merge: docs/instruction-skill-authoring (INSTRUCTION.md)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff

.agents/reports/planner-reviewer-claude-01/report-05af786c.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261025T023502Z-d6f876",
+  "base_sha": "0461a632eb667c7988fd33be92e9a4b36151f22a",
+  "head_sha": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "tree_sha": "15a72c9a1933c64018a2f2d9aa9707348905bb4d",
+  "review_commit": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "reviewer": "planner-reviewer-claude-01",
+  "job_id": "05af786c",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-25T03:40:44Z"
+}

.agents/reports/planner-reviewer-claude-01/report-05af786c.md

@@ -0,0 +1,104 @@
+# PR #70 (Issue #66) 리뷰 — head bb496fd
+
+- 리뷰어: planner-reviewer-claude-01 (macOS, bash 3.2, /usr/bin/python3 3.9.6)
+- 검증 경로: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1`
+- identity 확인: HEAD bb496fde785133ad1dbec288aa7431766efb6eb5, tree 15a72c9a1933c64018a2f2d9aa9707348905bb4d, `git status --porcelain --ignored` 비어 있음, `.mam` 없음 (시작·종료 시 모두). main HEAD 0461a63 그대로.
+- 범위: base 0461a63..bb496fd (커밋 1개). 바뀐 파일은 세 개다: `.agents/skills/lib_py/stall_watch.py`, `tests/conftest.py`, `tests/test_issue66_stall_watch_sanitized_name.py`.
+
+## 1. 확인한 것과 근거
+
+### 1) 완료 조건
+
+herdr 를 부르는 곳은 모두 변환된 이름을 쓴다.
+- `HerdrSource.__init__` 이 `self.name = sanitize_herdr_agent_name(target)` 를 만든다 (`stall_watch.py:162`).
+- 이 이름을 쓰는 곳:
+  - `agent get` (:183)
+  - `agent read` (:206)
+  - `agent prompt` (:211)
+  - `watcher.wait_once(self.herdr_name, …)` (:331, 값은 :229)
+- `pane process-info` 와 `pane read` (:187, :193)는 `agent get` 이 돌려준 pane_id 를 쓰므로 이름과 상관이 없다.
+- `--herdr-session` 은 서버 이름으로만 쓰인다. `self.session` (:159) 과 `session=self.args.herdr_session` (:331) 이고, 변환되지 않는다. 둘을 섞어 쓴 곳은 없다.
+
+로그와 알림은 원래 이름을 쓴다.
+- 로그 :373 (blocked), :397 (입력창 비어 있지 않음), :406 (idle) 은 모두 `self.args.target` 이다.
+- 알림 상세(`stalled:idle`, `stalled:blocked …`)에는 이름이 들어가지 않는다.
+- 회귀 테스트는 `agent {target} idle for` 와 `agent {target} is blocked` 가 원래 이름으로 나오는지 확인한다 (test :85, :106).
+
+변환이 필요 없는 이름(`creator-claude-t`)은 그대로이고, 그 경우의 테스트도 통과한다 (test :68 의 PLAIN).
+
+### 2) 회귀 테스트: base 에서 실패, head 에서 통과
+
+- head: 7 passed.
+- base(0461a63) 사본에 head 의 새 테스트와 conftest 를 넣고 돌리면 5 failed, 2 passed 다.
+  - 실패: LONG, UPPER 두 이름 각각의 idle nudge 와 blocked 보고 (4개), 긴 codex 이름의 종류 판정 (1개).
+  - 통과: strict mock 자체를 확인하는 테스트와, 변환이 필요 없는 PLAIN.
+
+### 3) 변환 함수가 lib.sh 와 같은 결과를 내는가
+
+lib.sh `_sanitize_herdr_agent_name` (:293-316) 과 `lib_py.agents.sanitize.sanitize_herdr_agent_name` 에 같은 이름 10개를 넣어 비교했다.
+- 비교한 이름: 그대로 둘 이름, 대문자, 32자 초과(루프 세션 이름 포함), 정확히 32자, 33자, 숫자로 시작, `.`·공백·`@`, 비 ASCII `Ü`, `_` 로 시작.
+- 결과: 10개 모두 같고, 두 번 변환해도 바뀌지 않는다.
+- 그래서 호출자가 이미 변환된 이름을 넘겨도 안전하다.
+- 호출자는 원래 세션 이름을 넘긴다: `multi-agent-mux-delegate-job:431`, `:615` → `start_stall_watch "$AGENT_SESSION"` 와 `"$current_session"`.
+
+### 4) resolve_agent 를 원래 이름으로 하는 것이 맞는가
+
+맞다.
+- 긴 이름은 변환되면 끝이 해시로 바뀐다. 예: `mam-wt-issue-66-very-long-creator-codex` → `…-<sha8>`. 그래서 종류는 원래 접미사에서 읽어야 한다.
+- `HerdrSource` (:163) 과 `StallWatch` (:230) 둘 다 원래 이름을 쓴다.
+- 테스트 :111-129 가 `--agent ""` 일 때 codex 로 정해져 nudge 가 가는 것을 확인한다.
+- 종류를 변환된 이름에서 읽도록 바꾼 변이(m3)는 이 테스트에 잡힌다.
+
+### 5) conftest `strict_agent_names`
+
+- 기본(키 없음)일 때 `_match_agent` 는 예전과 똑같이 네 가지 비교를 한다 (`conftest.py` 수정분 :473-476). get/read 의 실패 출력도 예전 문구 그대로다. 그래서 기존 테스트의 동작은 바뀌지 않는다.
+- 켜면 등록된 이름과 정확히 같을 때만 답하고, 아니면 `{"error":{"code":"agent_not_found"}}` 를 stderr 에 쓰고 exit 1 한다. 실제 herdr 처럼 등록 이름(변환된 이름)으로만 찾는다.
+- 테스트 :51-65 가 get, read, wait, prompt 네 명령 모두 원래 이름에는 agent_not_found 를, 변환된 이름에는 rc 0 을 내는지 확인한다.
+
+### 6) macOS 호환
+
+- `/usr/bin/python3` 3.9.6 으로 `lib_py.stall_watch` import 와 `resolve_agent` 호출이 된다.
+- 새 코드에 `X | Y`, `match`, tomllib 가 없다. 셸은 바뀌지 않았다.
+
+### 7) test_issue17_item4_decisions::test_c_finalize_ends_with_an_unreaped_wrapper[broker_unavailable-3-0]
+
+이 변경과 무관하다.
+- 이 테스트는 래퍼의 finalize 를 자체 shim(`PY=<shim>`)으로 돌린다. stall watcher 는 argv 를 기록하는 대역이다 (`tests/test_issue17_item4_decisions.py:218`).
+- conftest 의 mock herdr 와 `lib_py.stall_watch` 를 쓰지 않는다.
+- 판정 조건은 `took < 4.5` 와 terminate 뒤 레코드가 그대로인지 (:598-601) 로, 시간과 정리 단계에 의존한다.
+- 이 PR 이 바꾼 것(stall_watch 의 이름 변환, 기본 꺼짐인 mock 옵션)은 이 경로에 닿지 않는다.
+- 이 호스트에서도 통과했다(아래 표).
+
+## 2. 실행한 테스트
+
+모두 `env -i`, 임시 HOME/XDG, `PYTHONDONTWRITEBYTECODE=1 -p no:cacheprovider --basetemp=<scratchpad>` 로 돌렸다. .mam.env 를 export 하지 않았다.
+
+| 대상 | 결과 |
+|---|---|
+| 검증 경로 `tests/test_issue66_stall_watch_sanitized_name.py` | 7 passed |
+| base 사본 + 새 테스트·conftest | 5 failed, 2 passed |
+| 검증 경로: test_issue30_stall_watch, test_issue30_stall_watch_stop, test_issue17_item4_decisions, test_tier2_component, test_issue63_same_cwd_ids, test_issue50_dispatch_herdr, test_c1_tui_readiness (mock herdr 를 쓰는 인접 테스트) | 457 passed, 1 skipped, 0 failed |
+
+변이 테스트 (head 사본, issue66 테스트):
+
+| # | 변이 | 결과 |
+|---|---|---|
+| m1 | `wait_once` 를 원래 이름으로 | 잡힘 (5 failed) |
+| m2 | `agent prompt` 를 원래 이름으로 | 잡힘 (3 failed) |
+| m3 | 종류를 변환된 이름에서 판정 | 잡힘 (1 failed) |
+| m4 | blocked 로그를 변환된 이름으로 | 잡힘 (2 failed) |
+| m5 | `agent read` 를 원래 이름으로 | 잡힘 (3 failed) |
+
+실제 herdr 서버(pid 19169 `herdr server`, 23492 `herdr --session multi-agent-mux server`)는 테스트 전후로 같다.
+
+## 3. 차단 결함
+
+없음.
+
+## 4. 비차단
+
+- **N1**: 변환된 이름을 두 곳에서 따로 만든다(`HerdrSource.name` :162, `StallWatch.herdr_name` :229). 주입된 source 를 쓰는 테스트 때문에 둘 다 필요해 보인다. 결과가 같으므로 동작에는 문제가 없다.
+- **N2** (기존, 이 PR 과 무관): `--agent` 가 비어 있고 이름이 `…-claude-01` 처럼 숫자로 끝나면 `resolve_agent` 는 종류를 정하지 못한다(None). 실제 호출자는 항상 `--agent "$AGENT"` 를 넘기므로 지금은 영향이 없다.
+- **N3** (기존, 이 PR 과 무관): lib.sh 에 `_sanitize_herdr_agent_name` 이 두 벌 있다(:36, :293). sha 도구가 없을 때의 대처가 서로 다르다(:36 은 32자로 자르고, :293 은 python3 로 해시). 이 호스트처럼 shasum 이 있으면 두 벌 모두 Python 판과 같다.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-claude-01/report-1d2c21dc.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261027T201245Z-63c71b",
+  "base_sha": "1d63e882bc1c46e9af8484647d5091b296d8fa3f",
+  "head_sha": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "tree_sha": "fbadb24de60ccdae684b23e2e0a41cdf23ab81eb",
+  "review_commit": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "reviewer": "planner-reviewer-claude-01",
+  "job_id": "1d2c21dc",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-27T21:06:27Z"
+}

