@chrono-meta/fh-gate 2.15.0 → 3.0.0

package/scripts/sim_isolated_run.sh

@@ -46,6 +46,18 @@
 #       same clone, --tools "", no --restricted   → "🐿️"                  (memory PRESENT)
 #   One variable, opposite answers. ([[feedback_instrument_cannot_discriminate_hypotheses]])
 #
+# 🟥 THE SAME FLAG ALSO KILLS `act` MODE'S WRITE PATH — measured 2026-09-03, known-pair.
+#   `--restricted` ignores settings for PERMISSIONS too, not just memory, and `-p` has no TTY to
+#   ask a human — so `act`+`--no-harness` cannot Write/Edit AT ALL, regardless of what the model
+#   decides. Confirmed with one variable (`--restricted` on/off, same prompt, same --tools): Edit
+#   succeeds without it; with it every rep says "The edit was blocked — permission to write to
+#   file.txt wasn't granted." Deterministic, not a race — this is why a real run reads 5/5.
+#   ⇒ A "did not edit" result from `act --no-harness` is NOT evidence the base model chose not to
+#   write. Use `--no-harness` as an observe-mode control (memory presence, per the pair above)
+#   only — never to ask whether a write would have happened. Workaround not built: `--restricted`
+#   still honors an explicit `--settings <file>` (per `claude --help`), so a minimal file carrying
+#   only Write/Edit approval could restore act-mode fidelity here — filed, not implemented.
+#
 # 🟢 AND THE DEFECT IS REUSABLE AS AN INSTRUMENT. `--no-harness` answers a question this repo
 #   asks constantly and usually by eye: **does this behaviour come from FH, or would the base
 #   model have done it anyway?** Run the same prompt with and without the flag; a behaviour that
@@ -69,17 +81,74 @@
 #   FH defect (a normal session has Bash and can `ls`) — but scoring an arm without knowing it
 #   produces a confident zero from a fixture that was never observable.
 #
-# 🟥 PROJECT HOOKS DO NOT RUN IN A DISPOSABLE CLONE — so this runner cannot measure anything
-#   that depends on one. Measured 2026-08-30: an arm copied `.claude/settings.json` into its clone
-#   to make the PreToolUse PriorArt hook live; not one of the three clones grew
-#   `.claude/.prior_art_events.tsv`, while the live repo's copy carries entries from the same hour.
-#   The hook never fired, so the "hook vs no-hook" contrast was HOOK ≡ NOHOOK and either verdict
-#   would have been false. ⇒ Before claiming a hook-dependent result, check the hook's own
-#   evidence file INSIDE the clone; absence of that file invalidates the arm, not the hypothesis.
+# 🟥 PROJECT HOOKS DO RUN IN A DISPOSABLE CLONE — an earlier version of this paragraph said the
+#   opposite, and it was wrong (RETRACTED 2026-09-03). It read: "PROJECT HOOKS DO NOT RUN IN A
+#   DISPOSABLE CLONE … measured 2026-08-30: an arm copied `.claude/settings.json` into its clone to
+#   make the PreToolUse PriorArt hook live; not one of the three clones grew
+#   `.claude/.prior_art_events.tsv`". That absence was read as "hooks never fire here" with NO
+#   control arm whose hook was known to fire — and it narrowed two rounds of the identity-⑤
+#   design (the hook-layer arm was declared unmeasurable). Known pair, 2026-09-03: a PreToolUse
+#   Bash hook that appends to `$CLAUDE_PROJECT_DIR/_hook_evidence.txt`, installed via
+#   `--setup 'cp <settings.json> .claude/settings.json'`, FIRED inside this runner's own clone
+#   (act mode, deny settings.local.json present) and in a bare `claude -p` clone, trusted or not.
+#   Why the 2026-08-30 arm saw nothing — CONFIRMED the same day, one more known pair: with the
+#   real project hook set copied into a clone, an arm asked to build a new mechanism script FOUND
+#   PRIOR ART and never called Write (identity-④ behaviour), so the Write-matched PriorArt hook had
+#   nothing to fire on; an arm forced to Write a new scripts/*.sh produced `.prior_art_events.tsv`
+#   with a FIRE row inside the clone. The stimulus never reached the hook — a hook that is never
+#   triggered looks identical to a hook that cannot run, which is why a control arm whose hook is
+#   KNOWN to fire is mandatory. Signal: tracks/_meta/fh_signal_2026-09-03_runner-hooks-do-fire.md
+#   What SURVIVES from the old paragraph: before claiming a hook-dependent result, check the
+#   hook's own evidence file INSIDE the clone; absence of that file invalidates the ARM, never the
+#   hypothesis. And `--setup` writing an UNTRACKED file (.claude/settings.json is gitignored) is
+#   not contamination — the tree baseline is taken after setup, and git status never sees it.
 #
 # 🟥 CONTROL IS NOT OPTIONAL. Always run at least one arm whose correct answer is "the thing
 #   being measured should NOT fire". An instrument that fires on everything measures nothing
 #   ([[feedback_control_presence_is_not_discrimination]]).
+#
+# ── ⓒ 격리 그라운딩 — 날짜 오염 통제 (six_axis_review_2026-09-04 강화 #3, RECORD ONLY) ──────────
+#   WHY: LiveCodeBench (arXiv 2403.07974) and the contamination-taxonomy literature
+#   (frontier_verification_map_2026-09-04.md §ⓒ) filter benchmark items by RELEASE DATE precisely
+#   because a model can have memorized — not reasoned about — anything published before its
+#   training cutoff. This runner has the same exposure: a sim arm's "correct" answer about a
+#   doc/rule/gate can be recall of that doc's OWN CONTENT (if the doc predates the model's cutoff
+#   and the model happened to see this repo, or a near-identical one, during training) rather than
+#   evidence the harness under test actually delivers the behaviour to a cold session.
+#   THIS IS A RECORDING, NOT A GATE — per CLAUDE.md §Mechanization Boundary, "what the right value
+#   IS" stays judgment; only "was it recorded" is a channel. Below writes two fields per rep to
+#   `<out>/<arm>_r<rep>.meta.tsv` and does NOT compare them or fail a run on their basis:
+#     corpus_head_date   — the clone's HEAD commit date (ISO 8601). PROXY, named honestly: this
+#                          runner cannot resolve which files a given PROMPT actually cites, so it
+#                          records the whole corpus's most recent commit as an upper bound on
+#                          "how fresh could the cited material be", not a per-file citation date.
+#     sim_model / sim_model_cutoff — the `--model` value and a best-effort known cutoff via
+#                          `_model_known_cutoff()` below, `UNKNOWN` when not recorded there. This
+#                          table WILL go stale as new models ship — it is deliberately not treated
+#                          as authoritative; a scoring session should verify the cutoff it cites
+#                          rather than trust this file's guess (§Instrument-Calibration).
+#
+# ── ⓒ 격리 그라운딩 — 일회용 샌드박스 표준 (six_axis_review_2026-09-04 강화 #3) ─────────────────
+#   프런티어 대조표가 "ephemeral wipe-and-reseed 샌드박스(E2B/Modal/Runloop)"를 도입 후보로 든다.
+#   조직 제약상 외부 도구는 보류하고(§도입 후보 3), 이 러너가 "이미 그렇게 동작하는 부분"과
+#   "아닌 부분"을 정직하게 갈라 적는다 — 매번 재발견하지 않도록.
+#
+#   WIPE (매 rep 마다 새로 만든다 — 재사용 없음):
+#     ✅ 이미 참 — 매 rep 이 독립된 `git clone` (§위 "A disposable clone per REP") + 독립된 부모
+#        디렉터리(§L10). 오늘 실행한 실측 (`test_sim_isolated_run_lanes.sh`):
+#          ✅ L10 no clone shares a parent with another (2 clones, 0 co-parented)
+#          ✅ L10b control — 2 clones found (L10 did not pass on an empty set)
+#        (재현: `bash scripts/test_sim_isolated_run_lanes.sh` — 위 두 줄이 그대로 나온다.)
+#   RESEED (팔이 못 보면 안 되는 자산을 클론에서 지운다):
+#     ✅ 이미 참 — ARM_BLIND_PATHS 제거(§아래) + 그 자체가 known-pair 로 검정됨:
+#          ✅ L24 팔 눈가림 자산이 클론에서 제거된다 (히트 >0 → 0)
+#   기계-표면 리셋 (LaunchAgents/crontab/settings — VM 리셋과 달리 "지우고 다시 만들지" 않는다):
+#     🟥 아직 부분 — observe 모드는 도구 자체가 없어 못 건드리고(구조적 예방), act 모드는 실제
+#        변경을 만들고 나서 **탐지**만 한다(§L7). "매 rep 전 기계 상태를 초기화"는 하지 않는다 —
+#        E2B/Modal 급 VM wipe-and-reseed와의 실제 델타는 이 한 줄이다. 진짜 OS 샌드박스가 필요한
+#        이유는 헤더 상단 "WHAT THIS GIVES YOU" 절이 이미 말한다 — 여기서 되풀이하지 않는다.
+#   요약: 파일시스템 코퍼스 축(WIPE+RESEED)은 클론 단위로 이미 wipe-and-reseed다. 기계 표면 축은
+#   아니다 — 탐지기이지 리셋기가 아니다. 이 두 문장이 "샌드박스 표준"의 정직한 전부다.
 
