Files
claude_mac/.claude/tasks/plans/2026-11-14-perl-timeout-group-0030.md
T

2.2 KiB

PLAN — perl-timeout-group (phase 4b-4d residual, GATE 2 LOW 2026-11-13) r1

Scope: hooks/session-start.sh (:39-47), lib/tests/session-digest.test.sh (SD19 area).

DIAGNOSIS: _SS_TMO=(perl -e "alarm shift; exec { \$ARGV[0] } @ARGV" 2) (fallback when neither timeout nor gtimeout is on PATH, stock macOS). alarm's SIGALRM kills the exec'd process only. A child of memory.sh (background job, subshell) inherits stdout/stderr; the callers capture them (:263 $(… 2>&1 >/dev/null) stderr, :320 rows=$(…) stdout), so the command substitution waits for EOF until that child exits: the 2 s bound does not hold. timeout(1) has the same single-process limit only without --kill-after... (GNU timeout signals the child only too, but runs it in its own foreground handling; out of scope: timeout/gtimeout paths unchanged). SD19 (exec sleep 8 stub) passes because the hung process IS the exec'd one. RELATED MEMORY: none bears (no BLK/LRN on perl alarm or process groups); honors BDR-136 spirit (hooks fail open: digest prints unknown on rc 124).

FIX PLAN:

  1. hooks/session-start.sh:45-46: perl runner forks; child setpgrp(0,0) then exec { $ARGV[0] } @ARGV (exit 127 on exec failure); parent setpgrp($pid,$pid) too (closes the race before the child's own call; failure after exec ignored), $SIG{ALRM} → kill 'KILL', -$pid; exit 124; alarm $t; waitpid $pid, 0; exit with the child's status ($? & 127 → 128+signal, else $? >> 8); fork failure → exit 125. Single-quoted perl program (no \$ escapes). Comment :39-40 updated: "perl forks the command into its own process group and kills the group, so a child holding the pipe dies too."
  2. lib/tests/session-digest.test.sh: new SD19b after SD19: memory.sh stub sleep 8 & exec sleep 8… no: ( sleep 8 ) & then sleep 8 (the background child keeps stdout/stderr open after the main process dies); same no-timeout PATH; assert run < 6 s and the digest shows - open: unknown (memory.sh index failed). Flip: old runner → ≥ 8 s, red.
  3. SD19 unchanged (direct hang still bounded). RISK: low. KILL (not TERM) on the group: the bound is the goal, memory.sh read-only calls hold no lock state worth a graceful stop. Linux/macOS perl both have setpgrp/fork/kill negative pid.