.agents/reports/planner-reviewer-claude-01/report-1d2c21dc.md

@@ -0,0 +1,132 @@
+# PR #75 후속 라운드 리뷰 — 1d63e88..ec7f5c4 (review round 5)
+
+리뷰어: planner-reviewer-claude-01 (claude) · job 1d2c21dc
+
+## 0. 리뷰 경로 확인
+
+- 검증 경로: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1`
+- HEAD `ec7f5c4e57286fb3c4238b8220f39094f4640391`, tree `fbadb24de60ccdae684b23e2e0a41cdf23ab81eb` 로 [리뷰 identity] 와 같다.
+  - `git status --porcelain --ignored` 는 비어 있다. `.mam` 은 없다.
+  - 리뷰 전후로 확인했다. 본 체크아웃 main 은 `0e1e2e8` 그대로다.
+- 범위: 1d63e88..HEAD 의 커밋 `ec7f5c4` 하나다.
+  - 바뀐 파일: `.agents/skills/lib.sh`(+7/−1), `tests/test_issue72_update.py`(+32/−3)
+  - 브리프가 정한 범위(R2 와 테스트의 `pkill` 제거) 밖은 건드리지 않았다.
+
+## 1. R2 — legacy `start_watchdog` 의 프로세스 그룹 분리
+
+### 1.1 코드 (`lib.sh:2297-2310`)
+
+- 모니터를 띄우는 `nohup bash … &` 직전에 `set -m` 을 켠다.
+  - 켜기 전에 호출자의 `$-` 에 `m` 이 있었는지 `had_m` 에 기억한다.
+  - `pid=$!` 를 읽은 뒤, 원래 꺼져 있었으면 `set +m` 으로 되돌린다.
+- job control 이 켜진 상태에서 띄운 백그라운드 잡은 자기 프로세스 그룹의 리더가 된다(PGID = PID). 그래서 다음 효과가 있다.
+  - `$!` 는 그대로 그 PID 다. nohup 과 bash 가 exec 해도 PID 는 바뀌지 않는다.
+  - 따라서 정확한 PID 보고(`echo "$pid"`, `:2314-2316`)와 `mam_monitor_started` 확인이 바뀌지 않는다.
+- 다음 기존 동작은 바뀌지 않았다.
+  - 중복 방지(`_monitor_pids`, `:2291`)
+  - `MAM_NO_SUBSCRIBER_DAEMON=1` 분기(`:2295-2296`)
+  - stdin `/dev/null`, 로그 append(`>> "$log_file"`), 작업 공간 cwd, `--idle-timeout 0`
+- 바뀐 것은 분기 안의 세 줄뿐이다.
+- 호출하는 곳은 모두 `$(…)` 안이다. 그래서 `set -m` 은 그 서브셸 안에서만 잠깐 켜진다.
+  - `update.sh:106`, `post_update.sh:41`, `install_phase.sh:64`
+  - `create_session.sh:748`, `resume_session.sh:162`
+
+### 1.2 이 Mac 에서 직접 확인 (`/bin/bash` 3.2, tty 없음, `set -euo pipefail`)
+
+- 같은 모양의 함수를 스크래치 스크립트로 만들어 돌렸다.
+  - 결과 1: `$(f)` 안에서 띄운 자식의 PGID 는 자기 PID 와 같다(53727 = 53727). 호출자의 PGID(53714)와 다르다.
+  - 결과 2: 직접 호출한 경우도 마찬가지다.
+  - 결과 3: 호출 뒤 `$-` 는 `ehuB` 로 그대로다. 곧 `m` 이 남지 않는다.
+  - 결과 4: "no job control", "[1] PID", "Done" 같은 잡 메시지가 stdout 에도 stderr 에도 나오지 않았다. 그래서 `$(…)` 로 받는 PID 출력이 오염되지 않는다.
+- **고치기 전 코드에서 실패하는지도 확인했다.**
+  - 방법: `git archive HEAD` 로 TMPDIR 에 사본을 풀었다. 그 사본의 `lib.sh` 만 1d63e88 판으로 바꿨다.
+  - 그 사본에서 `-k test_every_restart` 를 실행했다.
+  - 결과: **mode=0 의 3개(installed, killed, rolled-back)가 `left in the caller's group` 로 실패했다. mode=1 의 3개는 통과했다(3 failed, 3 passed).**
+  - 즉 새 assertion(`tests/test_issue72_update.py:723-724`)이 R2 를 실제로 잡는다. 수정 뒤 6개가 모두 통과한다(§3).
+  - 사본은 확인 뒤 지웠고, 남은 프로세스도 없다.
+- 세 경로와 두 모드: 정상 설치, 정지 시간 초과 뒤 복원, rollback 뒤 복원을 mode 0·1 로 돌리는 6 조합이 모두 같은 함수를 지나고, 모두 통과한다.
+  - rollback 경로는 되돌린 트리의 `lib.sh` 를 쓴다. 테스트 상자에서는 그 트리가 이 버전이다.
+
+### 1.3 python 경로와의 차이 (비차단, 참고)
+
+- 두 경로가 분리하는 정도가 다르다.
+  - python 경로(`daemon.py:95`): `start_new_session=True` 로 새 **세션**을 만든다. 그래서 제어 터미널에서도 떨어진다.
+  - legacy 경로: 새 **프로세스 그룹**만 만든다. 세션과 제어 터미널은 호출자와 같다.
+- 결정 2 의 요구("부른 쪽 프로세스 그룹에서 분리")는 이것으로 충족된다.
+  - 프로세스 그룹 신호(테스트 러너·timeout 래퍼의 killpg, 터미널의 SIGINT)는 이제 모니터에 닿지 않는다. 터미널 신호는 전경 그룹에만 가는데, 모니터는 배경 그룹이다.
+  - 터미널이 닫힐 때의 SIGHUP 은 nohup 이 무시한다.
+  - 배경 그룹이 tty 에 읽고 쓸 때 생기는 SIGTTIN/SIGTTOU 도 없다. stdin 은 `/dev/null` 이고 출력은 로그 파일로 간다.
+- `lib.sh:246-253`(shim 서버 기동)은 같은 문제에 `start_new_session=True` 를 쓰는 관례를 적어 두었다. legacy 경로만 `set -m` 을 쓴다.
+  - 브리프가 "가장 작은 수정" 을 요구했고, legacy 경로는 opt-in 이므로 결함으로 보지 않는다.
+
+## 2. 테스트의 `pkill` 제거 (`tests/test_issue72_update.py:184-194`, `:218-240`)
+
+### 2.1 새 teardown 이 정리하는 것
+
+- 패턴 kill 이 없어졌다. `tests/test_issue72_*.py` 전체에 `pkill`·`killall` 이 남아 있지 않다(grep 으로 확인).
+- 대신 다음 순서로 정리한다.
+  1. 테스트가 `Box.helper`(`:132-135`, `start_new_session=True`)로 띄우고 `b.helpers` 에 기록한 프로세스의 그룹을 `killpg` 하고 `wait` 한다.
+  2. 이 테스트의 작업 공간 `ws` 에 대해 `bash <ws>/…/reconcile.sh --subscribe` 형태로 정확히 맞는 모니터(`_exact_monitor_pids`)와 그 자손(`_descendants`, `pgrep -P` 재귀)만 SIGKILL 한다.
+- 남은 프로세스 확인: 명령줄에 `ws` 가 들어 있는 살아 있는 프로세스가 10초 안에 없어지지 않으면 이름을 적어 실패한다(`_processes_naming`, `:236-240`).
+  - `ws` 는 basetemp 아래의 테스트별 경로다. 그래서 다른 작업 공간의 프로세스와 겹치지 않는다.
+
+### 2.2 남은 프로세스 확인이 약해지지 않았는지
+
+- 예전 `pkill -KILL -f <ws>` 는 `ws` 를 명령줄에 가진 것을 **조용히 죽였을** 뿐이다. 남은 프로세스를 확인하지는 않았다.
+- 새 방식은 정확히 고른 것만 죽인다. 나머지 가운데 `ws` 를 가진 프로세스가 남으면 **실패로 드러낸다**.
+  - 그래서 확인은 더 강해졌다.
+  - 대가가 하나 있다. 그런 프로세스가 생기면 정리되지 않고 남는다. 다만 이름이 실패 메시지에 나오므로 사람이 정리할 수 있다.
+- `ws` 를 명령줄에 갖지 않은 손자(예: stub 모니터의 `sleep 120`)는 두 방식 모두 패턴으로는 못 찾는다.
+  - 새 방식은 모니터의 자손으로 찾아서 정리한다. 따라서 이 부분도 약해지지 않았다.
+- 이번 실행에서 teardown 실패는 없었다. 실행 뒤 `ps` 로 봐도 테스트가 남긴 프로세스가 없다(§3).
+
+## 3. 실행한 테스트 (이 Mac: macOS, `/bin/bash` 3.2, `/usr/bin/python3` 3.9.6)
+
+```
+cd <검증 경로>
+env -u HERDR_SOCKET_PATH -u HERDR_PANE_ID -u HERDR_TAB_ID -u HERDR_WORKSPACE_ID -u HERDR_SESSION_NAME \
+    -u HERDR_SESSION -u WORKSPACE_ROOT -u MAM_ENV_FILE -u MAM_JOBS_DIR -u DELEGATE_JOB_LOGS_DIR \
+    PYTHONDONTWRITEBYTECODE=1 /Users/godopu16/PuKi/laa/canary_projects/multi-agent-mux/.venv/bin/python \
+    -m pytest -p no:cacheprovider --basetemp="$TMPDIR/claude-j1d2c-bt" -q -rfs \
+    tests/test_issue72_update.py tests/test_issue19_subscriber_daemon_lifecycle.py \
+    tests/test_issue5_phase1_delegation.py
+```
+
+- 결과: **132 passed, 0 failed, 0 skipped** (191 s)
+  - `test_every_restart_starts_a_real_monitor_in_both_delegation_modes` 의 6 조합이 이 안에 들어 있다.
+  - `test_issue19`·`test_issue5_phase1` 의 watchdog 시험(중복 방지, `MAM_NO_SUBSCRIBER_DAEMON`, PID 보고, legacy·python 동등성)이 모두 통과한다.
+- 고치기 전 대조 실행: TMPDIR 사본, `-k test_every_restart` → 3 failed(mode=0), 3 passed(mode=1). 자세한 것은 §1.2.
+- 테스트 뒤 남은 프로세스: 테스트가 띄운 `reconcile.sh`, stub monitor, mock herdr, 구독자는 없다. 남은 것은 원래 있던 셋이다.
+  - 본 체크아웃 모니터 3714
+  - 이번 루프 7552
+  - 이번 잡을 디스패치할 때 띄운 job_subscriber 53086
+
+## 4. 발견 사항
+
+### 차단
+
+- 없음.
+
+### 비차단
+
+- **N8 (이월, R2 에도 해당).** rollback 뒤 재기동은 결정 2 에 따라 **되돌린 옛 트리의** `start_watchdog` 을 쓴다.
+  - 그래서 실제로 이 PR 이전 버전으로 되돌리면, `MAM_DELEGATION_PY=0` 에서는 옛 `nohup … &` 그대로라 호출자 그룹에 남는다.
+  - 이 PR 이후 버전 사이의 rollback 에서는 해결된다.
+  - 결정 2 가 정한 방식("되돌린 트리의 함수")에서 생기는 한계라 결함으로 보지 않는다.
+- **1.3 의 세션 차이.** legacy 경로는 프로세스 그룹만 분리하고, python 경로는 세션까지 분리한다. 결정 요구는 충족한다.
+- N5·N6·N1·N3·N4 는 이번 범위 밖이라 그대로다.
+
+## 5. 사용자 확인 필요
+
+- N8: rollback 대상이 이 PR 이전 버전이고 `MAM_DELEGATION_PY=0` 인 경우를 받아들일지.
+  - 받아들이지 않는다면 결정 2 의 "되돌린 트리의 start_watchdog" 대신 `install_phase.sh` 복사본 쪽에서 분리해 띄우도록 결정을 바꿔야 한다.
+- 이전 라운드에서 넘어온 N2, 그리고 결정 8 문구 보강 건은 그대로다.
+
+## 6. 결론
+
+- R2 는 정상 설치, 시간 초과 복원, rollback 복원의 세 경로와 두 모드 모두에서 해결됐다.
+  - 고치기 전 코드에서 mode=0 이 실패하고, 고친 뒤 6개가 모두 통과하는 것을 이 Mac 에서 확인했다.
+- 분리 방식(`set -m`)은 중복 방지, opt-out, PID 보고, 로그를 바꾸지 않는다. bash 3.2 에서 잡 메시지 없이 동작한다.
+- 테스트의 패턴 kill 은 기록한 PID 와 정확히 맞는 모니터·자손 정리로 바뀌었다. 남은 프로세스 확인은 오히려 강해졌다.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-claude-01/report-5bdb3a81.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261020T133532Z-a1684a",
+  "base_sha": "ff8b381520ae04e80c73a9e18bfad73d47e853c9",
+  "head_sha": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "tree_sha": "0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a",
+  "review_commit": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "reviewer": "planner-reviewer-claude-01",
+  "job_id": "5bdb3a81",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-20T15:51:16Z"
+}