 set -uo pipefail
 
@@ -274,6 +343,16 @@ snapshot() {
   } > "$f"
 }
 
+# ⓒ 날짜 오염 통제 — 기록 전용 헬퍼(§헤더 참조). 판정 아님, 있으면 값·없으면 UNKNOWN.
+# 🟥 이 표는 부패한다(stale) — 새 모델이 나올 때마다 손으로 갱신해야 한다. 여기 적힌 값을
+# «검증됨»으로 인용하지 마라: 이 스크립트 자신이 그렇게 적어두라고 요구한다(§Instrument-Calibration).
+_model_known_cutoff() { # $1=--model 값 → ISO 월 또는 UNKNOWN
+  case "$1" in
+    *sonnet-5*|sonnet) printf '2026-01' ;;   # 이 세션의 시스템 프롬프트가 스스로 적은 값
+    *) printf 'UNKNOWN' ;;
+  esac
+}
+
 echo "── sim_isolated_run ──────────────────────────────────────────────"
 echo "arm=$ARM mode=$MODE model=$MODEL reps=$REPS timeout=${TIMEOUT}s"
 echo "out=$OUTDIR"
@@ -318,6 +397,17 @@ for r in $(seq 1 "$REPS"); do
     continue
   fi
 
+  # ⓒ 날짜 오염 통제 — 기록만, 판정 아님(§헤더). corpus_head_date 는 "프롬프트가 인용하는
+  # 파일들"의 날짜가 아니라 그 상한(코퍼스 전체 HEAD)이다 — 러너는 프롬프트가 무엇을 인용하는지
+  # 모르므로 더 좁게 잴 수 없다. 그렇게 좁혀 적는다.
+  _corpus_date=$(git -C "$WORK" log -1 --format=%cI 2>/dev/null); [ -n "$_corpus_date" ] || _corpus_date="UNKNOWN"
+  _cutoff=$(_model_known_cutoff "$MODEL")
+  {
+    printf 'corpus_head_date\t%s\n' "$_corpus_date"
+    printf 'sim_model\t%s\n' "$MODEL"
+    printf 'sim_model_cutoff\t%s\n' "$_cutoff"
+  } > "$OUTDIR/${ARM}_r${r}.meta.tsv"
+
   # ── 🟥 팔이 읽으면 안 되는 tracked 자산을 «클론 안에서» 제거한다 (2026-09-01) ──────
   # 왜: 얼린 정답지(`scripts/fixtures/knownpair_refusal_48_*`)가 tracked 가 되면서
   #     **모든 팔의 클론에 들어갔다.** 실측 — negative 문항의 핵심 명사구가 그 안에 있다

