# cannot exit (and be reaped by bash) before verification. No copy code runs
+# its child; only after cleanup continues the stopped leader does it return
-# in this handshake; set +m ensures setsid need not fork away from child.
+# the saved command status. An open proc directory pins its task identity.
-"$setsid_bin" /bin/bash -c 'kill -STOP "$BASHPID"; exec "$@"' -- "$@" & child=$!
+"$setsid_bin" /bin/bash -c '
+    set +m
+    kill -STOP "$BASHPID"
+    "$@" & command=$!
+    rc=0; wait "$command" 2>/dev/null || rc=$?
+    kill -STOP "$BASHPID"
+    exit "${rc}"
+' -- "$@" & child=$!
+{ exec {session_ref}<"/proc/$child"; } 2>/dev/null || exit 85
 # Allow session creation the whole inner budget, rather than a 200 ms margin.
 while :; do
     rc=0; stat_fields "$child" || rc=$?
     [ "$rc" != 3 ] || exit 85
-    if [ "$rc" = 0 ] && [ "$ST_SESSION" = "$child" ] && [ "$ST_STATE" = T ]; then
+    if [ "$rc" = 0 ] && [ "$ST_SESSION" = "$child" ] && [ "$ST_STATE" = T ] && [ "$ST_PARENT" = "$$" ]; then
         verified=1
         kill -CONT "$child" 2>/dev/null || exit 85
         break
@@ -347,13 +385,15 @@ while :; do
     "$sleep_bin" 0.002
 done
 [ "$verified" = 1 ] || exit 85
-while kill -0 "$child" 2>/dev/null; do
+while :; do
+    rc=0; stat_fields "$child" || rc=$?
+    [ "$rc" = 0 ] || exit 86
+    case "$ST_STATE" in Z|X) exit 86 ;; esac
+    [ "$ST_STATE" != T ] || break
     kill -0 "$timer" 2>/dev/null || exit 81
     "$sleep_bin" 0.01
 done
 kill -0 "$timer" 2>/dev/null || exit 81
-rc=0; wait "$child" || rc=$?
-[ "$rc" = 0 ] || exit 87
 exit 0
 MOSAIC_TESTER_SUPERVISOR
 # row253-supervisor-end