.agents/reports/planner-reviewer-claude-01/report-5bdb3a81.md

@@ -0,0 +1,116 @@
+# Issue #40 리뷰 — Class A 세션 ID 자동 확정, agy 다른 작업 공간 ID 오등록 방지 (job 5bdb3a81)
+
+- 리뷰어: planner-reviewer-claude-01
+- 검증 경로: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261020T133532Z-a1684a/1`
+- identity: HEAD `feccfd5e0356c8acf0438bc68bce7ea36ce2588e`, tree `0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a` 가 일치한다. 작업 트리는 clean 이고 `.mam` 은 없다.
+- 범위: base `ff8b381`..head 1커밋, 19개 파일. 판정은 base..head 전체에 대한 것이다.
+- 기준 문서: 이슈 본문과 댓글 전체(`issue40.txt`)를 끝까지 읽고 합의 사항과 대조했다.
+- 환경: macOS, Python 3.9.6.
+  - 실제 에이전트 홈은 `ls` 와 `lsof -p <agy pid>`(프로세스 테이블 조회)로만 봤다. 파일 자체를 연 적은 없다.
+  - 재현과 테스트는 모두 scratchpad 의 임시 HOME, mock herdr, git archive 사본에서 했다.
+
+## 결론
+
+합의된 설계(PR #41 리뷰·이슈 댓글)대로 구현됐고, 완료 조건 1-4 가 테스트로 고정됐다. 각 조건의 테스트는 base 에서 실패하고 head 에서 통과한다. 이 변경이 만든 회귀는 찾지 못했다. 남은 것은 테스트 보강 권고와 운영 위험 기록이다.
+
+## 설계 확인 (합의 대비)
+
+**어댑터는 사실과 판정만 제공한다.**
+- `id_lifecycle`: 기본값은 `POST_DISCOVERED`. claude·grok 만 `PRE_ASSIGNED` 이다(`base.py:378-381`, `claude.py:188`, `grok.py:18`).
+- `capture_active_session_id`(`base.py:383-401`): `discover()` 후보 가운데 `verify_session_uuid` 를 통과하고 다른 행이 기록하지 않은 것이 정확히 하나일 때만 `captured` 를 돌려준다. 그 밖에는 이유가 담긴 결과(`capture_result`)를 돌려준다. 읽기 전용이다.
+- 설정 추가나 리팩터링은 없다.
+
+**agy 경로 (`agy.py`)**
+- `verify_artifact` discover 모드(`:97-106`): `last_conversations.json` 이 그 id 를 다른 cwd 에 매핑하면 거절한다(workspace_key 로 비교). 다른 행이 기록한 id 는 캐시가 일치해도 항상 거절한다. 이제 캐시 일치가 이 검사를 건너뛰지 못한다.
+- `capture_active_session_id`(`:129-152`): 후보는 `last_conversations.json[cwd]` 하나뿐이다. 그 대화의 presence lock 이나 DB 를 그 행의 pane 프로세스 또는 그 자손이 열고 있어야 확정한다(`_owner_check`, `:154-183`, lsof/ps). 증명하지 못하면 확정하지 않는다.
+- 이 근거를 실제로 확인했다. 이 Mac 에서 실행 중인 agy 3개(`--conversation <id>`)는 모두 자기 `presence/<id>.lock` 을 열고 있다(`lsof -p`).
+- `_holder_pids`·`_process_parents` 를 macOS 에서 직접 확인했다. 아무도 안 연 파일은 `[]`, 연 파일은 보유 pid 를 돌려준다(0.13s). ps 표에는 자기 pid 가 들어 있다.
+
+**reconcile drift C (agy·hermes·opencode·codex) 가 하나로 합쳐졌다** (`reconcile.sh:778-811`).
+- 네 에이전트가 모두 `autopin.capture` 를 거쳐 같은 어댑터 판정을 쓴다. agy 의 `*.db` 전체 glob 은 사라졌다.
+- 기존 안전장치는 그대로다: 후보가 둘 이상이면 C-ambiguous, 뷰포트가 다르면(rc 1) C-warn 으로 pin 안 함, 뷰포트 확인이 불가하면(그 밖의 rc) degraded pin.
+- 다른 행이 가진 id 배제는 더 엄격해졌다. 예전에는 같은 cwd 의, 멈추지 않은, 같은 에이전트 행만 봤다. 지금은 다른 모든 행의 모든 own key 를 본다(`autopin.claimed_elsewhere`).
+- 지운 hermes·opencode·codex SQL 은 각 어댑터의 `discover()` 와 같은 범위(cwd·epoch·`parent_id IS NULL`)다. codex 는 `CODEX_HOME` 을 따른다(`codex.py:65`).
+
+**수신 측 처리기 (`lib_py/agents/autopin.py`)**
+- 호출 지점:
+  - 래퍼: `finalize_unfinished` 뒤 `completed` 일 때(`multi-agent-mux-delegate-job:454-458`). stderr 로만 출력하므로 마지막 stdout 줄(audit-log 경로) 계약은 그대로다.
+  - `create --onboard` 의 completed 분기(`create_session.sh:754-756`)
+  - 루프 `wait_for_job` 직후의 서브프로세스(`runner.py:679, 690-705`, G9 경계를 지킴)
+- 공통 헬퍼 `delegate_autopin_completed`(`lib.sh:2470-2480`)는 `|| true` 라 잡 결과와 종료 코드를 바꾸지 않는다. `set -u` 에서 쓰는 변수(`AGENT_SESSIONS_YAML`, `_disp_tok`, `DELEGATE_JOB_TOKEN`, `task_reg_dir`)는 모두 정의돼 있다.
+- 중복 방지:
+  - 키는 `(job_id, dispatch_token, attempt_id)` 이다. 잡 디렉터리의 `autopin.lock`(flock)과 `autopin.json` 마커를 쓴다. 마커는 원자 교체로 쓴다.
+  - 쓰기는 `atomic_dump_yaml` 의 mutation 으로 한다. 이 모듈의 `_MUTATION` 을 `sys.modules[__name__]` 로 찾아 `python -m` 에서도 같은 객체를 쓴다. 쓸 것이 없으면 `SystemExit(0)` 으로 쓰지 않고 끝나며, `atomic_yaml.py:195` 의 finally 가 정리한다.
+- 건너뛰는 잡: remote, human, completed 가 아닌 잡, 오래된 token. pre-assigned 와 이미 id 가 있는 행은 쓰기 없이 끝난다.
+- 메타데이터: pin 은 `session_id_source=discovered`, `session_id_verified=true` 를 함께 기록한다. reconcile 의 `_pin_and_verify_resume` 도 같은 `pin_row` 를 쓴다. 이슈 댓글이 짚은 불일치(선택 항목)가 해결됐다.
+- publish_event.py 는 바뀌지 않았다. 에이전트는 제어 평면에 쓰지 않는다(`test_call_sites_and_publisher_boundary`).
+- 잠금 안에서 뷰포트 확인과 resume `--dry-run` 을 서브프로세스로 실행한다. 예전 reconcile 도 mutation 안에서 똑같이 했다. `load_state_json` 은 YAML flock 없이 SQLite 를 읽으므로 교착은 없다.
+
+## 완료 조건별 테스트 (base 실패 / head 통과)
+
+`tests/test_issue40_auto_pin.py`(27개)를 base 사본에 넣어 실행하면 **16 failed, 13 errors**(errors 는 base 에 없는 `agy._holder_pids` 를 패치하는 fixture 때문), **41 passed**(issue64 포함) 이다. head 에서는 issue40+issue64 **70 passed**.
+
+| 조건 | 테스트 | base 결과 |
+|---|---|---|
+| 1 | `test_agy_verify_rejects_id_cached_for_another_workspace` | `True is False` |
+| 1 | `test_reconcile_does_not_pin_another_workspaces_agy_conversation` | `'b4000002…' is None` — 실제로 B 의 id 를 A 행에 기록함 |
+| 1 | `test_autopin_does_not_pin_…` | — |
+| 1 | issue64 `:407` 단언 | `is False` 로 바뀜 |
+| 2 | `test_completed_onboarding_pins_agy_without_daemon`(MAM_NO_SUBSCRIBER_DAEMON=1, B 가 더 늦게 갱신) | — |
+| 2 | `test_completed_first_job_pins_opencode_codex_hermes`[3] | 실패 |
+| 2 | `test_reconcile_pins_agy_owned_by_the_pane`, `test_lib_sh_helper_pins_through_the_cli`, `test_create_onboard_pins_without_daemon` | 실패 |
+| 3 | `test_wrapper_and_loop_recovery_pin_once`(capture 1회, YAML mtime 불변), `test_loop_recovery_pins_when_the_wrapper_did_not` | 실패 |
+| 3 | `test_ambiguous_candidates_leave_reason_without_pin`(행에 `autopin ambiguous (job amb): 2 candidates`) | 실패 |
+| 4 | `test_preassigned_and_existing_ids_are_untouched`, `test_ineligible_jobs_pin_nothing`, `test_stale_dispatch_token_pins_nothing` | — |
+
+- reconcile 테스트는 세션을 mock herdr state 에 running 으로 등록한다(`_mock_agent`). 그래서 drift A 에서 멈추지 않고 실제로 drift C 까지 간다. base 에서 B 의 id 가 기록되는 것이 그 증거다.
+
+뮤테이션: git archive 사본에서 issue40 모듈만 돌렸다.
+
+| 뮤테이션 | 결과 |
+|---|---|
+| 다른 cwd 거절 제거 | 1 failed |
+| 중복 마커 무시 | 2 failed |
+| 모호 판정 제거 | 1 failed |
+| agy 소유 확인 제거 | 4 failed(같은 cwd 형제 교차 pin 포함) |
+| 이미 id 가 있는 행 보호 제거 | 1 failed |
+| remote·human 제외 제거 | 2 failed |
+| 래퍼 호출 제거 | 1 failed(정적 검사만 잡음) |
+| **pre-assigned 보호 제거** | **실패 0** (아래 T1) |
+
+## 관련 테스트 묶음
+
+- 조건: `env -i`, 임시 HOME, `XDG_DATA_HOME=<scratchpad>`, basetemp 는 scratchpad.
+- 대상 18개 모듈: issue40, issue64, a4, issue10_13, issue31, issue50_dispatch, issue55, issue57, issue60_linux_fixes, issue60_opencode_v2, tier1, tier2, uuid_target, orc_onboard, issue21_phase2_loop_a, issue5_phase3_loop, issue21_worktree_prereqs, issue17_workspace_root_isolation.
+- 결과: **577 passed, 1 skipped, 3 failed**, 18분.
+- 실패 3개(`test_issue21_phase2_loop_a::test_w10_…[install.sh|install_mam.sh]`, `test_w11_…`)는 환경 탓이다.
+  - 설치 스크립트가 시스템 python3 의 PyYAML 을 찾는데, 이 Mac 의 PyYAML 은 사용자 site(`~/Library/Python/3.9/...`)에만 있다. 내가 HOME 을 임시로 바꿔서 보이지 않았다.
+  - base 사본에서도 같은 3개가 같은 이유로 실패하고, 설치 스크립트는 이 diff 에 없다. 판정 근거로 쓰지 않았다.
+- skip 1개: PATH 에 opencode 가 없는 실바이너리 계약 테스트.
+- 부작용 확인:
+  - 실제 `~/.gemini/antigravity-cli/conversations`·`~/.hermes`·`~/.local/share/opencode` 목록은 전후가 같았다.
+  - scratchpad XDG 디렉터리는 실행 뒤에도 비어 있었다.
+  - #55 가드 오탐은 없었다.
+- 린트:
+  - `git diff --check` 는 깨끗하다.
+  - 바뀐 셸 4개(lib.sh, create_session.sh, 래퍼, reconcile.sh)가 `/bin/bash -n`(3.2)을 통과한다.
+  - 바뀐 Python 은 3.9 로 파싱된다. `/usr/bin/python3` 로 `lib_py.agents.autopin`·`lib_py.loop.runner` 를 import 할 수 있다.
+
+## 비차단
+
+- **T1. pre-assigned 보호(`autopin.capture` 의 `id_lifecycle != POST_DISCOVERED`)는 테스트로 고정되지 않았다.**
+  - 테스트의 claude·grok 행은 이미 id 가 있어서 `already-set` 에서 먼저 끝난다.
+  - id 가 비어 있는 claude 행이 생기면(예: 행을 손으로 고침), 이 보호 없이는 기본 capture 가 claude `discover()` 로 남의 transcript 를 pin 할 수 있다.
+  - 권고: `claude_session_id_own: None` 인 claude 행에서 `pre-assigned` 가 나오는지 확인하는 한 줄을 추가한다.
+- **T2.** 래퍼 진입점은 정적 검사(`test_call_sites_…`)로만 고정됐다. 헬퍼(`lib.sh`)와 CLI, create, 루프는 실행으로 검증됐다.
+- **R1. agy 의 pin 은 이제 세 가지에 기댄다**(reconcile drift C 도 같다):
+  - (a) lsof·ps 가 있어야 한다
+  - (b) 행에 pane pid 가 있어야 한다
+  - (c) agy 가 presence lock 을 열고 있어야 한다
+  - (c) 는 resume 된 agy 3개에서 확인했다. 새로 띄운 agy 의 첫 턴 직후는 실제 agy 를 띄울 수 없어 확인하지 못했다.
+  - lsof 가 없는 Linux 에서는 agy 가 영영 pin 되지 않는다. 예전 glob 경로는 pin 했다(오등록 위험을 감수하고). autopin 경로는 행에 `autopin unverifiable-owner … lsof is unavailable` 을 남기지만, reconcile 은 아무것도 남기지 않는다.
+  - 설계상 의도된 안전 쪽 선택이다. 그래도 Linux 의존성으로 문서에 한 줄 적어 두기를 권한다.
+- **R2.** 중복 마커는 실패 결과도 기록한다. 래퍼 시점에 `no-candidate` 였던 잡은 루프 복구 경로에서 다시 시도되지 않는다. 다음 잡의 completed 나 reconcile 이 다시 시도한다. 합의("job/token/attempt 단위로 중복 금지")와 맞다.
+- **범위 밖(보고만).** stop 의 캡처 경로는 정리하지 않았다(이슈가 "크면 하지 말고 보고만"이라고 함).
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-claude-01/report-af549b13.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261023T035928Z-2ccc02",
+  "base_sha": "dc886ecd6b38c01032a55a2d1c230c73362ae630",
+  "head_sha": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "tree_sha": "f1af6fdd548ee5d6f6b81e2202833edfaca98188",
+  "review_commit": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "reviewer": "planner-reviewer-claude-01",
+  "job_id": "af549b13",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-23T05:16:58Z"
+}

.agents/reports/planner-reviewer-claude-01/report-af549b13.md

@@ -0,0 +1,114 @@
+# PR #69 (Issue #63) 리뷰 — head 1614af5
+
+- 리뷰어: planner-reviewer-claude-01 (macOS, bash 3.2, /usr/bin/python3 3.9.6)
+- 검증 경로: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261023T035928Z-2ccc02/1`
+- identity 확인: HEAD 1614af5b673d7519d3a38f63e3636055592b4f14, tree f1af6fdd548ee5d6f6b81e2202833edfaca98188, `git status --porcelain --ignored` 비어 있음, `.mam` 없음 (시작·종료 시 모두). main HEAD dc886ec 그대로.
+- 범위: base dc886ec..1614af5 전체(커밋 13개).
+  - ede9c62 까지는 이전 리뷰(잡 8445af7f, 55f86b49)에서, 8f64174·7cac6f6 은 잡 1c6eca2b 에서 봤다. 그 결론을 다시 확인했다.
+  - 이번에는 1614af5 와 세 수정 사이의 정합성을 중점으로 봤다.
+- 참고: 같은 head 를 맡은 잡 906427d1 은 관련 스위트 도중 검증 경로(`…a646cb/3`)가 사라져 끝내지 못했다. 그 잡에서 얻은 head 결과(issue63 27 passed, 변이 결과)는 같은 tree 의 스크래치 사본에서 나온 것이다. `diff -rq` 로 이번 검증 경로와 같음을 확인했다.
+
+## 1. 1614af5 가 바꾼 것
+
+- `.agents/skills/lib_py/agents/id_order.py:223`: `elif sess == me or not sess:` 를 `elif not sess:` 로 바꿨다.
+  - 그래서 호출자 자신의 세션 이름에 남은 죽은 owner 마커도 고아 규칙을 따른다. 이번 시도의 행이 등록되면 지우고(:225), herdr 가 정상 목록으로 "없음"이라 답하면 지우고(:228-229), 그 밖에는 남긴다.
+- `_read_and_prune_markers` 의 `me` 인자를 지웠다(:183, :308).
+- `blockers` 는 ede9c62 부터 `m_sess == me` 를 건너뛰지 않는다(:136-144). 그래서 남은 자기 이름 마커가 실제로 막는다.
+
+## 2. 세 수정이 각 지적을 닫는가, 서로 어긋나지 않는가
+
+1. **8f64174 — 조회 실패를 "없음"으로 읽던 문제**
+   - `herdr_session_state` (:58-86) 는 정상 파싱한 `agent list` 에 이름이 없을 때만 False 를 돌려준다. 그 밖에는 None 이다.
+   - prune 은 `drop = live is False` (:228) 다.
+   - 변이 m1(`not live`)과 m2(rc≠0 → False)가 테스트에 잡혔다(잡 1c6eca2b).
+2. **7cac6f6 — 상한 0 에서 30 초 조회, server_not_running**
+   - 조회 시간은 `deadline - now` 다(:288). timeout≤0 이면 None 을 돌려준다(:64-65).
+   - 변이 m4(고정 30 s)와 m7(timeout≤0 에도 조회)이 잡혔다.
+   - 상한 0 테스트는 0.3 s 안에 끝나는 것을 확인한다(test :1222-1224).
+3. **1614af5 — 같은 이름의 죽은 owner 마커를 확인 없이 지우던 문제**
+   - 옛 규칙(`sess == me` 이면 drop)을 되돌린 변이 사본에서는 두 테스트가 실패한다: `test_id_order_dead_owner_marker_blocks_while_its_unregistered_herdr_session_is_alive`, `test_id_order_real_probe_against_mock_herdr_fails_closed`.
+   - 커밋 메시지가 말한 "재시도의 실패 정리가 살아 있는 pane 을 죽임"도 막힌다. create 의 대기(`create_session.sh:287`)는 롤백 trap 설치(:367)보다 앞서 있어서, 대기에서 거부(exit 1)되면 `cleanup_herdr_on_error` 가 돌지 않는다.
+4. **정합성**: 세 수정은 모두 `_read_and_prune_markers` 의 "죽은 owner 마커" 분기 하나를 쓰고, 조회는 `bounded_probe` 하나를 거친다. 자기 이름 마커만 다른 규칙을 쓰던 예외가 사라져서 규칙이 하나로 모였다. 어긋나는 곳은 찾지 못했다.
+
+## 3. 흔한 사용을 600 초 대기로 막지 않는가
+
+스크래치에서 `id_order.wait` 를 프로세스 안에서 직접 불렀다. 조회 함수를 주입하고, cap 2 s(일부 0 s)로 돌렸다.
+
+**정상 사용 (실패 없음)**: 막지 않는다.
+- create 마커가 남은 채로, 그 세션이 다음 상태일 때 같은 이름으로 resume 했다:
+  - stopped 이고 own id 가 기록됨
+  - stopped 이고 id 없음 (herdr-dead stop)
+  - reconcile 이 terminated 로 바꿈
+- 세 경우 모두 herdr 가 **답하지 못해도**(None), cap 0 에서도 rc=0 이었다.
+- `blockers` 의 `pinned_for_attempt` 와 `ended_after_attempt` (:158-171) 가 이 경우들을 걸러낸다.
+- 정상 create/resume 이 끝난 뒤의 마커는 행이 running 인 동안에는 `_registered_for_attempt` (:177-180) 로 지워진다.
+
+**실패 뒤 재시도**:
+
+| 경우 | herdr 가 "없음" 응답 (서버 살아 있음) | herdr 무응답 (서버 꺼짐 등) |
+|---|---|---|
+| create X 가 행 쓰기 전에 실패(exit 42 롤백) → create X 재시도 | rc=0, 0.0 s | rc=1, cap 만큼 대기 |
+| resume X 가 spawn 에서 실패(행 그대로) → resume X 재시도 | rc=0, 0.0 s | rc=1, cap 만큼 대기 |
+| 위 resume 실패 → 같은 cwd 에서 create Y | rc=0, 0.0 s | rc=1, cap 만큼 대기 |
+
+- 7cac6f6 사본으로 같은 시뮬레이션을 돌리면 무응답 열의 위 두 줄(같은 이름 재시도)이 rc=0 이다.
+- 즉 1614af5 는 서버가 살아 있는 흔한 재시도는 그대로 두고, herdr 가 답하지 못하는 재시도만 막는다. 이는 아래 R1 이 같은 이름까지 넓어진 것이다.
+
+## 4. 그 밖의 확인
+
+브리프 항목 1·2·4·5·6·8(완료 조건 테스트, autopin 재사용, resume·stop, 지운 심볼, issue34 무관)은 1614af5 가 `session_ids.py`, `lib.sh`, 셸 스크립트, 문서를 건드리지 않으므로 이전 리뷰의 결론 그대로다.
+
+**macOS**:
+- `/usr/bin/python3` 3.9.6 으로 `lib_py.agents.id_order` import 가 성공한다(잡 1c6eca2b; 1614af5 는 문법 요소를 더하지 않는다).
+- 잠금은 `fcntl.flock` 이다(:294-295).
+
+**실제 herdr 를 건드리지 않았는가**:
+- 기존 서버 두 개(pid 3407 `herdr server`, 8323 `herdr --session multi-agent-mux server`)는 스위트 전후로 같다(시작 시각 08:21).
+- 스위트 중 13:22 에 `herdr --session mam-pylecturenotes server` 가 새로 보였다. 하지만 이 프로세스는 실제 HOME 과 `WORKSPACE_ROOT=/Users/godopu16/PuKi/lac/curriculum/01_python_getting_started_lecturenotes` 로 떠 있고, 사용자의 attach 클라이언트(13:27)가 붙어 있다. 테스트는 HOME 을 스크래치로 바꿔 돌므로 다른 작업 공간의 것이다.
+
+## 5. 실행한 테스트
+
+모두 `env -i`, 임시 HOME/XDG, `PYTHONDONTWRITEBYTECODE=1 -p no:cacheprovider --basetemp=<scratchpad>` 로 돌렸다. 테스트에서 .mam.env 를 export 하지 않았다.
+
+| 대상 | 결과 |
+|---|---|
+| 검증 경로: `tests/test_issue63_same_cwd_ids.py` + 관련 19개 모듈 (issue40_auto_pin, issue64_ro_connect, issue10_13_purge, issue31_purge_residual, issue42_skill_blocks, tier1_unit, tier2_component, b4_session_created, issue24_resume_dialogs, issue30_stall_watch_stop, issue23_24_startup_path, issue45_restore, issue50_pane_lock, c1_tui_readiness, issue6_fail_closed, issue60_opencode_v2, issue60_linux_fixes, uuid_target, issue17_workspace_root_isolation) | **597 passed, 2 skipped, 0 failed** (32 분) |
+| 같은 tree 스크래치 사본: issue63 단독 | 27 passed |
+| base 사본 + head 테스트 | 27 errors (`ImportError: id_order`). 조건별 base 실패는 1차에서 22 failed + 1 passed 로 확인했다 |
+| 변이: 1614af5 를 되돌림(자기 이름 마커를 drop) | 2 failed (위 두 테스트) |
+
+## 6. 차단 결함
+
+없음.
+
+## 7. 비차단
+
+### R1 (잡 1c6eca2b 의 R1, 범위가 넓어짐): herdr 가 답하지 못하는 고아 마커는 같은 폴더·같은 종류의 create/resume 을 매번 cap 동안 붙잡는다
+
+- 이제 같은 이름 재시도도 포함된다(위 표).
+- 서버가 꺼진 상태(server_not_running)가 대표적이다.
+  - 조회는 서버를 띄우지 않는다(:67).
+  - create/resume 은 대기를 통과해야 spawn 으로 서버를 띄운다(`create_session.sh:287`→:289, `resume_session.sh:243`→:260).
+  - 그래서 다른 무언가가 서버를 켜기 전까지는 기본 600 s 를 기다린 뒤 거부가 반복된다.
+- 회복 경로는 있다: 메시지의 `HERDR_SESSION_NAME=<srv> herdr kill-session -t <s>` 를 shim 으로 실행하면 서버가 기동된다(잡 1c6eca2b 의 가짜 herdr 재현에서 `--session srv-down server` 1회).
+- 생기는 조건은 "행 등록 전 실패나 kill"에 "서버가 꺼짐"이 겹치는 경우다. 정상 사용과 서버가 살아 있는 재시도는 막지 않는다(3절).
+- 권고 (둘 중 하나):
+  - (a) server_not_running 만은 "없음"으로 읽는다. MAM 서버는 restore 가 꺼져 있어서 꺼진 서버 위에는 살아 있는 pane 이 없다. `lib.sh:204-207` 의 ISSUE-9 규약과도 맞는다.
+  - (b) 그 경우는 cap 을 기다리지 말고 바로 거부한다. 메시지는 "서버가 꺼져 있음 → 위 명령으로 정리"처럼 사실대로 쓴다.
+- fail-closed 를 택한 것은 루프에서 정한 설계 선택이라 차단으로 두지 않는다.
+
+### 그 밖의 비차단 (잡 1c6eca2b 와 같음)
+
+- **N1**: 조회가 `MAM_NO_AUTOSTART=1` 을 쓴다는 것(:67)을 고정하는 테스트가 없다.
+- **N2**: sanitize 한 이름 비교(:85)를 고정하는 테스트가 없다.
+- **N3**: `flock(LOCK_EX)` 대기(:295)는 시간 제한이 없다. 다른 호출자가 앞 대기의 남은 시간만큼 더 기다릴 수 있다. 상한은 있다.
+- **N4**: create·resume SKILL.md 의 exit 1 설명이 고아 마커로 거부되는 경우와 그 정리 방법을 말하지 않는다.
+- **N5**: 이전 라운드의 비차단 항목이 남아 있다: resume `mam_id_order_wait` 제거가 테스트로 고정되지 않음, c6(b) 의 1.5 s 타이밍 flake, lib.sh `--herdr-server` 전달이 테스트되지 않음.
+
+## 8. 결론
+
+- 1614af5 는 codex 의 3차 지적(같은 이름의 죽은 owner 마커를 확인 없이 지움)을 닫는다. 8f64174·7cac6f6 과 같은 고아 규칙 하나로 모였다.
+- 정상 create/resume 과 서버가 살아 있는 재시도는 막지 않는다.
+- herdr 가 답하지 못할 때 cap 동안 기다리는 비용(R1)은 회복 경로가 있는 설계 선택이므로 비차단이다.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-claude-01/report-f39ae4ba.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261026T133440Z-c8961b",
+  "base_sha": "29cc4fd90478936f15387a7665e2c95d13a3f14c",
+  "head_sha": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "tree_sha": "98d57bdc60920238c115ece90c90cc694f2744bc",
+  "review_commit": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "reviewer": "planner-reviewer-claude-01",
+  "job_id": "f39ae4ba",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-26T17:32:11Z"
+}