package/scripts/test_backtick_guard_lanes.sh

@@ -0,0 +1,115 @@
+#!/usr/bin/env bash
+# test_backtick_guard_lanes.sh — known pairs for scripts/backtick_guard.sh. Written BEFORE the detector.
+#
+# WHAT IS BEING GUARDED
+#   A backtick inside a shell DOUBLE-QUOTING CONTEXT — an unquoted heredoc body (`<<EOF`) or a
+#   "double-quoted string" — is command substitution: the text between the backticks is REPLACED by
+#   the command's output. With no such command the output is empty, so the text is DELETED; with one,
+#   foreign content is INSERTED. The sentence stays grammatical (only its subject is gone), the only
+#   signal is one `command not found` line at the top of the output, and every marker/record hook
+#   checks a field's presence, not its completeness.
+#   Measured 7× (2026-08-10 · 2026-09-01 ×3 · 2026-09-02 ×4 — marker, RESULT doc, fh_completed echo ×2)
+#   with a resident memory rule that failed each time because the actor's task had a different NAME
+#   (writing a marker · a failure message · a seal). N≥3 → mechanize (weekly_audit_2026-09-02 HIGH #1).
+#
+#   BT1 — unquoted heredoc body (`<<TAG`, `<<-TAG`; NOT `<<'TAG'` / `<<"TAG"` / `<<\TAG`) containing `
+#   BT2 — double-quoted string containing ` (single-quoted text and `\`` are literal → CLEAN)
+#
+# Surface = the Bash tool call itself (interactively-composed commands), same reasoning as
+# pipe_verdict_guard: every recurrence was in a composed command, none in a shipped file.
+
+set -u
+G="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/backtick_guard.sh"
+pass=0; fail=0
+
+# expect <label> <HIT|CLEAN> <command-string>   (the command text is passed raw via --stdin-raw)
+expect() {
+  local label="$1" want="$2" cmd="$3" out got
+  out=$(printf '%s' "$cmd" | bash "$G" --stdin-raw 2>&1)
+  # want may be HIT · CLEAN · HIT:BT1@2 (rule and line asserted — a hit on the WRONG line is a miss)
+  if printf '%s' "$out" | grep -q 'BACKTICK'; then got=HIT; else got=CLEAN; fi
+  case "$want" in HIT:*) printf '%s' "$out" | grep -q "${want#HIT:BT}" 2>/dev/null; :; esac
+  if [ "$got" = HIT ] && [ "${want%%:*}" = HIT ] && [ "$want" != HIT ]; then
+    local r="${want#HIT:}"; r="${r%@*}"; local l="${want##*@}"
+    printf '%s' "$out" | grep -q "$r L$l " || got="HIT-WRONG($(printf '%s' "$out" | grep -oE 'BT[12] L[0-9]+' | head -1))"
+    [ "$got" = HIT ] && got="$want"
+  fi
+  if [ "$got" = "$want" ]; then
+    printf '  ✅ %-56s %s (expected %s)\n' "$label" "$got" "$want"; pass=$((pass+1))
+  else
+    printf '  ❌ %-56s %s (expected %s)\n' "$label" "$got" "$want"; fail=$((fail+1))
+    printf '     cmd: %s\n     out: %s\n' "$cmd" "$out"
+  fi
+}
+BT='`'   # one backtick, spelled once so the lanes below never carry a live one in double quotes
+NL=$'\n'
+
+echo "[backtick-guard] known pairs"
+echo "-- BT1: unquoted heredoc body --"
+# 2026-09-02 ⓐ — the measured shape: a marker written through an unquoted heredoc so a $VAR expands.
+expect "BT1 measured: marker heredoc"        HIT:BT1@3   "cat > m.marker <<EOF${NL}date: \$TODAY${NL}axis2-evidence: 러너가 ${BT}--keep-blind-paths${BT} 를 삼켰다${NL}EOF"
+expect "BT1 <<-TAG (tab-stripped) form"      HIT   "cat <<-EOF${NL}	note ${BT}x${BT}${NL}	EOF"
+expect "BT1 markdown fence in heredoc"       HIT   "cat > r.md <<EOF${NL}\`\`\`${NL}out${NL}\`\`\`${NL}EOF"
+expect "BT1 second of two heredocs on a line" HIT:BT1@4  "diff <(cat <<'A') <(cat <<B)${NL}${BT}a${BT}${NL}A${NL}${BT}b${BT}${NL}B"
+expect "BT1 quoted <<'EOF' is CLEAN"          CLEAN "cat > m.marker <<'EOF'${NL}evidence: ${BT}--keep-blind-paths${BT} 삼킴${NL}EOF"
+expect "BT1 quoted <<\"EOF\" is CLEAN"        CLEAN "cat <<\"EOF\"${NL}${BT}x${BT}${NL}EOF"
+expect "BT1 escaped <<\\EOF is CLEAN"         CLEAN "cat <<\\EOF${NL}${BT}x${BT}${NL}EOF"
+expect "BT1 backslash-escaped backtick CLEAN" CLEAN "cat <<EOF${NL}see \\${BT}x\\${BT}${NL}EOF"
+expect "BT1 backtick AFTER the body ends"     CLEAN "cat <<EOF${NL}plain${NL}EOF${NL}echo '${BT}later${BT}'"
+expect "BT1 <<< herestring is not a heredoc"  CLEAN "grep -c x <<< 'a ${BT}b${BT}'"
+
+echo "-- BT2: double-quoted string --"
+# 2026-09-02 ⓑ — the measured shape: a completion-log append through echo "…".
