test(ci): make queue guard harness deterministic (#1062)

Co-authored-by: be-coder-08 <[email protected]>

packages/mosaic/framework/tools/git/test-ci-queue-wait-tristate.sh

@@ -9,10 +9,51 @@ WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/ci-queue-wait-tristate}
 REPO_DIR="$WORK_DIR/repo"
 STUB_DIR="$WORK_DIR/stubs"
 AUDIT_LOG="$WORK_DIR/audit/ci-queue-wait.jsonl"
+STATUS_OBSERVED="$WORK_DIR/status-observed"
+CLOCK_LOG="$WORK_DIR/clock.log"
+WATCHDOG_PYTHON="/usr/bin/python3"
+WATCHDOG_SCRIPT="$WORK_DIR/real-clock-watchdog.py"
+WATCHDOG_TIMEOUT_SEC=5
+WATCHDOG_EXIT=90
 FEATURE_BRANCH="fix/rm-03-fixture"
 
+if [[ ! -x "$WATCHDOG_PYTHON" ]]; then
+    echo "FAIL setup: required real-clock watchdog runtime is unavailable at $WATCHDOG_PYTHON" >&2
+    exit 1
+fi
+
 rm -rf "$WORK_DIR"
 mkdir -p "$REPO_DIR" "$STUB_DIR"
+cat > "$WATCHDOG_SCRIPT" <<'PY'
+import os
+import signal
+import subprocess
+import sys
+
+if len(sys.argv) < 3:
+    raise SystemExit(2)
+
+timeout_seconds = float(sys.argv[1])
+process = subprocess.Popen(sys.argv[2:], start_new_session=True)
+try:
+    return_code = process.wait(timeout=timeout_seconds)
+except subprocess.TimeoutExpired:
+    try:
+        os.killpg(process.pid, signal.SIGKILL)
+    except ProcessLookupError:
+        pass
+    process.wait()
+    print(
+        f"FAIL HANG watchdog: subject exceeded {timeout_seconds:g}s "
+        "before completing its intended path",
+        file=sys.stderr,
+    )
+    raise SystemExit(90)
+
+if return_code < 0:
+    raise SystemExit(128 - return_code)
+raise SystemExit(return_code)
+PY
 git -C "$REPO_DIR" init -q
 git -C "$REPO_DIR" checkout -q -b "$FEATURE_BRANCH"
 git -C "$REPO_DIR" remote add origin https://git.example.test/acme/widgets.git
@@ -33,6 +74,9 @@ printf '%s\n' "$url" >> "${MOSAIC_STUB_URL_LOG:?}"
 
 case "$url" in
     */branches/*)
+        if [[ "${MOSAIC_STUB_BRANCH_MODE:-ok}" == "hang-before-provider" ]]; then
+            while :; do :; done
+        fi
         if [[ "${MOSAIC_STUB_BRANCH_MODE:-ok}" == "unreachable" ]]; then
             exit 7
         fi
@@ -44,6 +88,7 @@ case "$url" in
         fi
         ;;
     */status)
+        : > "${MOSAIC_STUB_STATUS_OBSERVED:?}"
         case "${MOSAIC_STUB_STATUS_MODE:?}" in
             success)   printf '%s' '{"state":"success","statuses":[{"status":"success"}]}' ;;
             pending)   printf '%s' '{"state":"pending","statuses":[{"status":"pending","context":"ci/test"}]}' ;;
@@ -63,7 +108,31 @@ case "$url" in
     *) echo "unexpected curl URL: $url" >&2; exit 2 ;;
 esac
 SH
-chmod +x "$STUB_DIR/curl"
+
+cat > "$STUB_DIR/date" <<'SH'
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ "$#" -ne 1 || "$1" != "+%s" ]]; then
+    echo "unexpected date invocation: $*" >&2
+    exit 2
+fi
+
+if [[ -e "${MOSAIC_STUB_STATUS_OBSERVED:?}" ]]; then
+    printf 'date-phase=after-status\n' >> "${MOSAIC_STUB_CLOCK_LOG:?}"
+    printf '1002\n'
+else
+    printf 'date-phase=before-status\n' >> "${MOSAIC_STUB_CLOCK_LOG:?}"
+    printf '1000\n'
+fi
+SH
+
+cat > "$STUB_DIR/sleep" <<'SH'
+#!/usr/bin/env bash
+set -euo pipefail
+printf 'sleep-after-status=%s\n' "$*" >> "${MOSAIC_STUB_CLOCK_LOG:?}"
+SH
+chmod +x "$STUB_DIR/curl" "$STUB_DIR/date" "$STUB_DIR/sleep"
 