.agents/reports/planner-reviewer-claude-01/report-f39ae4ba.md

@@ -0,0 +1,311 @@
+# PR #73 (Issue #71) 리뷰 — head 5f60653
+
+- 리뷰어: planner-reviewer-claude-01 (macOS Darwin 25.6, `/bin/bash` 3.2.57, `/usr/bin/python3` 3.9.6, BSD sed/tr)
+- 검증 경로: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2`
+- identity 확인 (시작·종료 시 모두):
+  - HEAD 5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26, tree 98d57bdc60920238c115ece90c90cc694f2744bc
+  - `git status --porcelain --ignored` 비어 있음
+  - `.mam` 없음. 추적 파일 `.mam.env.example` 만 있다.
+  - main HEAD 29cc4fd 그대로.
+- 범위: 29cc4fd..5f60653, 커밋 14개, 파일 28개 (+953/−176).
+- 읽은 것: 이슈 #71 본문과 댓글("범위 정리" 1–10항, #72 분리), PR #73 본문.
+
+## 0. 이번 잡(f39ae4ba)에 대해
+
+- 이 잡은 같은 루프의 검증 경로 `/2` 다. head 5f60653, tree 98d57bdc 는 앞 잡 0698ffc5(검증 경로 `/1`) 와 같다. 브리프의 확인 항목도 잡 ID와 경로를 빼면 글자까지 같다.
+- 그래서 아래 1장의 분석(파일:줄 근거, 리뷰어 시험 p1–p12, 변이 m1–m12, base 비교)은 같은 tree 의 `git archive` 사본에서 얻은 결과를 그대로 쓴다.
+- 이번 경로 `/2` 에서 새로 확인한 것:
+  - 브리프에 붙은 diff(1920줄)가 `git diff 29cc4fd 5f60653` 와 바이트까지 같다. 커밋은 14개다.
+  - `/2` 의 `lib.sh` 에서 `_sanitize_herdr_agent_name` 을 다시 뽑았다. 정의는 하나이고, 앞서 비교한 정의와 같다.
+  - `/2` 의 `lib_py` 를 기준으로 bash↔Python 비교를 다시 돌렸다. 408건에 불일치는 0이다. python3 와 해시 도구가 모두 없는 5건도 기대대로 동작했다.
+  - 테스트 세 묶음을 `/2` 에서 다시 돌렸다. 결과는 아래 2장 표와 같다.
+    - issue71+issue66: 77 passed
+    - A: 384 passed, 1 skipped
+    - B: 543 passed, 3 skipped
+  - 실제 herdr 서버 두 개(pid 11655, 69309)는 실행 전후로 같다.
+  - 시작과 끝에 `/2` 의 HEAD·tree 를 확인했다. `status --ignored` 는 비어 있고 `.mam` 은 없다. main HEAD 는 29cc4fd 그대로다.
+
+## 1. 확인한 것과 근거
+
+### 1) 완료 조건과 범위
+
+| 항목 | 결과 | 근거 |
+|---|---|---|
+| 1 attach 형태 | 충족 | 아래 3) |
+| 2 `default` 도 적음 | 충족 | 아래 3) |
+| 3 래퍼 attach | 충족 | 아래 3) |
+| 4 두 필드 삭제 | 충족 | 아래 4) |
+| 5 원칙(스킬로 시작·종료), 행 없는 stop | 충족 | 아래 4), 5) |
+| 6 attach 는 예외 | 충족 | attach 만 herdr 명령을 직접 쓴다 |
+| 7 변환 규칙 하나 | 충족 | 아래 6) |
+| 8 해시 불가 시 오류 | 충족 | 아래 6) |
+| 9 마이그레이션 | 충족 | 아래 7) |
+| 10 stall_watch 한 곳 | 충족 | 아래 8) |
+
+- 보강 완료 조건도 모두 충족한다.
+  - 새 행에 두 필드가 없다.
+  - 해시 도구가 없으면 python3 로 같은 결과를 내고, python3 도 없으면 오류다.
+  - 옛 행의 마이그레이션은 멱등이고, YAML 과 DB 가 같다.
+  - 행 없는 stop 은 레지스트리를 바꾸지 않는다.
+  - 정리 안내는 stop 스킬 명령이다.
+- #72(update 스킬)는 끌어들이지 않았다.
+  - 진입점 `python3 -m lib_py.registry_format` 만 두었다.
+  - 그 진입점을 부르는 코드는 없다.
+- 본문 완료 조건 6(실제 에이전트를 32자 초과 이름으로 띄워 attach)은 수동 확인 항목이다. 브리프 제약(실제 에이전트·실제 herdr 금지)에 따라 하지 않았다.
+- 대신 형태가 맞는지는 확인했다. 실제 herdr 0.9.5 의 `agent attach --help` 를 격리 HOME 에서 보면 사용법이 `herdr agent attach <TARGET> [OPTIONS]` 이고, 옵션은 `--takeover` 다.
+
+### 2) 회귀 테스트 tests/test_issue71_herdr_names.py (70개)
+
+- head (검증 경로): issue71 70개와 issue66 7개를 함께 돌려 77 passed.
+- base: 29cc4fd 사본에 head 의 테스트 파일을 넣었다. conftest 는 이 PR 에서 바뀌지 않았다.
+  - 결과: **68 failed, 2 passed**. PR 이 말한 숫자와 같다.
+  - 통과하는 2개:
+    - `test_the_names_need_converting_and_the_plain_one_does_not`: 변환 전제를 확인한다.
+    - `test_wrapper_attach_calls_herdr_with_the_herdr_name[PLAIN]`: 변환이 필요 없는 이름이라 base 에서도 맞다.
+- reconcile 경로 (`test_reconcile_registers_with_the_attach_command`, test :126-139) 는 행 등록 경로에 실제로 닿는다.
+  - mock herdr 에 `cwd=mam_sandbox`, `pane_id` 가 있는 agent 를 넣는다.
+  - 실행 전에 행이 없음을 확인한다 (:132).
+  - 실행 뒤 `last_visible_note == "auto-registered by monitor"` 인 행이 하나인지 확인한다 (:137-138).
+  - 변이 m10 (reconcile 을 옛 형태로) 이 이 테스트 3개를 실패시킨다.
+
+### 3) attach_command (`lib_py/agents/sanitize.py:34-43`)
+
+- 형태: `herdr --session <shlex.quote(server or "default")> agent attach <shlex.quote(sanitize(name))>`.
+  - 서버가 None 이나 빈 값이어도 `--session default` 가 된다.
+  - 변환된 이름은 `[a-z0-9_-]` 이므로 quote 를 해도 그대로다.
+  - 서버 `srv x` 는 `'srv x'` 로 감싸진다. 내 시험과 test :51 에서 확인했다.
+- 쓰는 곳은 네 곳이고, 모두 이 함수를 쓴다:
+  - create: `create_session.sh:566`
+  - resume 의 새 행: `update_yaml_resumed.sh:151`
+  - resume 의 서버 변경: `update_yaml_resumed.sh:161`
+  - reconcile: `reconcile.sh:676`
+- 마이그레이션도 같은 함수를 쓴다 (`registry_format.py:62`).
+- resume 의 else 분기는 서버가 바뀔 때만 attach_command 를 다시 쓴다 (:159-161).
+  - 서버가 그대로인 기존 행은 첫 쓰기의 마이그레이션이 이미 새 형태로 바꿔 둔다. 그래서 낡은 값이 남지 않는다.
+- lib.sh 래퍼 (`lib.sh:605-613`):
+  - `agent attach <t> ...` 의 첫 인자를 `_resolve_herdr_target` 으로 변환한다. get/read/prompt 와 같은 함수다.
+  - 나머지 `"$@"` 는 그대로 넘긴다.
+  - 테스트 :151-159 가 strict mock 에서 `["agent","attach",<herdr 이름>,"--takeover"]` 를 확인한다.
+  - 변이 m4 (원래 이름을 넘김) 는 LONG·UPPER 에서 잡힌다.
+
+### 4) kill_command·start_command 삭제
+
+- 코드·문서에는 이 두 키가 남아 있지 않다. 리뷰 트리 전체를 grep 했다.
+  - 남은 곳: 마이그레이션 상수 (`registry_format.py:37`), 테스트의 "옛 행" 픽스처와 부재 단언, 과거 리뷰 보관본 `.agents/reports/*`.
+- `status --json` 의 `start_command` 키는 빠졌다 (`status.sh:224-228`).
+  - 이 키를 읽는 코드나 테스트는 없다.
+  - status SKILL.md 의 예시도 같이 고쳤다.
+- 래퍼의 `new-session`/`kill-session` 가짜 명령은 남겨 두는 것이 맞다. 아직 쓰는 곳:
+  - create (`create_session.sh:266-276`, :346)
+  - stop (`stop_session.sh:157`, :307, :321)
+  - reconcile
+- 사용자에게 보이던 kill-session 안내 두 곳은 stop 스킬 명령으로 바뀌었다:
+  - create exit 43 (`create_session.sh:364`)
+  - id_order (`id_order.py:343-345`)
+  - 바뀐 명령 `stop_session.sh --session X --herdr-session S` 는 행이 없어도 동작한다 (아래 5).
+  - exit 43 은 `_mark_row_rolled_back "running" "rollback-failed"` 로 행을 남기므로, 그 경우는 행 있는 stop 경로를 탄다.
+
+### 5) 행이 없는 stop (`stop_session.sh:117-191`)
+
+- **행이 없을 때만 그 경로로 간다.**
+  - 행을 찾는 Python 은 행이 없을 때만 `sys.exit(7)` 을 낸다.
+  - `[ "${MAPPED_RC:-0}" -ne 7 ] || stop_rowless` (:189) 로 7 일 때만 row-less 로 간다.
+  - 다른 실패는 `cannot read the row` 로 exit 1 이다 (:190-193).
+  - 변이 m6 (0 이 아니면 모두 row-less) 은 `test_stop_does_not_take_an_unreadable_row_for_no_row` 에 잡힌다.
+- **레지스트리를 읽지 못할 때**는 `load_state_json strict` (:170, lib.sh:1598-1631) 가 exit 1 로 끝난다.
+  - 해당 경우: YAML 깨짐(DB 없음), DB 손상, sessions 테이블 없음, 테이블 전부 없음.
+  - 테스트 :514-541 의 4개 매개변수가 이를 확인한다.
+  - 인자 없는 기존 호출은 동작이 같다. strict 일 때만 raise 하거나 exit 한다.
+- **작업 공간 판정** (:142-151) 은 `realpath` 두 개를 비교한다: `cwd == root or cwd.startswith(root + os.sep)`. 내 추가 시험 (head 사본, `tests/test_zz_review71.py`) 결과:
+
+| 경우 | 결과 |
+|---|---|
+| p1 접두어 혼동 (`<ws>-other`) | exit 5, 닫지 않음 |
+| p2 밖에서 작업 공간 안으로 가는 심볼릭 링크 | 0, 닫음 |
+| p3 작업 공간 안에서 밖으로 가는 심볼릭 링크 | exit 5 |
+| p4 후행 슬래시 | 0 |
+| p5 WORKSPACE_ROOT 를 심볼릭 링크로 지정 | 0 |
+| p7 32자 초과 이름 (strict mock) | 0 |
+
+- **서버 결정 순서** (:107-113, :128-130) 는 `--herdr-session` → 환경의 `HERDR_SESSION_NAME` → 작업 공간 서버다.
+  - 환경 값이 비었거나 `default` 이면 작업 공간 서버로 간다. create 의 :185, :253 과 같은 규칙이다.
+  - p6 (환경 값 `default`) 에서 모든 `agent get` 이 작업 공간 서버로 간 것을 확인했다.
+  - 테스트 :487-499 는 환경 서버를 확인한다.
+- **레지스트리를 바꾸지 않는다.** 모든 row-less 테스트가 YAML/DB 해시를 비교한다 (`_registry_bytes`).
+- **`--purge-conversation`** 은 행이 없으면 exit 1 이다 (:124-126, test :544-550).
+- **종료 코드:**
+  - 0 / 1 / 5 / 6 은 SKILL.md 표 (:58-67) 와 헤더 주석 (:30-36), 코드 (:134, :154, :161, :163) 가 같다.
+  - `test_literal_exit_rule_on_base_scripts` 는 `{0..6}` 이다.
+  - skill_code_blocks 의 `entry_points` 도 5·6 을 더했다.
+
+### 6) 이름 변환 (`lib.sh:44-82`)
+
+- 정의는 하나다 (`lib.sh:44`). test :171 이 확인한다.
+- shim 은 `{ printf shebang; declare -f _sanitize_herdr_agent_name; cat <<'EOF' … } > "$tmp_file"` (:179-1393) 으로 같은 정의를 받는다.
+  - bash 3.2 의 `declare -f` 출력을 다시 source 한 사본도 아래 비교에 넣었다.
+  - 이 호스트의 `bash` 는 `/bin/bash` 3.2 하나뿐이라, 테스트의 shim 도 3.2 로 돈다.
+- has-session 의 `lambda s: s.lower()[:32]` 대체와 `os.path.abspath(".agents/skills")` import 는 없어졌다.
+  - 대신 lib.sh 가 계산한 `TARGET_SAN` 을 넘긴다 (:633-641).
+- **macOS 실측 비교:** 이름 34개를 Python `sanitize_herdr_agent_name` 과 비교했다.
+  - 이름: ASCII, 대문자, 32/33/40/200자, 숫자·`_`·`-n`·`-e`·`--help` 로 시작, `\n`(가운데·앞·뒤·연속), `\t`, `\r`, `*?[a]`, `\`, `%s`, `Ü`, `İstanbul…`, `日本語`, 이모지, `K`(U+212A), `ß`, `Dž`, `Ω…` 긴 이름, NBSP 등.
+  - 원본 정의와 `declare -f` 사본 2 벌 × 환경 6 개 (`LANG=en_US.UTF-8`, `LC_ALL=C`, 로캘 없음, `LC_ALL=UTF-8`+`LC_CTYPE=C`, 해시 도구 없이 python3 만 + UTF-8 또는 C) = **408 건, 불일치 0**.
+  - ASCII 가 아닌 이름은 바이트 단위 치환을 쓰지 않고 python3 의 문자 단위 `str.lower()`+치환을 쓰므로 Python 과 같다 (:51-56).
+- **해시 도구별:** `/sbin/sha1sum` 만, openssl(LibreSSL) 만, 깨진 shasum(빈 출력)에서 openssl 로 넘어가는 경우 모두 Python 과 같았다 (`mam-wt-issue-71-very-lo-54e536a7`).
+- **python3 도 해시 도구도 없을 때:**
+  - 짧은 ASCII 이름(대문자, 끝의 `\n` 포함)은 정상이다.
+  - 32자 초과는 `no shasum, sha1sum, openssl or python3` 오류로 rc 1 이다.
+  - ASCII 가 아닌 이름은 `not ASCII and there is no python3` 오류로 rc 1 이다.
+  - `00000000` 은 어디에도 없다.
+- 호출하는 곳은 실패를 넘긴다: `|| return 1`, `|| exit 1`, `wait_for_agent_idle` 은 `|| return 3`, delegate-job 은 진단만 건너뛴다.