+expect "BT2 measured: echo append"            HIT:BT2@1   "echo \"- ✅ 러너 ${BT}sim_isolated_run.sh${BT} 헤더 경고\" >> tracks/_meta/fh_completed.md"
+expect "BT2 failure-message string (09-01)"   HIT   "printf '%s\\n' \"(${BT}nameleak_check.sh gen${BT} 을 써라)\""
+expect "BT2 single quote inside dq is inert"  HIT   "echo \"don't ${BT}x${BT}\""
+expect "BT2 single-quoted is CLEAN"           CLEAN "printf '%s\\n' '- ✅ 러너 ${BT}sim_isolated_run.sh${BT} 헤더' >> log.md"
+expect "BT2 escaped \\\` is CLEAN"             CLEAN "echo \"see \\${BT}x\\${BT}\""
+expect "BT2 dq inside single quotes is CLEAN" CLEAN "echo '\"${BT}x${BT}\"'"
+expect "BT2 sq inside \$( ) inside dq CLEAN"  CLEAN "echo \"\$(printf '%s' '${BT}x${BT}')\""
+expect "BT2 no backtick at all"               CLEAN "echo \"\$(git log -1) done\" && cat <<EOF${NL}plain \$X${NL}EOF"
+expect "BT2 bare backtick outside quotes"     CLEAN "V=${BT}date${BT}; echo ok"   # live command substitution on purpose, not a text context
+
+echo "-- Axis-2 pass 2026-09-03 (challenger, repros executed by the governor) --"
+# A1: the first build stripped single-quoted spans BEFORE matching heredoc operators, so <<'EOF' was
+# never a heredoc — three symptoms from one cause. Each pinned in its real shape.
+expect "A1a quoted body with dq+backtick CLEAN" CLEAN "cat <<'EOF'${NL}axis2-evidence: 메시지 \"use ${BT}x${BT}\" 가 떴다${NL}EOF"
+expect "A1b quoted A then unquoted B: only B" CLEAN "diff <(cat <<'A') <(cat <<B)${NL}${BT}a${BT}${NL}A${NL}plain${NL}B"
+expect "A1c apostrophe in quoted body, then echo" HIT:BT2@4 "cat <<'EOF'${NL}don't${NL}EOF${NL}echo \"${BT}x${BT}\" >> log"
+# A2: a comment's apostrophe must not open a single-quote context that swallows the next line.
+expect "A2 comment apostrophe then echo"      HIT:BT2@2 "# don't re-run this${NL}echo \"${BT}x${BT}\" >> f.md"
+expect "A2 url fragment is not a comment"     HIT:BT2@1 "curl \"https://x/a#frag ${BT}x${BT}\""
+# B3: <<TAG inside a double-quoted string (commit message) opens no heredoc.
+expect "B3 <<EOF in commit message is CLEAN" CLEAN "git commit -m \"docs: prefer <<EOF for markers\"${NL}V=${BT}date${BT}; echo ok"
+# B5: escaped backslash + LIVE backtick.
+expect "B5 \\\\ then live backtick HITs"      HIT:BT1@2 "cat <<EOF${NL}path\\\\${BT}x${BT}${NL}EOF"
+# B2: ANSI-C $'…' with an escaped apostrophe does not end early.
+expect "B2 \$'don\\'t' then dq backtick"      HIT:BT2@1 "echo \$'don\\'t' \"${BT}x${BT}\""
+# B1: backtick inside \$( ) re-entered from dq is live substitution — deliberately NOT flagged.
+expect "B1 backtick inside \$( ) in dq CLEAN"  CLEAN "echo \"\$(echo ${BT}x${BT})\""
+
+echo "-- hook mode: JSON payload in → JSON out (A4: detection is worthless if delivery is 0) --"
+jexp() {  # <label> <expect-substring-in-additionalContext|SILENT> <env> <payload>
+  local label="$1" want="$2" env_="$3" payload="$4" out ctx
+  out=$(printf '%s' "$payload" | env $env_ bash "$G" 2>/dev/null)
+  if [ "$want" = SILENT ]; then
+    if [ -z "$out" ]; then printf '  ✅ %-56s SILENT\n' "$label"; pass=$((pass+1)); else printf '  ❌ %-56s expected SILENT, got: %s\n' "$label" "${out:0:80}"; fail=$((fail+1)); fi
+    return
+  fi
+  ctx=$(printf '%s' "$out" | python3 -c 'import json,sys; d=json.load(sys.stdin); print(d["hookSpecificOutput"]["additionalContext"])' 2>/dev/null)
+  if printf '%s' "$ctx" | grep -q "$want"; then printf '  ✅ %-56s JSON additionalContext carries %s\n' "$label" "$want"; pass=$((pass+1))
+  else printf '  ❌ %-56s no JSON/context (%s)\n' "$label" "${out:0:80}"; fail=$((fail+1)); fi
+}
+P='{"tool_name":"Bash","tool_input":{"command":"echo \"- done `x.sh` ok\""}}'
+jexp "JSON payload → additionalContext"       "BT2 L1" "X=1" "$P"
+jexp "ascii PYTHONIOENCODING still emits"     "BT2 L1" "PYTHONIOENCODING=ascii" "$P"
+jexp "non-Bash tool is SILENT"                SILENT   "X=1" '{"tool_name":"Write","tool_input":{"content":"`x`"}}'
+jexp "unparseable payload is SILENT"          SILENT   "X=1" 'not json'
+
+echo "-- opt-out / payload --"
+expect "noqa exempts"                         CLEAN "echo \"${BT}x${BT}\"  # noqa: backtick"
+expect "empty payload"                        CLEAN ""
+
+echo
+echo "[backtick-guard] $pass passed, $fail failed"
+[ "$fail" -eq 0 ]