 run_guard() {
     local status_mode="$1"
@@ -83,13 +152,46 @@ run_guard() {
             export GITEA_URL=https://git.example.test
             export MOSAIC_STUB_STATUS_MODE="$status_mode"
         fi
+        rm -f "$STATUS_OBSERVED" "$CLOCK_LOG"
         export MOSAIC_STUB_URL_LOG="$WORK_DIR/urls.log"
+        export MOSAIC_STUB_STATUS_OBSERVED="$STATUS_OBSERVED"
+        export MOSAIC_STUB_CLOCK_LOG="$CLOCK_LOG"
         export MOSAIC_CI_QUEUE_AUDIT_LOG="$audit_log"
-        "$SCRIPT_DIR/ci-queue-wait.sh" --purpose "${MOSAIC_TEST_PURPOSE:-push}" -t 0 -i 0 "$@"
+        # Provider observation is the synchronization event. The one-second
+        # timeout is subject semantics under virtual time, never a wall wait.
+        # The absolute Python runtime uses an internal monotonic wait and kills
+        # the subject's isolated process group. Neither operation can resolve
+        # to the virtual date/sleep stubs at the front of PATH.
+        local subject_rc
+        if "$WATCHDOG_PYTHON" "$WATCHDOG_SCRIPT" "$WATCHDOG_TIMEOUT_SEC" \
+            "$SCRIPT_DIR/ci-queue-wait.sh" --purpose "${MOSAIC_TEST_PURPOSE:-push}" -t 1 -i 1 "$@"; then
+            subject_rc=0
+        else
+            subject_rc=$?
+        fi
+        return "$subject_rc"
     )
 }
 
 failures=0
+assert_provider_observed() {
+    local name="$1" require_expiration="${2:-0}"
+    if [[ ! -e "$STATUS_OBSERVED" ]]; then
+        echo "FAIL $name: status provider was not observed" >&2
+        failures=$((failures + 1))
+    fi
+    if [[ ! -s "$CLOCK_LOG" ]] || ! grep -q '^date-phase=before-status$' "$CLOCK_LOG"; then
+        echo "FAIL $name: virtual clock interception did not run before provider observation" >&2
+        failures=$((failures + 1))
+    fi
+    if [[ "$require_expiration" -eq 1 ]]; then
+        if ! grep -q '^sleep-after-status=' "$CLOCK_LOG" || ! grep -q '^date-phase=after-status$' "$CLOCK_LOG"; then
+            echo "FAIL $name: pending path did not expire after provider observation" >&2
+            failures=$((failures + 1))
+        fi
+    fi
+}
+
 run_assertion() {
     local name="$1" expected_rc="$2" status_mode="$3" required_text="$4"
     local output rc
@@ -124,6 +226,13 @@ run_assertion() {
         printf '%s\n' "$output" >&2
         failures=$((failures + 1))
     fi
+    if [[ "$status_mode" != "credential-unresolvable" ]]; then
+        if [[ "$status_mode" == "pending" ]]; then
+            assert_provider_observed "$name" 1
+        else
+            assert_provider_observed "$name"
+        fi
+    fi
 }
 
 set -e
@@ -140,6 +249,27 @@ run_assertion large-payload not126 large-success 'state=terminal-success'
 run_assertion credential-unresolvable zero credential-unresolvable 'CANNOT_ASSERT'
 run_assertion provider-unreachable zero unreachable 'CANNOT_ASSERT'
 
+# Positive liveness control: a subject mutant hangs before the branch lookup
+# can reach the status provider. Only the independent real-clock watchdog may
+# terminate it, and its failure must be distinct from subject timeout rc=124.
+set +e
+watchdog_output=$(MOSAIC_STUB_BRANCH_MODE=hang-before-provider run_guard success "$AUDIT_LOG" 2>&1)
+watchdog_rc=$?
+set -e
+if [[ "$watchdog_rc" -ne "$WATCHDOG_EXIT" ]]; then
+    echo "FAIL watchdog-control: expected hang-specific rc=$WATCHDOG_EXIT, got rc=$watchdog_rc" >&2
+    failures=$((failures + 1))
+fi
+if [[ "$watchdog_output" != *"FAIL HANG watchdog:"* ]]; then
+    echo "FAIL watchdog-control: expected distinct hang-specific diagnostic" >&2
+    printf '%s\n' "$watchdog_output" >&2
+    failures=$((failures + 1))
+fi
+if [[ -e "$STATUS_OBSERVED" ]]; then
+    echo "FAIL watchdog-control: hanging mutant unexpectedly reached the status provider" >&2
+    failures=$((failures + 1))
+fi
+
 if [[ ! -s "$AUDIT_LOG" ]] || ! grep -q '"outcome":"CANNOT_ASSERT"' "$AUDIT_LOG"; then
     echo "FAIL provider-unreachable-audit: expected durable CANNOT_ASSERT JSONL record" >&2
     failures=$((failures + 1))
@@ -160,6 +290,7 @@ if [[ "$merge_unreachable_output" != *"CANNOT_ASSERT"* ]]; then
     echo "FAIL merge-provider-unreachable: expected loud CANNOT_ASSERT diagnostic" >&2
     failures=$((failures + 1))
 fi
+assert_provider_observed merge-provider-unreachable
 merge_audit_lines_after=$(wc -l < "$AUDIT_LOG")
 if [[ "$merge_audit_lines_after" -le "$merge_audit_lines_before" ]]; then
     echo "FAIL merge-provider-unreachable: expected an additional audit record" >&2
@@ -223,6 +354,7 @@ if [[ "$audit_failure_output" != *"audit"* ]]; then
     echo "FAIL audit-unavailable: expected loud audit failure diagnostic" >&2
     failures=$((failures + 1))
 fi
+assert_provider_observed audit-unavailable
 
 if [[ "$failures" -ne 0 ]]; then
     echo "ci-queue-wait tri-state regression failed ($failures assertions)" >&2