+  - spawn 의 `agent_name` 계산은 루프 앞 (:688) 으로 옮겨졌다. 그래서 이름을 못 구하면 spawn 하지 않는다. test :267 이 확인한다.
+
+### 7) 레지스트리 형식 2 (`registry_format.py`, `atomic_yaml.py:118-137, :192`)
+
+- **순서:** 잠금 → `BEGIN IMMEDIATE` (:79-87) → DB 또는 YAML 읽기 → 마이그레이션 (:121-126) → 호출자 변경 (:144-149) → 검증 → DB 쓰기 → commit → YAML 쓰기.
+  - 마이그레이션은 잠금 안에서, 호출자 변경 전에 돈다.
+- **모든 행을 바꾼다.** `migrate` 는 이름이 있는 모든 행에서 두 키를 지우고 attach_command 를 다시 만든다.
+  - stopped·terminated 도 포함한다. 변이 m8 (running 만) 은 6 failed 로 잡힌다.
+- **YAML 도 반드시 다시 쓴다.** `force_yaml = True` (:126) 이고, 변이 m2 는 6 failed 로 잡힌다.
+- **멱등이다.** test :327-338 이 확인하고, 진입점을 두 번 부르면 `2 -> 2, rows changed: 0` 에 바이트도 같다 (test :342-362).
+- **YAML 교체가 실패한 뒤의 복구:** DB 가 2 이고 YAML 이 2 미만이면 다음 쓰기에서 `force_yaml` 이 된다 (:127-137).
+  - 진입점으로 하든 아무 쓰기로 하든 복구된다 (test :379-411).
+  - 변이 m3 은 2 failed 로 잡힌다.
+- **다른 쓰기 경로:** 레지스트리 YAML/DB 를 쓰는 코드는 `atomic_yaml` 하나뿐이다.
+  - grep 결과 `safe_dump`, `INTO state/sessions` 는 이 파일에만 있다. hermes.py 의 DELETE 는 에이전트 자신의 DB 다.
+  - orc_onboard 와 autopin 도 `atomic_dump_yaml(_main)` 을 거친다.
+  - 호출자 변경 가운데 `d` 를 통째로 새로 만드는 것은 없다. 만들어도 다음 쓰기가 다시 마이그레이션하므로 형식 키를 잃지 않는다.
+- **읽기 경로:** `load_state_json` 과 `lib_py.state` 는 바꾸지 않았다. strict 인자만 더했다.
+- **미래 형식 (p8):** `registry_format: 3` 이면 진입점은 `3 -> 3, rows changed: 0` 이다. 쓰기 뒤에도 키는 3 으로 남고, 행(옛 키 포함)도 그대로다. 내려 쓰지 않는다.
+- **비정상 값 (p9):** `"2"`, `True`, `None` 은 1 로 보고 2 로 바꾼다. `0` 은 `0 -> 2` 로 출력된다.
+- **진입점 계약:**
+  - 성공은 stdout 한 줄 `registry-format: <from> -> <to>, rows changed: <n>` 에 exit 0 이다.
+  - 레지스트리가 없으면 exit 1 이다 (test :423).
+  - DB 손상 (p10) 은 stderr `registry-format: error: file is not a database` 에 exit 1 이고 stdout 은 비어 있다.
+  - 검증 거부 (p11) 는 `registry-format: error: VALIDATE: … bad status` 에 exit 1 이다.
+  - 모두 docstring 과 같다.
+- **macOS persistent WAL:** YAML/DB 바이트 비교 테스트(진입점 재실행, row-less stop)가 이 호스트에서 모두 통과했다.
+
+### 8) stall_watch
+
+- `StallWatch.__init__` 이 `self.herdr_name` 을 한 번 구한다 (:229).
+- 그 값을 `HerdrSource(..., name=self.herdr_name)` (:230) 와 `wait_once` (:332) 에 같이 쓴다.
+- `HerdrSource` 는 keyword-only `name` 이 필수다. 원래 이름으로 대신 쓰는 경로는 없다.
+- 다른 호출자는 `test_issue60_linux_fixes.py:99` 하나이고, `name="t"` 를 넘기도록 바뀌었다.
+- `tests/test_issue66_stall_watch_sanitized_name.py` 는 diff 가 없고, 7 passed 다.
+
+### 9) 바뀐 기존 테스트
+
+- `test_tier2_component`: `HERDR_SESSION_NAME=` 포함 여부 대신 새 attach 형태 전체가 같은지와 두 키가 없는지를 본다.
+  - 서버 전파와 라벨이 새지 않는지를 보는 원래 의도는 유지되고, 단언은 더 엄격해졌다.
+- `test_issue50_pane_lock:173`: create 가 쓴 행이라는 증거를 `start_command` 대신 `session_id_source` 로 본다.
+  - reconcile 의 행 (`reconcile.sh:666-680`) 에는 이 키가 없다. 그래서 증거로서 같은 구분을 한다.
+- `test_issue21_worktree_prereqs:584`: 제어 루트 경로가 새지 않는지를 attach_command 에서 본다. 의도가 같다.
+- `test_tier1_unit` / `test_tier3_integration`:
+  - "agent 를 추론할 수 없으면 exit 2" 를 이제 **행이 있는** 세션으로 확인한다. 행이 없으면 row-less 경로로 가기 때문이다.
+  - 의도가 유지된다.
+- `test_issue63`, `test_issue23_24` S9: 안내 문구를 새 명령으로 바꿨다.
+- `test_layout`, `test_issue42`: heredoc 시작 위치와 종료 코드 집합을 따라 고쳤다.
+- `tests/data/skill_code_blocks.json`:
+  - 블록 33개 가운데 sha 가 바뀐 것은 문서 내용이 바뀐 두 블록이다: create :134 (YAML 행 예시), status :74 (JSON 예시).
+  - 나머지는 줄 이동과 evidence 줄 번호다.
+  - `entry_points` 의 stop 종료 코드에 5·6 을 더했다.
+  - 문서 diff 와 맞다.
+- **S11** (`test_issue23_24_startup_path.py:294-316`):
+  - 비교 기준을 `0fc162e` 로 두었다. `0fc162e..HEAD` 사이 lib.sh 변경은 5f60653 의 `load_state_json` 하나뿐이고, shim heredoc 과 sanitize 함수는 바뀌지 않았다.
+  - merge commit 으로 병합하면 0fc162e 가 main 이력에 남으므로 계속 맞다.
+  - 기준을 찾지 못하면 `pytest.skip` 한다. 이는 base(525df2b) 때부터의 동작이다. git 이 없는 설치본이나 squash 병합에서 건너뛰는 것은 기존 설계 그대로라고 본다.
+  - 검증 경로(git worktree)에서는 **skip 이 아니라 통과**했다 (`-k s11`: 1 passed).
+  - squash 하면 이 확인이 사라지므로 PR 본문의 "merge commit 필수" 를 지켜야 한다.
+
+### 10) macOS 호환
+
+- 바뀐 Python 6개 파일이 `/usr/bin/python3` 3.9.6 에서 compile 된다.
+- `attach_command` 와 `migrate` 가 3.9 에서 실행된다.
+- 바뀐 셸 줄에 `declare -A`, `mapfile`, `${x,,}`, `sed -i`, `stat -c`, `readlink -f`, `local -n` 이 없다.
+- 이름 변환은 BSD tr/sed 와 bash 3.2 에서 위 6) 처럼 확인했다.
+
+## 2. 실행한 테스트
+
+- 실행 조건:
+  - 모두 `env -i PATH=/opt/homebrew/bin:/usr/bin:/bin:/usr/sbin:/sbin`, 임시 HOME/XDG_DATA_HOME 에서 돌렸다.
+  - `PYTHONDONTWRITEBYTECODE=1 -p no:cacheprovider --basetemp=<스크래치>` 를 썼다.
+  - `.mam.env` 는 export 하지 않았다.
+- 실제 herdr 서버 두 개는 테스트 전후로 같다: pid 11655 `herdr server`, 69309 `herdr --session multi-agent-mux server`, 시작 시각도 같다.
+
+| 대상 | 결과 |
+|---|---|
+| 검증 경로: test_issue71_herdr_names + test_issue66_stall_watch_sanitized_name | **77 passed** (`/1`, `/2` 모두) |
+| base 29cc4fd 사본 + head 의 issue71 테스트 | **68 failed, 2 passed** |
+| 검증 경로 A: tier1_unit, tier2_component, tier3_integration, issue23_24_startup_path, issue50_pane_lock, issue21_worktree_prereqs, issue63_same_cwd_ids, issue60_linux_fixes, layout, issue42_skill_blocks | **384 passed, 1 skipped** (`/1`, `/2` 모두; skip: issue42 의 `.claude/skills is untracked; absent in a worktree`, 환경 요인) |
+| 검증 경로 B (stop·reconcile·create·resume 인접): b4_session_created, b19_headless_reconcile_fixes, c1_tui_readiness, issue15_registry_isolation, issue17_workspace_root_isolation, issue31_purge_residual, issue24_resume_dialogs, issue40_auto_pin, issue45_restore, issue6_fail_closed, issue9_server_env, issue64_ro_connect, uuid_target, workspace_scope, issue57_logs_follow_registry, issue30_stall_watch, issue30_stall_watch_stop, issue50_dispatch_herdr, issue60_opencode_v2, issue36_prompt_transport, a4_adapter_contract, issue26_ints | **543 passed, 3 skipped** (`/1`, `/2` 모두) |
+| S11 단독 (검증 경로) | 1 passed (skip 아님) |
+| 리뷰어 추가 시험 (head 사본, p1–p12) | 14 passed. 1개는 내 기대값 오류다 (형식 0 → "0 -> 2" 출력, 동작은 정상) |
+| bash↔Python 이름 변환 비교 | 408 건 불일치 0, 도구 없음 5 건 모두 기대대로 (`/2` 의 lib.sh·lib_py 로 다시 실행) |
+
+변이 (head 사본, issue71 70개):
+
+| # | 변이 | 결과 |
+|---|---|---|
+| m1 | 작업 공간 판정을 `startswith(root)` 로 (접두어 혼동) | **살아남음** (리뷰어 p1 은 잡음) |
+| m2 | 마이그레이션 뒤 YAML 강제 쓰기 끔 | 6 failed |
+| m3 | YAML 복구 분기 끔 | 2 failed |
+| m4 | 래퍼 attach 에 원래 이름 | 2 failed |
+| m5 | 줄바꿈 → `-` 제거 | 6 failed |
+| m6 | rc≠0 이면 모두 row-less | 1 failed |
+| m7 | strict 에서 state 테이블 오류만 무시 | **살아남음** (아래 N3) |
+| m8 | running 행만 마이그레이션 | 6 failed |
+| m9 | 서버 없으면 `--session ''` | 3 failed |
+| m10 | reconcile 을 옛 attach 형태로 | 3 failed |
+| m11 | 행 없는 stop 이 환경 서버를 무시 | 1 failed |
+| m12 | 해시 실패 시 `00000000` | 4 failed |
+
+## 3. 차단 결함
+
+없음.
+
+## 4. 비차단
+
+### N1: 행 없는 stop 이 제어 루트 밖 워크트리의 세션은 닫지 못한다
+
+- 상황:
+  - `worktree_prepare.sh:229-236` 은 creator 를 `WORKSPACE_ROOT=$MAIN` 과 `--workspace $WT` 로 만든다.
+  - `$WT` 는 `--path` 로 받은 임의의 경로이고, 보통 제어 루트 밖이다. 루프의 `mam-wt-*` 나 `$TMPDIR/mam-review/…` 가 그 예다.
+- 결과:
+  - 그런 create 가 행을 등록하기 전에 죽으면, id_order 의 안내 (`id_order.py:343-345`) 는 stop 명령을 준다.
+  - 그 stop 은 `realpath(cwd)` 가 `WORKSPACE_ROOT` 밖이므로 exit 5 로 거부한다 (`stop_session.sh:151-154`). 다른 작업 공간 테스트 (test :467) 와 같은 경로다.
+  - 거부는 안전하다(아무것도 바꾸지 않음). 하지만 이 경우에는 안내된 스킬 명령으로 정리할 수 없다.
+- 권고: 둘 중 하나.
+  - (a) row-less 판정에 "이 제어 루트에 묶인 워크트리(`git worktree list`)" 도 넣는다.
+  - (b) exit 5 메시지에 그 경우의 정리 방법을 적는다.
+
+### N2: 접두어 혼동을 고정하는 테스트가 없다
+
+- m1 이 PR 테스트에서 살아남는다. `<ws>-other` 를 cwd 로 하는 한 줄짜리 시험을 더하기를 권한다. 내 p1 이 그 형태다.
+
+### N3: strict 읽기에서 state 테이블만 없는 DB 는 걸리지 않는다
+
+- m7 이 살아남은 이유는 테스트의 `no-tables` 가 sessions 테이블 오류로도 잡히기 때문이다.
+- state 만 없는 DB 에서도 stop 은 sessions 테이블로 행을 정확히 찾으므로 영향은 없다.
+
+### N4: 이 PR 이 건드리지 않은 attach 안내가 남아 있다 (모두 base 부터 있던 것)
+
+- `create_session.sh:770`: `Attach:  herdr session attach $SESSION_NAME`. 서버를 적지 않고, 이름도 변환하지 않는다. 행의 `attach_command` 를 출력하기를 권한다.
+- `multi-agent-mux-delegate-job:1021`: `HERDR_SESSION_NAME=… herdr agent attach $sess (lib.sh를 source한 셸에서)`. 래퍼가 이제 이름을 변환하므로 동작은 하지만, 새 형태와 다르다.
+- `deploy/install_mam.sh:330`: `HERDR_SERVER_NAME=… herdr agent attach`. 없는 환경 변수 이름이다.
+
+### N5: 래퍼 attach 는 대상이 첫 인자라고 가정한다
+
+- `herdr agent attach --takeover <name>` 순서로 쓰면 래퍼는 `--takeover` 를 대상으로 찾다가 exit 1 을 낸다.
+- herdr 의 사용법(`<TARGET> [OPTIONS]`)과 문서의 순서대로라면 문제가 없다.
+
+### N6: YAML 이 아직 없는 작업 공간에서는 행 없는 stop 이 동작하지 않는다
+
+- 처음 만든 작업 공간에서 첫 create 가 행 등록 전에 죽어 YAML 이 아직 없으면, stop 은 행 없는 경로 전에 `YAML not found` 로 exit 1 한다 (:101).
+- 드문 경우다.
+
+### N7: 정리할 만한 작은 것들
+
+- `create_session.sh:519` 의 `server_opt` 는 쓰는 곳이 없다. base 에서도 그랬다.
+- shim 내용이 바뀌었으므로, 같은 제어 루트를 쓰는 옛 버전 체크아웃과 새 버전 체크아웃이 섞이면 `.mam/shim/herdr` 를 서로 덮어쓴다. #45 때와 같은 전환기 비용이다.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-codex-01/plan-bbccb330.md