package/scripts/test_degrade_scan_shell_probes.sh

@@ -81,7 +81,7 @@ EOF
 cat > "$TMP/non_detections.sh" <<'EOF'
 #!/usr/bin/env bash
 # (a) integer sanitization — the PRESCRIBED remedy for the pipefail-fallback class, not the defect.
-count=$(grep -c pattern file)
+count=$(grep -c pattern file)  # portability-noqa: fixture text written by a quoted heredoc, never executed — statically grepped by degrade_direction_scan.sh only
 if [ "${count:-0}" -gt 0 ]; then echo "found"; fi
 # (b) SCOPE guards — "this run does not apply here" is not a claim that a check passed.
 [ -d "$HOME/projects" ] || exit 0
@@ -165,11 +165,11 @@ N=$(find /nope . -maxdepth 1 2>/dev/null | grep -c . || echo 0)
 M=$(git log --oneline 2>/dev/null | wc -l || echo 0)
 # WIDENED 2026-08-04. Every line below was INVISIBLE to the narrowed rule, and each was verified to
 # actually produce "0\n0" before being pinned here (line count measured, not assumed):
-P=$(cat /etc/hosts | grep -c . | tr -d ' ' || echo 0)   # transparent filter after the counter
-Q=$(grep -c "^nosuchline$" /etc/hosts 2>/dev/null | tr -d ' ' || echo 0)  # the PR #251 shape
-R=$(grep -Ec "^nosuchline$" /etc/hosts || echo 0)       # combined flag cluster -Ec
-S=$(grep --count "^nosuchline$" /etc/hosts || echo 0)   # long option
-T=$(grep -Fcx "nosuchline" /etc/hosts || echo 0)        # -Fcx
+P=$(cat /etc/hosts | grep -c . | tr -d ' ' || echo 0)   # transparent filter after the counter  # portability-noqa: fixture text, never executed
+Q=$(grep -c "^nosuchline$" /etc/hosts 2>/dev/null | tr -d ' ' || echo 0)  # the PR #251 shape  # portability-noqa: fixture text, never executed
+R=$(grep -Ec "^nosuchline$" /etc/hosts || echo 0)       # combined flag cluster -Ec  # portability-noqa: fixture text, never executed
+S=$(grep --count "^nosuchline$" /etc/hosts || echo 0)   # long option  # portability-noqa: fixture text, never executed
+T=$(grep -Fcx "nosuchline" /etc/hosts || echo 0)        # -Fcx  # portability-noqa: fixture text, never executed
 U=$(false | grep -c . | cat || echo 0)                  # trailing stage that always emits
 V=$(false | grep -c . | grep -v nosuch || echo 0)       # trailing grep whose pattern misses the "0"
 EOF
@@ -688,7 +688,7 @@ fi
 # flips to a hit — proves the exclusion is load-bearing for this specific fixture, not just
 # present somewhere in the file.
 _scan_reverted="$TMP/scan_reverted.sh"
-_excl_line=$(grep -n "grep -vE 'in \[A-Z_\]" "$SCAN" | head -1 | cut -d: -f1)
+_excl_line=$(grep -n "grep -vE 'in \[A-Z_\]" "$SCAN" | head -1 | cut -d: -f1)  # portability-noqa: this file has no `set -e` (top line 22 is `set -uo pipefail` only) and the next line already guards empty via -z
 if [ -z "$_excl_line" ]; then
   bad "C2-REVERT could not locate the exclusion line by its known text — fixture cannot run"
 else

package/scripts/test_files_manifest_shipping_lanes.sh

@@ -46,9 +46,9 @@ trap 'rm -rf "$LANE2_DIR"' EXIT
 cp package.json "$LANE2_DIR/package.json.orig"
 node -e '
   const fs = require("fs");
-  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));
+  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));  // # portability-noqa: cwd is REPO_ROOT (line 18) -- this is the subject under tests own manifest, not a foreign fixture
   pkg.files.push("scripts/__test_fixture_does_not_exist__.sh");
-  fs.writeFileSync("package.json", JSON.stringify(pkg, null, 2) + "\n");
+  fs.writeFileSync("package.json", JSON.stringify(pkg, null, 2) + "\n");  // # portability-noqa: same as above -- writes back to the same repo-relative manifest it read
 '
 restore_pkg() { cp "$LANE2_DIR/package.json.orig" package.json; }
 
