chore(memory): BLK-021/022, LRN-150/151, BDR-088, EVAL-029 — macOS port

Capitalizes the macOS port and the gstack Chromium deadlock, plus an
append-only correction to BLK-008 / LRN-038: their "ubuntu24.04 fallback
build" cause is refuted — macOS arm64 has a native Playwright 1.58.2 build,
no fallback, and the same hang reproduces. The real variable was the Node
version, and that wrong record misdirected this investigation for an hour.

EVAL-029 records two process failures worth keeping: the first fix
recommendation (pin node@22) was reversed only because the user asked
whether the browser was current — staleness had gone unpriced; and the grep
sweep returned empty twice while defects were present, once to `set -e`,
once to a pattern that could not match `${1,,}`.

Index rows added for all four registries. Pre-existing index drift
(BLK-018..020, LRN-144..149) left alone — backfilling means summarising
entries someone else wrote.

.claude/memory/learnings.md

@@ -139,6 +139,8 @@ rules:
 | LRN-134 | 2026-07-17 | resolve-then-pin in stdlib http.client beats monkeypatching getaddrinfo — dual-stack, thread-safe, no requests; classify the OS-resolved IP not the URL text | closing SSRF/DNS-rebinding on any Python HTTP egress |
 | LRN-135 | 2026-07-17 | a prefix-only scan for a dangerous construct is bypassable by padding — scan the WHOLE document | refusing any hostile construct (DTD/directive/marker) before parse |
 | LRN-143 | 2026-08-26 | `cmd \| head \|\| fallback` — pipeline rc is head's (0), fallback dead; bounded output → drop head, else pipefail | any probe/fallback bash in skills before trusting `\|\|` |
+| LRN-150 | 2026-09-13 | Lockfile-pinned dep vs fast runtime: undeclared incompatibility HANGS, never errors; `engines` has no upper bound | any pinned tool that stalls — check dep publish date vs runtime release, and the DECLARED range vs the lock |
+| LRN-151 | 2026-09-13 | Porting to macOS: bash 3.2 makes guards fail-OPEN, not abort; and a scan finding nothing proves nothing | after any OS migration — run the suite first, audit guards before cosmetics, self-check the detector |
 
 ---
 
@@ -624,6 +626,7 @@ rules:
 - **Future application**: any pinned tool that hardcodes an OS allowlist breaks on a fresh OS upgrade. Look for a host-platform override env before bumping/forking the dep. Prove the fallback binary actually runs (`ldd` = no missing libs + a real headless render), not just that the download resolves.
 - **Reference**: `install-plugins.sh` `playwright_platform_override()`, commit 211c7d4. Linked to [[BLK-008]].
 - **2026-06-23 CORRECTION (override REVERTED, commit b9c3937)**: the override is NOT a usable fix on Ubuntu 26.04. It makes `playwright install` switch to the ubuntu24.04 fallback build, which downloads to 100% then HANGS at extraction (chrome binary never materializes; real machine + sandbox). Turned a 0.5s fast-fail into an install-blocking hang. The isolated proof (`ldd` + headless render) PASSED but used an already-extracted sibling build (rev 1228) — it masked the install-path hang in the real flow (rev 1208). **Sharpened lesson**: proving the binary launches in isolation is NOT proving the install path works — run the ACTUAL install command end-to-end (it must COMPLETE, not just "download resolves" nor "a binary launches"). The override technique stays valid in general, but the EXTRACTION/COMPLETE step is part of "does it work".
+- **2026-09-13 CORRECTION**: "the ubuntu24.04 fallback build hangs at extraction" is REFUTED as the cause. Same hang, same signature, on macOS arm64 where 1.58.2 ships a native build and no fallback is involved — so the cause is Playwright 1.58.2 deadlocking on a too-new Node, not the build. This entry cost real time: it sent the 2026-09-13 macOS investigation hunting fallback builds first. A fix that WORKS can freeze a WRONG cause. See [[BLK-021]] / [[LRN-150]].
 