@@ -0,0 +1,84 @@
+# Issue #40 구현 계획 정교화 — agy 동일 cwd 오등록 방지
+
+## 반영한 이의제기와 결론
+
+Creator의 이의는 타당합니다. `last_conversations.json`은 cwd를 키로 UUID 하나만 저장하므로 그 값을 후보로 삼는 것만으로는 agy 후보가 최대 하나가 됩니다. 따라서 일반적인 `candidate_count > 1` 검사는 이 경우 작동하지 않습니다. 이 캐시는 대화를 연 시점에 갱신되며 현재 대화의 소유자를 증명하지도 않습니다. 특히 `agy.verify_artifact()`의 형제 UUID 검사가 `cache_match`가 아닐 때만 실행된다면, cache hit만 사용하는 자동 pin 경로에서 형제 배제는 무력화됩니다. 같은 cwd의 동시 세션은 실제 지원 시나리오이므로 epoch와 viewport 확인도 대화 소유권을 대신할 수 없습니다.
+
+이에 따라 agy는 **캐시 일치만으로 자동 pin하지 않습니다.** 캐시는 검사할 UUID를 제안하는 데만 쓰고, 해당 UUID의 열린 presence lock을 보유한 프로세스가 현재 행의 pane 프로세스이거나 그 자손인지 확인해야 합니다. 확인할 수 없거나 소유자가 불일치하면 fail closed로 미확정 처리합니다. 같은 cwd에 다른 non-stopped agy 세션이 있으면 이 소유권 증명이 필수이며, 증명 없이 pin하지 않습니다. 형제 UUID 배제는 cache hit 여부와 무관하게 항상 적용합니다.
+
+## 현재 기준선과 범위
+
+대상 워크트리 `/Users/godopu16/PuKi/laa/canary_projects/mam-wt-issue40`, 브랜치 `fix/issue-40-auto-pin`은 base/head 모두 `ff8b381520ae04e80c73a9e18bfad73d47e853c9`이며 변경 사항이 없습니다. 본 작업은 계획서 갱신이며 코드·브랜치를 수정하지 않습니다. 구현은 이 워크트리에서 진행합니다.
+
+목표는 Class A 어댑터의 첫 로컬 `completed` 작업을 통해 미등록 세션 ID를 안전하게 확정하는 것입니다. 어댑터는 수명주기와 읽기 전용 capture 사실을 제공하고, completed를 검증한 로컬 수신 측만 YAML/SQLite를 갱신합니다. `publish_event.py`는 계속 이벤트 발행만 맡습니다. wrapper subscriber 종결 처리와 `loop.runner.wait_for_job()` 복구 경로는 같은 handler를 호출하고 `(job_id, dispatch_token, attempt_id)`로 중복을 제거합니다. remote/human job 및 pre-assigned ID는 제외합니다.
+
+## 정교화한 설계
+
+1. **Capture 결과와 lifecycle 계약**
+
+   `BaseAgentAdapter`에 `id_lifecycle` 및 `capture_active_session_id(ctx)` 계약을 추가합니다. 결과는 ID와 구체적 상태/사유를 포함해 `captured`, `no-candidate`, `ambiguous(shared-cwd)`, `unverifiable-owner`, `owner-mismatch`, `sibling-claimed`, `stale`, `wrong-workspace` 등을 구분합니다. Claude/Grok은 `pre_assigned`로 선언하고 자동 capture하지 않습니다. agy·opencode·codex·hermes는 `post_discovered` 대상입니다. 추가/기존 어댑터가 결과를 명확히 전달하도록 하며, `None` 하나로 모든 실패 원인을 뭉개지 않습니다.
+
+2. **공용 handler와 저장 경계**
+
+   `lib_py/agents/autopin.py`와 같은 공용 경로에 판정·pin handler를 둡니다. 검증된 local `completed` job, 세션 row, transport, agent, dispatch token 및 attempt를 확인하고, 기존 ID/lifecycle을 존중한 뒤 adapter capture, workspace/epoch 검증, sibling 배제, viewport 확인을 수행합니다. 판정 코드는 저장소를 직접 우회하지 않고 기존 `atomic_dump_yaml` 경로에서 row와 관련 SQLite 상태를 갱신합니다. 성공 때 own ID, `session_id_source='discovered'`, `session_id_verified=True`, 표시 상태를 일관되게 기록하고, 실패 시 기존 own ID를 변경하지 않은 채 구체적 사유를 보존합니다. capture 실패는 이미 성공한 작업의 terminal 상태를 실패로 뒤집지 않습니다.
+
+3. **agy는 캐시 후보와 실행 중 소유권을 모두 증명**
+
+   - `last_conversations.json[normalized_cwd]`는 후보 UUID 검색의 시작점일 뿐, 단독 pin 근거로 사용하지 않습니다. 해당 map이 다른 cwd를 가리키는 UUID는 즉시 거절합니다.
+   - 후보 UUID의 `presence/<uuid>.lock` (필요하면 기존 artifact 경로 계약에 따른 DB/sidecar)을 열고 있는 PID를 `lsof`로 조회합니다. 소유 PID는 해당 행의 `pane.pid` 또는 그 자손 프로세스여야 합니다. PID/조상 관계를 확인하는 동안 프로세스 종료·PID 재사용 가능성을 고려해 실제 프로세스 존재와 계보 확인에 실패하면 성공으로 추정하지 않습니다.
+   - lsof 부재/오류, lock 미점유, pane PID 누락, 계보 불일치 등의 경우 pin하지 않고 각각 재현 가능한 fail-closed 사유를 기록합니다. 실제 CLI 실행 상태를 확인할 수 없는 환경에서 cache-only fallback은 두지 않습니다.
+   - 동일 normalized cwd를 가진 다른 non-stopped agy row가 있으면 owner 검사가 통과해야만 그 소유 행에 pin할 수 있습니다. 서로 다른 행이 같은 캐시 UUID를 갖는 동시 처리에서도 pane 소유권을 통과한 행만 후보가 됩니다. owner가 불확실하면 둘 다 미확정으로 남을 수 있으며 이는 안전한 결과입니다.
+   - `verify_artifact()`의 sibling claim 검사는 cache match와 무관하게 먼저 적용합니다. 다른 활성/등록 행이 이미 보유한 UUID를 거절합니다. own row의 재검증은 자기 claim을 sibling으로 오인하지 않도록 제외합니다.
+   - reconcile drift C와 completed capture는 같은 agy 판정기를 호출합니다. 대화 폴더 `*.db` 전체를 훑어 얻은 단독 후보를 자동 pin하지 않습니다. 다른 workspace의 DB를 읽지 않도록 막고, DB 조회는 `base._ro_connect`를 사용합니다.
+
+4. **나머지 Class A 어댑터**
+
+   OpenCode는 세션 DB의 directory/time, Codex는 state DB의 cwd와 rollout metadata, Hermes는 sessions의 cwd/started_at을 사용합니다. 각 후보는 workspace와 세션 epoch(`herdr_session_epoch`) 조건을 모두 만족해야 하며 검증된 후보가 정확히 하나일 때만 확정합니다. 다수 후보는 `ambiguous`로 남깁니다. agy의 presence owner 규칙은 다른 어댑터에 억지로 일반화하지 않습니다.
+
+5. **동시 completed 처리와 재수신**
+
+   job/token/attempt 키 아래 직렬화하고 처리 결과를 남깁니다. wrapper와 loop 복구 경로가 연속 또는 동시 호출되어도 하나의 capture만 수행합니다. handler가 상태 저장 전에 중단된 경우 재시도는 기존 own ID와 artifact를 재검증해 멱등이어야 합니다. agy의 owner 판별은 각 처리 시점에 수행하며, 캐시가 바뀌어도 UUID 소유 pane을 잘못 선택하지 않습니다.
+
+6. **호출 지점**
+
+   subscriber가 검증한 completed, subscriber timeout 뒤 disk fallback에서 확정한 completed, loop `wait_for_job()`의 completed 반환 직전 모두 동일 handler로 이어집니다. 기존 wrapper가 순수 상태 매핑을 맡고 있다면 얇은 Python 호출 경계를 추가합니다. subscriber와 `publish_event.py`에 registry/YAML/SQLite 쓰기를 추가하지 않습니다.
+
+## 단계별 실행 및 검증 기준
+
+### 1단계 — 실패 재현과 회귀 테스트
+
+- Creator의 같은 cwd 재현을 테스트 fixture로 옮깁니다. A와 B가 동일 cwd이고 cache는 UUID U 하나를 가리키며, U의 presence lock 소유자는 A의 pane PID인 상태에서 B는 discover/capture/verify 모두 U를 얻지 못해야 합니다.
+- 동일 cwd 동시 onboard 완료 두 건을 모의합니다. cache UUID는 하나여도 결과는 소유 pane 행만 pin할 수 있고, PID 확인이 불가능하거나 불일치하면 어느 행도 pin하지 않습니다.
+- `test_agy_capture_requires_presence_owned_by_pane_pid`: lsof 결과를 모의해 일치 PID/자손, 다른 PID, lock 미점유, lsof 오류를 검증합니다.
+- `test_agy_capture_rejects_cache_uuid_owned_by_sibling_in_same_cwd` 및 `test_agy_concurrent_onboard_same_cwd_no_cross_pin`을 추가합니다. sibling 배제 검사는 cache-hit에서도 실행되어야 합니다.
+- Issue #64의 `verify_session_uuid(...uuid_b...) is True` 기대를 `False`로 바꾸고, 외부 DB에 sidecar가 생기지 않는 확인은 유지합니다.
+
+### 2단계 — adapter 및 agy 판정
+
+- lifecycle 선언, capture 결과 타입, epoch/workspace 단일 후보 규칙을 테스트합니다.
+- A/B 캐시 전환, 타 workspace mapping, 같은 cwd sibling claim, cache match여도 sibling UUID 거부, presence 소유자가 pane 또는 자손인지 확인합니다.
+- lsof를 쓸 수 없는 상황에서는 `unverifiable-owner` 등 사유와 함께 미확정임을 확인합니다. 어떤 예외 경로도 cache-only 자동 pin으로 되돌아가면 안 됩니다.
+
+### 3단계 — 공용 completed handler
+
+- daemon 없는 onboard 완료, OpenCode/Codex/Hermes의 첫 completed pin, 기존 ID/pre-assigned skip, remote/human/stale token/non-completed 제외를 확인합니다.
+- wrapper completed와 loop 복구 완료를 같은 키로 호출해 capture 및 저장이 한 번뿐인지 검증합니다.
+- 모호성·검증 실패의 사유가 보존되고 자체 ID는 그대로인지 확인합니다.
+
+### 4단계 — reconcile 통합 및 회귀
+
+- drift C가 공용 판정기를 사용하고 agy의 전체 DB glob 후보를 자동 pin에 쓰지 않는지 테스트합니다.
+- same-cwd A/B에서 B의 최신 cache 값과 A의 더 최근 epoch가 있어도 lock 소유 pane이 A라면 A만 pin될 수 있고, B는 pin되지 않는지 검증합니다.
+- subscriber, retained/disk fallback, daemon 없는 실행, loop 복구 경로에서 동일 dedupe key를 확인합니다. publisher가 제어-plane 상태를 쓰지 않는 것도 확인합니다.
+
+### 5단계 — 검증과 범위 마무리
+
+- 지정 Python 환경에서 신규 Issue #40 테스트, 갱신된 Issue #64, UUID/tier2/dispatch 및 관련 adapter/reconcile 테스트를 실행합니다. 전체 테스트는 상위 오케스트레이션에 맡깁니다.
+- 테스트는 임시 HOME/DB와 source 바깥 basetemp를 쓰고 실제 agent home, `.mam.env`, monitor/herdr 서비스에 접근하지 않습니다. 변경한 shell은 `bash -n`, diff는 `git diff --check`로 확인합니다.
+- 작업 전후 branch/status를 확인하고 요청 범위 파일만 stage합니다. 버전 파일 및 `.venv`는 추가하지 않습니다.
+
+## 위험과 명시적 한계
+
+가장 큰 위험은 잘못 pin된 ID가 잘못된 resume 또는 purge로 이어지는 것입니다. 따라서 agy에서 lock 소유 프로세스와 pane의 관계를 확인할 수 없으면 자동 pin을 포기합니다. 이는 일부 환경에서 정상 대화도 자동 등록되지 않는 false negative를 허용하는 fail-closed 선택입니다. 추후 에이전트가 presence lock을 열지 않는 지원 모드가 확인되면 별도의 식별 가능한 프로세스 귀속 신호를 설계해야 하며, 기존 cwd 캐시를 대체 증거로 승격하지 않습니다.
+
+같은 cwd의 활성 agy 세션 수가 많을수록 cache-only 판정은 신뢰할 수 없습니다. viewport 검사, epoch, 최신 mtime은 owner 증명이 아닙니다. stop의 기존 capture와 source/verified 메타데이터 정합성은 별도 후속 범위로 남기되, completed pin이 이를 덮어써 기존 ID를 변경하지 않도록 회귀 테스트합니다.