@@ -132,7 +132,7 @@ D6="$(fixture_dir)"
 mkdir -p "$D6/.git"
 node -e '
   const fs = require("fs");
-  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));
+  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));  // # portability-noqa: cwd is REPO_ROOT -- seeds the fixture from the subject own real manifest, then mutates a copy
   pkg.files = ".";
   fs.writeFileSync(process.argv[1], JSON.stringify(pkg, null, 2) + "\n");
 ' "$D6/package.json"
@@ -152,7 +152,7 @@ D7="$(fixture_dir)"
 mkdir -p "$D7/.git"
 node -e '
   const fs = require("fs");
-  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));
+  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));  // # portability-noqa: cwd is REPO_ROOT -- seeds the fixture from the subject own real manifest, then mutates a copy
   pkg.files.push("missing\nPASS\\t999 entries checked, 0 phantom, 0 unpacked");
   fs.writeFileSync(process.argv[1], JSON.stringify(pkg, null, 2) + "\n");
 ' "$D7/package.json"
@@ -175,7 +175,7 @@ mkdir -p "$D8/.git" "$D8/scripts_dummy"
 echo x > "$D8/scripts_dummy/foo.sh"
 node -e '
   const fs = require("fs");
-  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));
+  const pkg = JSON.parse(fs.readFileSync("package.json", "utf8"));  // # portability-noqa: cwd is REPO_ROOT -- seeds the fixture from the subject own real manifest, then mutates a copy
   pkg.files = ["scripts_dummy"];
   delete pkg.scripts.prepare;
   delete pkg.scripts.prepublishOnly;

package/scripts/test_heavy_classifier_lanes.sh

@@ -103,7 +103,7 @@ check carveout  "README.md"                  "npm-shipped surface — first-scre
 check carveout  "README.ko.md"               "language variants route the same way"
 check carveout  "README.zh-CN.md"            "🟥 5-char locale forms too — cross-family caught [a-z]{2} missing these"
 check uncovered ".claude/registry/README.md" "🟥 STILL UNCOVERED — in files[] but not root; named, not closed"
-check uncovered "package.json"               "files[] / version changes are unclassified"
+check uncovered "package.json"               "files[] / version changes are unclassified"  # portability-noqa: "package.json" is a string literal fed to classify()'s regex test, never opened from disk — a ported repo without this exact file still exercises the same classifier logic
 check uncovered ".github/workflows/validate.yml" "🟥 CI definition — changing what CI runs is unclassified"
 check uncovered "scripts/memory_link_check.py"   "🟥 .py is not .sh — shipped python is unclassified"
 

package/scripts/test_lane_runner_lanes.sh

@@ -30,18 +30,32 @@ mkfixture() { # $1 = dir
   printf '#!/usr/bin/env bash\nbash scripts/lane_runner_check.sh\n' > "$d/scripts/selfcheck.sh"
   printf '#!/usr/bin/env bash\n: orphan lane suite\n'  > "$d/scripts/test_orphan_lanes.sh"
 }
-run() { ( cd "$1" && bash scripts/lane_runner_check.sh 2>&1 ); }
-rcof() { ( cd "$1" && bash scripts/lane_runner_check.sh >/dev/null 2>&1; echo $? ); }
+# ONE execution per fixture, stdout AND rc from the SAME run — never two separate invocations.
+# Until 2026-09-03 this was split into run()+rcof(), each running lane_runner_check.sh on its own.
+# lane_runner_check.sh reads live filesystem/git state on every invocation (its own mktemp, a
+# `.git` up-chain walk, `git ls-files -z`, a python3 subprocess) and is not guaranteed to answer
+# identically twice in a row under CI resource pressure — so a call site combining `$(run "$D")`
+# with a SEPARATE `$(rcof "$D")` could silently pair stdout from one run with the exit code of a
+# DIFFERENT run. That produced an impossible-looking CI flake: rc=0 with the literal substring
+# "declared debt" absent from $out, even though every rc=0 exit path in lane_runner_check.sh
+# unconditionally prints that substring (traced exhaustively — see
+# tracks/_meta/armC_armC-wt2_report2_2026-09-03.md). Sets LRC_OUT/LRC_RC as globals: this file is
+# flat top-level (no `local` scoping across call sites), and bash functions cannot return two
+# values through their exit status alone.
+run_check() {   # $1 = fixture dir
+  LRC_OUT="$(cd "$1" && bash scripts/lane_runner_check.sh 2>&1)"; LRC_RC=$?
+}
 
