ubicloud: the remote session file is per runner invocation and setsid is optional on the image

Two watched commands on one VM wrote the same ~/.ubirun-<phase>.sid, so a cancel
could end the other's session; the file now carries the runner's pid and is
removed when the command ends. An image without setsid runs the command through
plain bash instead of failing with exit 127.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

scripts/ubicloud/ubi-runner.sh

@@ -182,13 +182,13 @@ mtime() { stat -c %Y "$1" 2>/dev/null || stat -f %m "$1"; }
 # sq STRING: STRING as one single-quoted shell word.
 sq() { printf "'%s'" "$(printf %s "$1" | sed "s/'/'\\\\''/g")"; }
 
-# remote_cancel NAME PHASE: end the session a watched PHASE started on the VM
-# (its leader pid is in ~/.ubirun-PHASE.sid there), bounded to 20 seconds.
-# Killing the local ssh client alone leaves a silent remote command running
-# until it next writes to the closed channel.
+# remote_cancel NAME SIDFILE: end the session a watched command started on the
+# VM (its leader pid is in SIDFILE there), bounded to 20 seconds. Killing the
+# local ssh client alone leaves a silent remote command running until it next
+# writes to the closed channel.
 remote_cancel() {
-  local name=$1 phase=$2 cpid i=0
-  remote "$name" "sid=\$(cat ~/.ubirun-$phase.sid 2>/dev/null); [ -z \"\$sid\" ] || { pkill -TERM -s \"\$sid\"; sleep 2; pkill -KILL -s \"\$sid\"; }; true" >/dev/null 2>&1 </dev/null &
+  local name=$1 sidf=$2 cpid i=0
+  remote "$name" "sid=\$(cat $sidf 2>/dev/null); [ -z \"\$sid\" ] || { pkill -TERM -s \"\$sid\"; sleep 2; pkill -KILL -s \"\$sid\"; }; true" >/dev/null 2>&1 </dev/null &
   cpid=$!
   while kill -0 "$cpid" 2>/dev/null && [ "$i" -lt 20 ]; do sleep 1; i=$(( i + 1 )); done
   kill "$cpid" 2>/dev/null || true
@@ -201,14 +201,17 @@ remote_cancel() {
 # RUN_TIMEOUT seconds in total: exit 124, reason and the last 40 lines on
 # stderr. The ssh runs in its own session (python3's setsid) so the watchdog
 # kills it and anything it started, not just the shell that launched it; on
-# the VM the command runs in its own session too, whose leader pid is written
-# to ~/.ubirun-PHASE.sid so remote_cancel can end it when the client is killed.
+# the VM the command runs in its own session too (setsid where the image has
+# it), whose leader pid is written to ~/.ubirun-PHASE-<runner pid>.sid so
+# remote_cancel can end it when the client is killed.
 watched() {
-  local name=$1 phase=$2 cmd=$3 out pid rc=0 start now last_beat idle elapsed why="" old_traps
+  local name=$1 phase=$2 cmd=$3 out pid rc=0 start now last_beat idle elapsed why="" old_traps inner sidf
+  sidf="~/.ubirun-$phase-$$.sid"
   load "$name"
   out="$(state_dir "$name")/$phase.log"
   : >"$out"
-  cmd="setsid -w bash -c $(sq "printf %s \$\$ >~/.ubirun-$phase.sid; $cmd")"
+  inner=$(sq "printf %s \$\$ >$sidf; $cmd")
+  cmd="if command -v setsid >/dev/null 2>&1; then setsid -w bash -c $inner; else bash -c $inner; fi; rc=\$?; rm -f $sidf; exit \$rc"
   # The caller's stdin is handed to the background ssh explicitly (a background
   # job in a non-interactive shell would otherwise read /dev/null), so piped
   # input reaches the remote command as it did before the watchdog.
@@ -244,7 +247,7 @@ watched() {
       kill -TERM -- "-$pid" 2>/dev/null || kill "$pid" 2>/dev/null || true
       wait "$pid" 2>/dev/null || true
       trap - INT TERM; eval "$old_traps"
-      remote_cancel "$name" "$phase"
+      remote_cancel "$name" "$sidf"
       return 124
     fi
     if [ "$HEARTBEAT" -gt 0 ] && [ $(( now - last_beat )) -ge "$HEARTBEAT" ]; then