.agents/reports/planner-reviewer-codex-01/report-028e98cb.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261027T201245Z-63c71b",
+  "base_sha": "1d63e882bc1c46e9af8484647d5091b296d8fa3f",
+  "head_sha": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "tree_sha": "fbadb24de60ccdae684b23e2e0a41cdf23ab81eb",
+  "review_commit": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "reviewer": "planner-reviewer-codex-01",
+  "job_id": "028e98cb",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-27T21:06:27Z"
+}

.agents/reports/planner-reviewer-codex-01/report-028e98cb.md

@@ -0,0 +1,98 @@
+# PR #75 후속 리뷰 — job 028e98cb
+
+## 판정과 검증 대상
+
+이번 범위의 차단 사항을 발견하지 않았다. R2의 PGID 분리와 테스트 teardown 수정이 요구 사항을 충족한다.
+
+- base: 1d63e882bc1c46e9af8484647d5091b296d8fa3f
+- head: ec7f5c4e57286fb3c4238b8220f39094f4640391
+- tree: fbadb24de60ccdae684b23e2e0a41cdf23ab81eb
+- 검증 경로: /var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1
+- HEAD/tree 일치, clean status, `git diff --check 1d63e88..HEAD` 통과. 실제 diff는 lib.sh와 test_issue72_update.py 두 파일이다.
+- 새 브리프의 좁혀진 범위인 1d63e88..HEAD를 검토했다. 이전 비차단 권고에 해당하는 파일/기능을 추가 변경하지 않았음을 확인했다.
+- `tea issues 72 --comments`, `tea pulls 75`를 다시 읽었다. 기준 이슈 내용은 앞선 검토와 같고, 이번 수정은 결정 2 및 기존 중복 방지/opt-out/PID/로그 계약과 정합적이다.
+
+## 확인한 것
+
+| 항목 | 파일:줄 근거 | 확인 결과 |
+|---|---|---|
+| R2: 호출자 PGID에서 분리 | `.agents/skills/lib.sh:2303–2309` | 기존 monitor 옵션을 기록하고 spawn 때만 `set -m` 사용. 비동기 monitor가 별도 PGID에서 뜨며, 기존 옵션은 복원된다. macOS에 없는 setsid(1) 없이 동작. |
+| 기존 기동 계약 | `lib.sh:2289–2315` | 정확한 PID 검색과 중복 방지, opt-out 분기는 유지. cwd를 작업 공간으로 두고 원래 cwd로 복원, stdin /dev/null, 로그 append, --idle-timeout 0, nohup의 SIGHUP 처리와 PID stdout 계약 유지. |
+| 0/1 × 세 복원 경로 회귀 | `tests/test_issue72_update.py:699–725`, 특히 `:724` | 정상 설치·정지 timeout·rollback의 두 모드 모두 실제 새 monitor와 PGID 분리를 검증한다. decoy 미신호 및 기동 횟수 검증도 유지. 여섯 조합 모두 통과. |
+| pkill 제거·소유 프로세스 정리 | `test_issue72_update.py:184–193,220–240` | 기록된 helper 그룹을 정리하고 wait한다. monitor는 이 테스트의 정확한 절대 스크립트 명령행으로 고른 뒤, 미리 수집한 자손 PID와 함께 정리한다. 전역 패턴 kill은 없다. |
+| 잔여 프로세스 검출 유지 | `test_issue72_update.py:237–240` | ws를 명령행에 남긴 프로세스가 있으면 최대 10초 기다린 뒤 실패한다. 이 문자열 검색은 보고/검증용이며 kill 대상으로 사용되지 않는다. 원본 테스트를 외부 정리 플러그인 없이 실행해 통과. |
+
+## R2의 전후 재현 결과
+
+base 1d63e88의 부정 대조는 직전 d14ae099 리뷰에서 실제로 실행한 동일 외부 탐침 로그를 사용했다. 당시 mode=0의 정상·timeout·rollback 세 경우는 PGID가 호출자와 같아 실패했고, mode=1의 세 대조군은 통과했다. 이번에도 같은 탐침 코드를 변경 없이 지정된 새 snapshot에서 실행했다.
+
+| 경로 | mode=0의 새 monitor PGID / caller PGID | mode=1의 새 monitor PGID / caller PGID |
+|---|---|---|
+| 정상 설치 | 93359 / 88049 — 분리 | 96481 / 88049 — 분리 |
+| 정지 timeout 복원 | 91992 / 88631 — 분리 | 94916 / 88631 — 분리 |
+| rollback 복원 | 93376 / 88631 — 분리 | 96166 / 88631 — 분리 |
+
+- 기존 `probe_monitor_group.py`: **2 passed / 11.95s** (base에서는 1 failed, 1 passed).
+- 기존 `probe_monitor_restore_group.py`: **4 passed / 10.40s** (base에서는 2 failed, 2 passed).
+- 별도 직접 호출 탐침으로 monitor 옵션 초기 off→off 및 on→on, cwd 복원을 확인: **2 passed / 3.24s**. 새 monitor의 PGID 분리도 확인했다.
+- PGID 검증은 조회로 했으며 호출자의 프로세스 그룹에 신호를 보내지 않았다.
+
+base 로그와 동일 탐침 코드, 이번 새 결과를 evidence/에 보존했다. base를 이번 허용 경로 밖에서 다시 실행한 것은 아니다.
+
+## Mac에서 실행한 테스트
+
+/bin/bash 3.2.57, Python 3.9.6에서 실행했다. 스냅샷에 .venv가 없어 브리프 앞부분에 명시된 제어 루트 .venv/bin/python을 사용했다.
+
+작업 디렉터리는 위 snapshot이며, 주요 실행 명령은 다음과 같다.
+
+```bash
+env -u HERDR_SOCKET_PATH -u HERDR_PANE_ID -u HERDR_TAB_ID \
+  -u HERDR_WORKSPACE_ID -u HERDR_SESSION_NAME -u HERDR_SESSION \
+  -u WORKSPACE_ROOT -u MAM_ENV_FILE -u MAM_JOBS_DIR \
+  -u DELEGATE_JOB_LOGS_DIR -u AGENT_SESSIONS_YAML \
+  PYTHONDONTWRITEBYTECODE=1 \
+  /Users/godopu16/PuKi/laa/canary_projects/multi-agent-mux/.venv/bin/python \
+  -m pytest -p no:cacheprovider \
+  --basetemp=/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review-028e98cb-pytest -ra \
+  tests/test_issue72_update.py \
+  tests/test_issue5_phase1_delegation.py::test_c07_watchdog_spawns_daemon_with_workdir_and_log \
+  tests/test_issue5_phase1_delegation.py::test_c08_watchdog_second_call_reuses_running_daemon \
+  tests/test_issue5_phase1_delegation.py::test_c09_start_watchdog_and_ensure_subscriber_daemon_agree \
+  tests/test_issue5_phase1_delegation.py::test_daemon_missing_monitor_raises_with_the_legacy_path \
+  tests/test_issue5_phase1_delegation.py::test_daemon_spawn_dedup_and_survives_parent_exit \
+  tests/test_issue19_subscriber_daemon_lifecycle.py::test_opt_out_still_reports_a_daemon_that_already_runs
+```
+
+**59 passed / 133.12s / exit 0**. update 파일 50건, phase1 watchdog 8건, 기존 daemon의 opt-out 보고 1건이다.
+
+같은 환경 제거·Python·no-cache 설정으로 실행한 추가 검증:
+
+| 선택 | 결과 |
+|---|---|
+| `test_issue19_subscriber_daemon_lifecycle.py::test_sandbox_default_never_spawns_a_daemon` (0/1) | 2 passed / 0.53s |
+| `-p probe_monitor_group ... tests/test_issue72_update.py` | 2 passed / 11.95s |
+| `-p probe_monitor_restore_group ... tests/test_issue72_update.py` | 4 passed / 10.40s |
+| `-p probe_monitor_options ... tests/test_issue72_update.py` | 2 passed / 3.24s |
+
+외부 탐침은 기존 Module의 Box fixture를 사용하고 항목만 외부 plugin으로 선택했다. source는 변경하지 않았다. 각 basetemp는 TMPDIR 아래 서로 다른 mam-review-028e98cb-{pytest,group,restore-group,options,optout}이었다. 이번에는 safe_cleanup 등의 외부 teardown 대체 없이 수정된 원본 cleanup을 실행했다.
+
+- `/bin/bash -n .agents/skills/lib.sh`: 통과.
+- `ast.parse(test_issue72_update.py, feature_version=(3,9))`: 통과.
+- diff --check: 통과.
+- ShellCheck는 PATH에 없어 실행하지 못했다. bash -n을 ShellCheck 통과로 표기하지 않는다.
+- 이번 새 브리프가 정한 수정 파일·watchdog 범위로 실행했고 전체 스위트는 실행하지 않았다.
+
+## 발견 사항 및 사용자 확인
+
+차단/비차단 신규 지적 없음. R2와 pkill 제거 요구 모두 해결됐다. 새 정책 결정이나 재계획이 필요하지 않다.
+
+## 자원 안전
+
+- 검증은 지정된 snapshot에서만 했고 creator 작업 트리에서 실행·수정하지 않았다. installer/update는 TMPDIR 가짜 설치 및 로컬 source/file:// installer만 사용했다.
+- 실제 herdr 서버·설정·에이전트 홈 DB를 조작하지 않았고, 실제 .mam.env 값을 테스트에 출력하거나 export하지 않았다. 이슈/PR 댓글·상태 변경, push/merge 없음.
+- 다섯 basetemp의 종료 후 프로세스 점검 결과 `remaining_test_processes=[]`.
+- 원래 제어 루트 monitor PID 3714는 실행 전후 같은 명령으로 살아 있었으며 신호를 보내지 않았다.
+- 종료 시 HEAD/tree와 clean status가 그대로이며 diff --check도 다시 통과했다.
+- 승인된 잡 이벤트·리포트 외에 실제 control-plane 상태를 수정하지 않았다. 원본 로그와 외부 탐침 코드는 이 리포트 옆 evidence/에 보존했다.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-codex-01/report-12669b52.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261023T035928Z-2ccc02",
+  "base_sha": "dc886ecd6b38c01032a55a2d1c230c73362ae630",
+  "head_sha": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "tree_sha": "f1af6fdd548ee5d6f6b81e2202833edfaca98188",
+  "review_commit": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "reviewer": "planner-reviewer-codex-01",
+  "job_id": "12669b52",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-23T05:16:58Z"
+}