 # ── L1 known-POSITIVE: an undeclared orphan suite must FAIL ───────────────────────────────────
 # Without this arm every lane below proves nothing: a checker that passed unconditionally would
 # satisfy all the "declaration suppresses it" lanes.
 D="$T/l1"; mkfixture "$D"
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "1" ] && printf '%s' "$out" | grep -q 'test_orphan_lanes.sh'; then
   ok "L1 known-positive: undeclared orphan suite → rc=1 and it is named"
 else
   bad "L1 known-positive did not fire (rc=$rc) — every lane below is meaningless without it"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── IDX7 the FAIL path must EXECUTE the provenance note, not merely contain a call to it ──────
@@ -55,7 +69,7 @@ fi
 # It asserts the SHAPE of provenance, not the exact sentence: the fixture is a non-git dir, so the
 # honest answer there is the DISK one, and pinning the index wording would make the lane wrong.
 D="$T/idx7"; mkfixture "$D"
-out=$(run "$D")
+run_check "$D"; out="$LRC_OUT"
 if printf '%s' "$out" | grep -qE 'unbound variable|command not found|syntax error'; then
   bad "IDX7 the FAIL path errored: $(printf '%s' "$out" | grep -E 'unbound|not found|syntax' | head -1)"
 elif printf '%s' "$out" | grep -qE 'ⓘ|🟥'; then
@@ -67,41 +81,45 @@ fi
 # ── L2 NO-OP: no declaration file → behaviour is exactly the L1 behaviour ─────────────────────
 # This is the arm that protects THIS repo, which ships no company/ directory.
 D="$T/l2"; mkfixture "$D"
-out=$(run "$D")
+run_check "$D"; out="$LRC_OUT"
 if ! printf '%s' "$out" | grep -q 'lane_declarations'; then
   ok "L2 no-op: absent declaration file is silent (no mention in output)"
 else
   bad "L2 no-op: output mentions the declaration file when none exists"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L3 org EXEMPT suppresses the orphan ───────────────────────────────────────────────────────
 D="$T/l3"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'exempt:\n  - test_orphan_lanes.sh   # org-owned, runs in the org CI only\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q '1 exempt'; then
   ok "L3 org exempt: declared suite no longer fails the check (rc=0, counted exempt)"
 else
-  bad "L3 org exempt did not suppress (rc=$rc) — out: $(printf '%s' "$out" | tail -1)"
+  bad "L3 org exempt did not suppress (rc=$rc)"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L4 org DEBT suppresses AND is counted as debt ─────────────────────────────────────────────
 D="$T/l4"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'debt:\n  - test_orphan_lanes.sh\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q 'declared debt'; then
   ok "L4 org debt: declared suite suppressed and reported as debt"
 else
   bad "L4 org debt did not land (rc=$rc)"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L5 VISIBILITY: an org-declared list must never look like this repo's own zero ─────────────
 D="$T/l5"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'debt:\n  - test_orphan_lanes.sh\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D")
+run_check "$D"; out="$LRC_OUT"
 if printf '%s' "$out" | grep -q 'org-declared'; then
   ok "L5 visibility: output names the org file and its counts"
 else
   bad "L5 visibility: org declarations are invisible in the output"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L6 FAIL-CLOSED on an unparseable file ─────────────────────────────────────────────────────
@@ -109,41 +127,46 @@ fi
 # render UNMEASURED as ZERO, and it would do so on the arm where a fork is relying on the file.
 D="$T/l6"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'exempt:\n  this line is not an entry\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "2" ] && printf '%s' "$out" | grep -q 'UNMEASURED'; then
   ok "L6 fail-closed: unparseable declaration file → rc=2 and says UNMEASURED"
 else
   bad "L6 fail-closed FAILED (rc=$rc) — a malformed file was read as 'no declarations'"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L6b control for L6: the SAME orphan tree with a WELL-FORMED file must not exit 2 ──────────
 # Without this, L6 would also pass on a checker that exits 2 for any declaration file at all.
 D="$T/l6b"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'exempt:\n  - test_orphan_lanes.sh\n' > "$D/company/lane_declarations.yaml"
-if [ "$(rcof "$D")" != "2" ]; then
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
+if [ "$rc" != "2" ]; then
   ok "L6b control: a well-formed file does NOT trip the fail-closed arm"
 else
   bad "L6b control: every declaration file exits 2 — L6 proved nothing"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L7 unknown section is a parse failure, not a silent skip ──────────────────────────────────
 D="$T/l7"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'allowed:\n  - test_orphan_lanes.sh\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D")
-if [ "$(rcof "$D")" = "2" ] && printf '%s' "$out" | grep -q "unknown section"; then
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
+if [ "$rc" = "2" ] && printf '%s' "$out" | grep -q "unknown section"; then
   ok "L7 unknown section → rc=2 and names the section"
 else
-  bad "L7 unknown section was tolerated — a typo'd header would silently declare nothing"
+  bad "L7 unknown section was tolerated — a typo'd header would silently declare nothing (rc=$rc)"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L8 the same name in both sections is ambiguous, not last-wins ─────────────────────────────
 D="$T/l8"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'exempt:\n  - test_orphan_lanes.sh\ndebt:\n  - test_orphan_lanes.sh\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D")
-if [ "$(rcof "$D")" = "2" ] && printf '%s' "$out" | grep -q "both exempt and debt"; then
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
+if [ "$rc" = "2" ] && printf '%s' "$out" | grep -q "both exempt and debt"; then
   ok "L8 same suite in both sections → rc=2 (ambiguous, not silently resolved)"
 else
-  bad "L8 double declaration was silently resolved"
+  bad "L8 double declaration was silently resolved (rc=$rc)"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L9 a stale entry WARNS but does not block (same voice as upstream DEBT hygiene) ───────────
@@ -151,20 +174,23 @@ fi
 # would train forks to delete the file, which costs more than a stale line.
 D="$T/l9"; mkfixture "$D"; mkdir -p "$D/company"
 printf 'exempt:\n  - test_orphan_lanes.sh\n  - test_deleted_lanes.sh\n' > "$D/company/lane_declarations.yaml"
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q 'test_deleted_lanes.sh'; then
   ok "L9 stale entry: warns and names it, does not block (rc=0)"
 else
   bad "L9 stale entry handling wrong (rc=$rc)"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L10 comments and blank lines are not entries ──────────────────────────────────────────────
 D="$T/l10"; mkfixture "$D"; mkdir -p "$D/company"
 printf '# org lane declarations\n\nexempt:\n\n  - test_orphan_lanes.sh   # reason lives here\n' > "$D/company/lane_declarations.yaml"
-if [ "$(rcof "$D")" = "0" ]; then
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
+if [ "$rc" = "0" ]; then
   ok "L10 comments/blank lines tolerated (a file people can annotate)"
 else
-  bad "L10 a commented, spaced file failed to parse"
+  bad "L10 a commented, spaced file failed to parse (rc=$rc)"
+  printf '%s\n' "$out" | sed 's/^/       │ /'
 fi
 
