fix(runner): job-control noise and timeout grace

CHANGELOG.md

@@ -3,8 +3,10 @@
 ## Unreleased
 
 ### Fixed
-- Coverage propagates execution counts across multiline array literals, quoted strings, heredocs and backslash continuations, including when Bash 3.x records an array assignment on its closing `)`. Parent statement hits no longer mark commands inside command or process substitutions as covered, including within quotes or arrays (#1338)
-- `--exclude-filter` treats a comma in one flag value as part of the test function name. Repeat the flag to exclude several names; the comma-separated `BASHUNIT_EXCLUDE_FILTER` cannot express a literal comma within one configured filter (#1340)
+- Coverage counts every line of a multiline statement: array literals, quoted strings, heredocs and backslash continuations, including the array assignment Bash 3.x records on its closing `)`. A parent statement's hits no longer mark commands inside command or process substitutions as covered, even within quotes or arrays (#1338)
+- `--exclude-filter` keeps a comma as part of the test function name. Repeat the flag to exclude several names. `BASHUNIT_EXCLUDE_FILTER` stays comma-separated, so one of its filters cannot hold a literal comma (#1340)
+- A `--parallel` run no longer replays bash's `child setpgid` warning as the stderr of a file that wrote nothing. Job control puts each test in its own process group, and bash's parent-side `setpgid` loses a harmless race with a child that already exec'd. The child sets the group first, so only the message was ever wrong (#1344)
+- A timed-out test finishes its `tear_down`. The watchdog allowed a flat 0.3s between SIGTERM and SIGKILL, which a loaded machine missed in about one parallel full-suite run in three. It now polls for the body to exit, capped at 2s (#1344)
 
 ## [0.50.1](https://github.com/TypedDevs/bashunit/compare/0.50.0...0.50.1) - 2026-08-22
 

src/console/test_line.sh

@@ -283,11 +283,21 @@ function bashunit::console_results::print_worker_stderr() {
   local test_file="$1"
   local stderr_file="$2"
 
+  # Not the file's output: the worker turns on job control so each test is its
+  # own process group, and bash's parent-side setpgid loses a harmless race
+  # against a child that already exec'd. The child set the group itself before
+  # exec, so the group is right and only the diagnostic is wrong -- but bash
+  # reports every errno except ESRCH, and macOS answers EPERM.
+  local noise='child setpgid ('
+
+  # Nothing but noise means no block at all, so a clean run stays quiet.
+  grep -qv "$noise" "$stderr_file" || return 0
+
   # To stderr, which is where this text came from: on stdout it landed ahead of
   # the document `--output json|junit` promises that stream is, so a worker that
   # wrote anything to stderr -- a failing `set_up`, for one -- made the report
   # unparseable.
   printf "\n%sStderr from %s%s\n" \
     "$_BASHUNIT_COLOR_SKIPPED" "$test_file" "$_BASHUNIT_COLOR_DEFAULT" >&2
-  sed 's/^/|/' "$stderr_file" >&2
+  grep -v "$noise" "$stderr_file" | sed 's/^/|/' >&2
 }

src/runner/exec.sh

@@ -421,7 +421,18 @@ function bashunit::runner::run_with_timeout() {
     kill -0 "$test_pid" 2>/dev/null || exit 0
     : >"$marker_file"
     kill -TERM -"$test_pid" 2>/dev/null
-    sleep 0.3
+    # Poll for the body to go instead of sleeping a flat window. The TERM has to
+    # kill whatever the body blocked on, wake bash, reach the EXIT trap and run
+    # tear_down; a flat 0.3s was a scheduling hiccup, not a grace, and on a
+    # loaded machine the body had not reached tear_down when the SIGKILL landed.
+    # Bounded at 2s so a hook that hangs cannot outlive the run, and the common
+    # case leaves as soon as the body is reaped -- sooner than the old sleep.
+    grace_ticks=0
+    while [ "$grace_ticks" -lt 20 ]; do
+      kill -0 "$test_pid" 2>/dev/null || break
+      sleep 0.1
+      grace_ticks=$((grace_ticks + 1))
+    done
     kill -KILL -"$test_pid" 2>/dev/null
   ) </dev/null >/dev/null 2>&1 &
   local watchdog_pid=$!

tests/acceptance/bashunit_timeout_test.sh

@@ -119,3 +119,26 @@ function test_bashunit_runs_tear_down_for_a_timed_out_test() {
   assert_file_exists "$marker.setup"
   assert_file_exists "$marker.teardown"
 }
+
+# The watchdog gave the body a flat 0.3s between its SIGTERM and its SIGKILL,
+# which is a scheduling hiccup, not a grace: on a loaded machine the body had
+# not even reached tear_down yet, and the #1324 test above failed about one
+# parallel full-suite run in three. A tear_down slower than that flat window is
+# the deterministic form of the same miss.
+function test_bashunit_waits_for_a_slow_tear_down_of_a_timed_out_test() {
+  local dir fixture marker
+  dir="$(bashunit::temp_dir timeout_slow_teardown)"
+  fixture="$dir/hanging_test.sh"
+  marker="$dir/marker"
+  {
+    printf 'function tear_down() { sleep 1; : >"$TIMEOUT_MARKER.teardown"; }\n'
+    printf 'function test_hangs() { sleep 30; assert_true true; }\n'
+  } >"$fixture"
+
+  local output
+  output="$(TIMEOUT_MARKER="$marker" ./bashunit --no-parallel --env "$TEST_ENV_FILE" \
+    --test-timeout 1 "$fixture")" || true
+
+  assert_contains "Test timed out after 1s" "$output"
+  assert_file_exists "$marker.teardown"
+}

tests/unit/console/results_test.sh

@@ -885,3 +885,27 @@ function test_tap_line_unknown_type_is_not_ok() {
 
   assert_same "not ok 9 - Something odd" "$out"
 }
+
+function test_worker_stderr_drops_bash_job_control_noise() {
+  local stderr_file out
+  stderr_file=$(bashunit::temp_file worker_stderr)
+  printf '%s\n' \
+    './src/runner/exec.sh: child setpgid (68809 to 68809): Operation not permitted' \
+    'diagnostic written by the file under test' >"$stderr_file"
+
+  out=$(bashunit::console_results::print_worker_stderr "some_test.sh" "$stderr_file" 2>&1)
+
+  assert_contains "diagnostic written by the file under test" "$out"
+  assert_not_contains "child setpgid" "$out"
+}
+
+function test_worker_stderr_block_is_omitted_when_only_job_control_noise() {
+  local stderr_file out
+  stderr_file=$(bashunit::temp_file worker_stderr)
+  printf '%s\n' \
+    './src/runner/exec.sh: child setpgid (1 to 1): Operation not permitted' >"$stderr_file"
+
+  out=$(bashunit::console_results::print_worker_stderr "some_test.sh" "$stderr_file" 2>&1)
+
+  assert_empty "$out"
+}