 ---
 
@@ -1421,3 +1424,18 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 - **Fail-open**: field absent (older client) → still signal. Missed notification worse than extra one.
 - **Cross-session gotcha**: hook is user-scope, so EVERY session runs it. A single-file dump (`> file`) gets overwritten by another project's session — append JSONL and filter on `.cwd`. That accident proved `permission_prompt` fires with `message="Claude needs your permission"` (unexercisable in this session under `defaultMode: auto`).
 - **Future**: any hook needing turn-completion semantics must check background_tasks; "turn ended" ≠ "work done". Verified live: Stop with 0 tasks signals, Stop with 1 running subagent silent.
+
+## LRN-150 — a lockfile-pinned dep vs a fast runtime: the undeclared incompatibility HANGS, it does not error
+- **Context**: 2026-09-13. gstack's lockfile-frozen Playwright 1.58.2 (Feb 2026) under Node 26.5.0 (Sept 2026). Chromium extraction deadlocks at 39/333 files, silently, forever. `engines: node >=18` claims support.
+- **Pattern**: `engines` is a CLAIM, not a test — an UPPER bound is almost never declared, so "too new" reads as "supported" and fails as a HANG, not an error. Diagnose with `sample <pid>` (macOS) or any stack dump: ALL threads idle (`kevent` + `__psynch_cvwait`, 0% CPU, libuv workers INCLUDED) = deadlock, nothing in flight; a thread parked in `write`/`read` would mean AV/FS/network instead — that one measurement ruled out Intego VirusBarrier in seconds. Then discriminate by moving ONE variable: same command + same revision under another runtime (`brew` keeps node@22 beside node@26).
+- **Read the declared range before calling it a pin**: `package.json` said `^1.58.2`, so 1.63.0 was already in range — only `bun.lock` froze it. A "bump" that needs no fork and breaks no contract was available the whole time.
+- **Corollary**: a fix that WORKS can freeze a WRONG cause in the registry. [[BLK-008]] blamed a fallback build; that record misdirected this investigation three months later. When a fix lands, record which variable was PROVEN, not the one suspected.
+- **Future**: pinned dep + hang → compare dep publish date vs runtime release date BEFORE blaming platform/network/AV. Any unattended install step that can hang needs a DEADLINE: silent-forever is strictly worse than failing loudly ([[BDR-088]]).
+
+## LRN-151 — porting to macOS: the danger is fail-OPEN, and a scan that finds nothing proves nothing
+- **Context**: 2026-09-13. Repo moved Linux → macOS. `/bin/bash` = 3.2.57 = what `#!/usr/bin/env bash` resolves to. Six distinct defect classes ([[BLK-022]]).
+- **Pattern — the failure direction is what matters**: bash 3.2 does not abort on a bash-4 construct, it makes the SUBSHELL fail, and a guard whose "block" path is an exit code then reads as "allow". `${1,,}` turned an SSRF allowlist into a pass-through; `mapfile` turned scope guards into empty-array no-ops that still reported success; missing `timeout` turned every gate criterion into NOT-MET. Audit order: find the guards FIRST, ask what an errored subshell returns there, and only then chase cosmetics.
+- **Empirically catalogued surface** (bash 3.2 + BSD userland): `${var,,}`/`${var^^}`, `mapfile`/`readarray`, `declare -A`, `timeout` (coreutils), `sed -i` (needs a suffix; no `\n` in the replacement), `touch -d`, `stat -c`, `wc -l` (pads with spaces — breaks string compares), `/bin/grep` (macOS has only /usr/bin/grep), `readlink -f` (OK since Monterey), `sort -V` (OK).
+- **The test suite is the oracle**: the repo's own `make test` located every one of these faster than reading code, because each defect surfaced as a specific assertion. Port = run the suite, fix what reddens, re-run.
+- **Self-check the detector**: my grep sweep returned EMPTY twice and I nearly read it as "clean" — once because `set -e` killed the loop on the first no-match grep, once because the pattern demanded a letter after `${` and so missed `${1,,}` (a digit). A scan that finds NOTHING must first be shown to find something known-present. Both misses were caught by accident, not by method.
+- **Future**: after any OS migration, run the full suite before trusting any static sweep, and treat a 100%-of-a-category warning as a stale check rather than 100% non-compliance ([[BDR-019]] sweep, `doctor.sh` + `Makefile`).