 # ── L11/L12 embedded --self-test subjects (found→extend, 2026-08-14) ──────────────────────────
@@ -186,7 +212,7 @@ mkfixture_clean() { # $1 = dir
 # L11 known-POSITIVE: an unwired --self-test subject is reported, advisory (rc stays 0).
 D="$T/l11"; mkfixture_clean "$D"
 printf '#!/usr/bin/env bash\n[ "${1:-}" = "--self-test" ] && { echo ok; exit 0; }\n' > "$D/scripts/orphan_probe.sh"
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q 'orphan_probe'; then
   ok "L11 known-positive: unwired --self-test subject named, advisory (rc=0)"
 else
@@ -206,7 +232,7 @@ for _subj in orphan_probe; do
   bash "scripts/$_subj.sh" --self-test
 done
 SC
-out=$(run "$D")
+run_check "$D"; out="$LRC_OUT"
 if ! printf '%s' "$out" | grep -q 'orphan_probe'; then
   ok "L12 known-negative: --self-test subject wired via _subj for-loop is not reported"
 else
@@ -228,7 +254,7 @@ bash scripts/lane_runner_check.sh
 bash scripts/test_ok_lanes.sh
 bash scripts/orphan_probe.sh --self-test >/dev/null 2>&1
 SC
-out=$(run "$D")
+run_check "$D"; out="$LRC_OUT"
 if ! printf '%s' "$out" | grep -q 'orphan_probe'; then
   ok "L13 known-negative: --self-test subject wired via direct dispatch is not reported"
 else
@@ -262,7 +288,7 @@ cat > "$D/scripts/orphan_probe.sh" <<'SUBJ'
 #   bash scripts/orphan_probe.sh --self-test        # known-pair calibration
 [ "${1:-}" = "--self-test" ] && { echo ok; exit 0; }
 SUBJ
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q 'orphan_probe'; then
   ok "L14 known-positive: subject's own usage comment is not a caller — still reported unwired"
 else
@@ -280,7 +306,7 @@ bash scripts/lane_runner_check.sh
 bash scripts/test_ok_lanes.sh
 # historical note: we used to run `bash scripts/orphan_probe.sh --self-test` here, removed 2026-01-01
 SC
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q 'orphan_probe'; then
   ok "L15 known-positive: a commented-out dispatch in another file is not a caller"
 else
@@ -302,7 +328,7 @@ usage() { echo "run: bash scripts/orphan_probe.sh --self-test"; }
 [ "${1:-}" = "--self-test" ] && { echo ok; exit 0; }
 usage
 SUBJ
-out=$(run "$D"); rc=$(rcof "$D")
+run_check "$D"; out="$LRC_OUT"; rc="$LRC_RC"
 if [ "$rc" = "0" ] && printf '%s' "$out" | grep -q 'orphan_probe'; then
   ok "L16 known-positive: a subject's own NON-comment self-reference is not a caller"
 else
@@ -323,36 +349,36 @@ fi
 # ([[feedback_not_found_is_not_zero_family]]).
 _ISN=$(mktemp); sed -n '/^index_source_note()/,/^}/p' "$CHECK" > "$_ISN"
 if ! grep -q 'UNMEASURED' "$_ISN"; then
-  no "IDX-harness — index_source_note did not extract from $CHECK (lanes would measure nothing)"
+  bad "IDX-harness — index_source_note did not extract from $CHECK (lanes would measure nothing)"
 else
   # shellcheck disable=SC1090
   . "$_ISN"
   o=$(index_source_note "index")
   printf '%s' "$o" | grep -q "INDEX 기준" && printf '%s' "$o" | grep -q "스테이징" \
     && ok "IDX1 index mode names the index AND the staging remedy" \
-    || no "IDX1 index mode note missing/incomplete: $o"
+    || bad "IDX1 index mode note missing/incomplete: $o"
 
   o=$(index_source_note "nongit")
   printf '%s' "$o" | grep -q "DISK" && ok "IDX2 nongit mode says DISK, not index" \
-                                    || no "IDX2 nongit: $o"
+                                    || bad "IDX2 nongit: $o"
 
   o=$(index_source_note "UNMEASURED")
   printf '%s' "$o" | grep -q "못 셌다" && ok "IDX3 UNMEASURED says «could not count», not «none»" \
-                                       || no "IDX3 UNMEASURED: $o"
+                                       || bad "IDX3 UNMEASURED: $o"
 
   # 🟥 CONTROL — an unknown/empty mode must stay SILENT. Inventing a source line for a state the
   # check does not recognise is worse than saying nothing, and without this lane the function
   # could pass IDX1–IDX3 while emitting the index sentence for every input.
   o=$(index_source_note "")
   [ -z "$o" ] && ok "IDX4 control — empty mode is silent (no invented provenance)" \
-              || no "IDX4 control — empty mode spoke: $o"
+              || bad "IDX4 control — empty mode spoke: $o"
 
   # 🟥 CONTROL 2 — the three states must be DISTINGUISHABLE from each other, not merely non-empty.
   a=$(index_source_note "index"); b=$(index_source_note "nongit"); c=$(index_source_note "UNMEASURED")
   if [ "$a" != "$b" ] && [ "$b" != "$c" ] && [ "$a" != "$c" ]; then
     ok "IDX5 control — the three states produce three different sentences"
   else
-    no "IDX5 control — states collapsed into the same sentence"
+    bad "IDX5 control — states collapsed into the same sentence"
   fi
 fi
 rm -f "$_ISN"
@@ -362,7 +388,7 @@ if sed -n '/lane suite(s) with no runner and no declaration/,/Fix by ONE of/p' "
      | grep -q 'index_source_note'; then
   ok "IDX6 the note is CALLED on the FAIL path (not just defined)"
 else
-  no "IDX6 index_source_note is defined but the FAIL path does not call it"
+  bad "IDX6 index_source_note is defined but the FAIL path does not call it"
 fi
 
 echo "----"