docs(issue-5): fold in the two non-blocking residuals from cross-review round 2

Both reviewers passed and each left one documentation item.

Grok: the benchmark's fork table still named the shell path `-m
lib_py.delegation.cli`, which is what R1 replaced. It now names the actual
bootstrap, and says why the module-execution form was abandoned. The fork count
is unchanged either way.

Claude (O-4): inside a freeze tree, _delegate_py_bin walks up from its own
location for a .venv and finds none, so it falls back to a system python that
has no paho. Harmless in phase 1, because nothing in production calls the frozen
lib.sh helpers; it becomes real in phase 3 when the loop process starts doing
exactly that. Recorded on P3-02 rather than fixed here, since the fix belongs
with the code that will depend on it. Verified the premise: the current freeze
root has no .venv.

No code changed. The unanimous PASS was issued on 95f3e9a.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UrDNJkHmm18uu7n7JwV5Qd

docs/contracts/issue-5/task.md

@@ -91,6 +91,7 @@
 ## Phase 3: `run_loop.sh` Thin Wrapper 전환 및 전면 회귀 (후속)
 - [ ] **P3-01** planner/reviewer/rebuttal/promotion 및 strict 판정/예산/중재/합의 테스트.
 - [ ] **P3-02** thin wrapper 인자·interpreter·cwd·signal·guard·child cleanup 호환 검증.
+  - *인계 (교차 리뷰 `25609c81` O-4)*: freeze 사본의 `lib.sh`에서 `_delegate_py_bin`은 `AGENT_PYTHON_BIN`/`VIRTUAL_ENV`가 없으면 **자기 위치에서 상향 탐색**하는데, freeze 디렉터리 아래에는 `.venv`가 없어 paho가 없는 시스템 `python3`로 떨어진다. Phase 1에서는 freeze `lib.sh`의 위임 헬퍼를 호출하는 프로덕션 경로가 없어 무해하나, **Phase 3에서 루프 프로세스가 freeze `lib.sh`의 헬퍼를 직접 호출하기 시작하면** 인터프리터 해석을 `WORKSPACE_ROOT`(또는 `MAM_REAL_ROOT`) 기준으로 앵커링해야 한다.
 - [ ] **P3-03** 전체 suite+신규 race/restart/lifecycle, writer 단일성, rollback checkpoint 인계 검증.
 
 ---