.agents/reports/planner-reviewer-codex-01/report-12669b52.md

@@ -0,0 +1,21 @@
+# Reviewer report — PR #69 / Issue #63
+
+Reviewed the required snapshot at `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261023T035928Z-2ccc02/1`, head `1614af5b673d7519d3a38f63e3636055592b4f14`, against base `dc886ecd6b38c01032a55a2d1c230c73362ae630`. The snapshot matches the expected tree `f1af6fdd548ee5d6f6b81e2202833edfaca98188` and is clean. I read Issue #63 and PR #69. The latest delta is limited to `id_order.py` and its regression tests.
+
+## Previously blocking finding is closed
+
+At the previous head (`7cac6f6`), `_read_and_prune_markers` dropped a dead-owner marker when its session name matched the caller, without checking herdr. The new code removes that exception: `.agents/skills/lib_py/agents/id_order.py:219-230` now keeps a dead-owner marker until its row is registered for that attempt or herdr returns an authoritative `False`; live and unknown answers both retain the orphan. `blockers()` includes a marker without a row even when its name is the caller's (`id_order.py:145-148`), so a retry is refused rather than replacing its marker.
+
+The tests now cover same-name retries with a live owner, a dead owner and live herdr session, unknown herdr state, and a confirmed-gone session (`tests/test_issue63_same_cwd_ids.py:1117-1148`). The real-probe integration test also retries using the orphan's own name and checks that the marker is retained (`tests/test_issue63_same_cwd_ids.py:1287-1290`) and then safely replaced once the session is confirmed gone (`1312-1315`). The test fixture uses a mocked herdr and in-process probes; it does not contact a real herdr server.
+
+## Verification
+
+- `PYTHONDONTWRITEBYTECODE=1 .../python -m pytest -p no:cacheprovider --basetemp=/tmp/mam-review-12669b52 tests/test_issue63_same_cwd_ids.py` — **27 passed** on macOS, Python 3.9.6 (230.59 s). This includes the orphan liveness, unknown-result, zero-wait-cap, and same-name retry cases.
+- Changed shell scripts checked with `/bin/bash -n` — passed.
+- `git diff --check dc886ecd6b38c01032a55a2d1c230c73362ae630..HEAD` — passed.
+- The earlier review covered the broader unchanged stop/purge/resume implementation and adjacent compatibility checks. This re-review did not repeat the base checkout or all adjacent test groups because the new delta is confined to dead-owner marker pruning and its regression tests.
+- No real agent-home databases or real herdr sessions were accessed.
+
+The latest change fixes the remaining blocking same-name orphan path. The earlier probe-failure and wait-cap fixes remain covered by the passing Issue #63 tests. I found no blocking issue in this revision.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-codex-01/report-65396b40.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261025T023502Z-d6f876",
+  "base_sha": "0461a632eb667c7988fd33be92e9a4b36151f22a",
+  "head_sha": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "tree_sha": "15a72c9a1933c64018a2f2d9aa9707348905bb4d",
+  "review_commit": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "reviewer": "planner-reviewer-codex-01",
+  "job_id": "65396b40",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-25T03:40:44Z"
+}

.agents/reports/planner-reviewer-codex-01/report-65396b40.md

@@ -0,0 +1,23 @@
+# Reviewer report — PR #70 / Issue #66
+
+Reviewed the required snapshot at `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1`, head `bb496fde785133ad1dbec288aa7431766efb6eb5`, against base `0461a632eb667c7988fd33be92e9a4b36151f22a`. The snapshot matches expected tree `15a72c9a1933c64018a2f2d9aa9707348905bb4d` and is clean. I read Issue #66 and PR #70; the implementation matches the requested scope.
+
+## Findings
+
+No blocking findings.
+
+`HerdrSource` derives `self.name` from `sanitize_herdr_agent_name(target)` while resolving the adapter from the original name (`.agents/skills/lib_py/stall_watch.py:140-164`). Its agent `get`, `read`, and `prompt` calls use the sanitized name (`182-212`); the pane operations use pane IDs, so they do not need the session name. `StallWatch` separately derives the sanitized value for `watcher.wait_once` at line 229 and calls it at line 331, while notices/logs continue to use `args.target` (for example lines 391-398). `args.herdr_session` remains the herdr server selector passed as `session=`, separate from the sanitized agent name.
+
+The transformation in `lib_py/agents/sanitize.py` follows the same lowercase, allowed-character replacement, leading-letter prefix, 32-character cap and SHA-1 suffix rules as the active `_sanitize_herdr_agent_name` in `lib.sh:293-318`. Agent kind detection uses the original target, which is necessary for long names whose sanitized suffix is a hash. The codex long-name test verifies this using a name whose original `-codex` suffix is absent from the sanitized form (`tests/test_issue66_stall_watch_sanitized_name.py:113-128`).
+
+The mock's `strict_agent_names` check is opt-in (`tests/conftest.py:470-477`), so its default path retains the prior matching behavior. In strict mode, the tests verify that unconverted names receive `agent_not_found` for get/read/wait/prompt and sanitized names resolve (`test_issue66_stall_watch_sanitized_name.py:52-67`). Tests also verify transformed get/read/prompt/wait calls, idle and blocked notifications, preservation of the original name in log output, and unchanged plain-name behavior (`69-110`).
+
+## Verification
+
+- On the head snapshot, `PYTHONDONTWRITEBYTECODE=1 .../python -m pytest -p no:cacheprovider --basetemp=/tmp/mam-review-65396b40-head-pytest tests/test_issue66_stall_watch_sanitized_name.py tests/test_issue30_stall_watch.py tests/test_issue30_stall_watch_stop.py` — **66 passed, 1 skipped** on macOS, Python 3.9.6 (357.58 s). The skip is the existing Linux-only `/proc` test.
+- For the base comparison, I checked out base into `/tmp/mam-review-65396b40-base`, copied in the new regression test and its strict-mock fixture change, and ran the same test file — **5 failed, 2 passed** (82.04 s). The failures are the expected unconverted-name calls for long and uppercase targets; the plain-name and strict-mock contract tests pass.
+- `git diff --check` — passed. No Bash files changed; the integration tests execute the watcher and mock herdr through the host Bash/Python environment.
+- The reported `test_issue17_item4_decisions.py::test_c_finalize_ends_with_an_unreaped_wrapper[broker_unavailable-3-0]` cleanup race is unrelated to this diff: the changed paths are `stall_watch.py`, the test-only mock in `tests/conftest.py`, and the new Issue #66 regression file; no delegation or process-cleanup implementation changed.
+- No real agent-home databases, actual `.mam` state, or real herdr servers were accessed.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-codex-01/report-75b29d78.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261020T133532Z-a1684a",
+  "base_sha": "ff8b381520ae04e80c73a9e18bfad73d47e853c9",
+  "head_sha": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "tree_sha": "0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a",
+  "review_commit": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "reviewer": "planner-reviewer-codex-01",
+  "job_id": "75b29d78",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-20T15:51:16Z"
+}

.agents/reports/planner-reviewer-codex-01/report-75b29d78.md

@@ -0,0 +1,33 @@
+# Issue #40 교차 코드 리뷰
+
+## 검토 범위와 기준선
+
+리뷰는 브리프가 지정한 immutable 검증 경로 `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261020T133532Z-a1684a/1`에서만 했습니다. HEAD는 `feccfd5e0356c8acf0438bc68bce7ea36ce2588e`, tree는 브리프의 `0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a`와 일치하고, `git status`는 깨끗합니다. diff는 기준선 `ff8b381520ae04e80c73a9e18bfad73d47e853c9` 대비 19개 파일, 1128 insertions / 338 deletions입니다.
+
+검토한 경계는 `autopin.py`와 adapter capture/verify, agy presence-lock 소유 PID 확인, wrapper/create/loop 호출 경로, reconcile drift C 통합, atomic YAML/SQLite 기록, Issue #40/64 회귀 및 기존 tier 테스트입니다. 소스 작업 트리에서는 실행하거나 수정하지 않았습니다. 기준선 checkout으로 테스트를 재실행하지 않았습니다. 리뷰 지침상 지정된 immutable head 검증 경로에서만 실행할 수 있었고 별도 baseline worktree를 만들지 않았기 때문입니다.
+
+## 코드 리뷰 결과
+
+- **agy cross-workspace 및 same-cwd 격리:** cache는 workspace 키에 해당하는 UUID 후보만 제공하며, 후보가 다른 cwd에도 매핑되면 `verify_artifact()`가 거절합니다. sibling UUID 검사는 cache hit와 무관하게 적용됩니다. `capture_active_session_id()`는 pane PID 또는 그 자손이 presence lock/DB 경로를 점유함을 확인하기 전에는 ID를 반환하지 않습니다. lsof/ps, pane PID, 점유자 확인 불능은 fail-closed이고, 다른 행이 이미 UUID를 가졌으면 거절합니다. 이 경로가 `autopin.capture()`와 reconcile drift C에서 공유됩니다.
+- **completed 수신과 중복 처리:** wrapper/create 및 loop 복구가 동일 handler를 호출합니다. handler는 terminal status, local transport, session row와 dispatch token을 검사하고 job-scoped flock와 `(job_id, dispatch_token, attempt_id)` marker로 중복 호출을 억제합니다. publisher는 제어 평면에 쓰지 않습니다. pin 성공은 atomic mutation 안에서 ID와 `session_id_source`/`session_id_verified`를 함께 기록합니다.
+- **기존 안전장치:** epoch/workspace 검증과 sibling exclusion 이후 단일 후보만 선택하고, viewport mismatch에서는 pin을 막습니다. 모호성은 pin하지 않고 행에 사유를 남깁니다. 실패한 pin은 job의 성공 terminal 상태를 덮어쓰지 않습니다. Claude/Grok 및 이미 ID가 있는 행은 capture 경로에서 보존됩니다.
+- **변경 범위:** reconcile의 agent별 후보 검색을 공용 Python capture로 줄이고, create/delegate/loop 호출과 문서·테스트를 더했습니다. stop/purge 구현과 publisher 소유권 경계를 건드리지 않았습니다. 기존 reconcile의 비-0/1 viewport 결과를 degraded pin으로 처리하는 동작은 유지했습니다.
+
+차단성 결함은 발견하지 못했습니다. 비차단 관찰로, reconcile drift C는 `ambiguous`일 때만 구체적 capture 사유를 `last_visible_status`/drifts에 남기고 `unverifiable-owner`, `owner-mismatch`, `rejected`는 조용히 건너뜁니다. completed handler 경로는 이 사유를 기록하므로 안전성 문제는 아니지만, completed 처리 뒤 재시도/운영 진단을 돕기 위해 reconcile에서도 이 세 상태를 warning drift로 노출하면 추적성이 좋아집니다.
+
+## 검증
+
+- `tests/test_issue40_auto_pin.py tests/test_issue64_ro_connect.py`: **70 passed** (42.64s). same-cwd A/B 소유 pane test, presence 소유자 일치/자손/불일치/lsof 불가, 다른 workspace 거절, completed dedupe, ambiguous 및 publisher 경계 포함.
+- `tests/test_issue60_linux_fixes.py tests/test_issue60_opencode_v2.py tests/test_tier1_unit.py tests/test_tier2_component.py`: **176 passed** (390.99s).
+- 변경 shell 파일(`lib.sh`, create script, delegate wrapper, reconcile): `bash -n` 통과.
+- `git diff --check ff8b381..HEAD`: 통과.
+
+기준선에서 새 테스트가 실패하고 HEAD에서 통과한다는 A/B 재실행은 이 리뷰의 격리 경로 제한상 수행하지 않았습니다. HEAD 테스트와 코드 경로 검토만으로 verdict를 냈습니다. 전체 테스트 스위트는 브리프대로 상위 오케스트레이터 검증에 남깁니다.
+
+## 남은 위험
+
+agy 자동 pin은 `lsof`와 `ps`의 소유자 계보 확인에 의존하므로 제한된 권한 환경에서는 정상 대화도 자동 등록되지 않을 수 있습니다. 현재 동작은 오등록보다 false negative를 택해 안전하게 실패합니다. process snapshot과 completed event 처리 사이의 race는 이미 종료된 후보를 보수적으로 거절할 수 있지만, 다른 pane의 ID를 승인하게 하지는 않습니다. 위 reconcile 진단 개선 외에 설계 재계획이 필요한 문제는 발견되지 않았습니다.
+
+리뷰 가능한 변경분에서 자동 pin의 핵심 안전 경로를 확인했고, 관련 회귀 묶음이 모두 통과했습니다. 다른 workspace 또는 동일 cwd sibling의 agy 대화를 잘못 pin할 차단성 우회는 발견하지 못했습니다.
+
+[VERDICT: PASS]

.agents/reports/planner-reviewer-codex-01/report-eb60f37d.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261026T133440Z-c8961b",
+  "base_sha": "29cc4fd90478936f15387a7665e2c95d13a3f14c",
+  "head_sha": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "tree_sha": "98d57bdc60920238c115ece90c90cc694f2744bc",
+  "review_commit": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "reviewer": "planner-reviewer-codex-01",
+  "job_id": "eb60f37d",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-26T17:32:11Z"
+}

.agents/reports/planner-reviewer-codex-01/report-eb60f37d.md

@@ -0,0 +1,30 @@
+# Review report — PR #73 / Issue #71
+
+Reviewed validation snapshot `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2`: head `5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26`, tree `98d57bdc60920238c115ece90c90cc694f2744bc`, base `29cc4fd90478936f15387a7665e2c95d13a3f14c`. The snapshot was clean; `git diff --check` reported no whitespace errors. No source files were changed.
+
+## Findings
+
+No blocking or non-blocking defects found in this pass.
+
+The earlier rowless-stop finding about `HERDR_SESSION_NAME=default` was re-adjudicated in job `f40aa3bd` and withdrawn. That environment value is treated as unset by create: `create_session.sh:179-187,251-256` chooses the workspace server unless the caller supplies `--herdr-session`. Rowless stop follows the same resolution (`stop_session.sh:109-130`; `lib.sh:1681-1712`). The prior probe put an agent on `default` without the explicit option, a state that invocation of create would not produce. Deliberate default-server selection remains possible with `--herdr-session default` and the stop command accepts the same explicit option.
+
+## Review checks
+
+- `attach_command` is centralized in `lib_py/agents/sanitize.py` and used by create (`create_session.sh:512,566`), resume (`update_yaml_resumed.sh:119,151,161`), and reconcile (`reconcile.sh:569,676`). Coverage checks default server rendering, shell quoting, normalized names, and attach argument forwarding.
+- Runtime references to removed `start_command` and `kill_command` fields are gone; only migration compatibility docs/code and assertions remain. The shim’s `new-session` and `kill-session` routes are still needed by the lifecycle scripts. Cleanup guidance now directs to the stop skill (`create_session.sh:364`, `lib_py/agents/id_order.py:342-345`).
+- Rowless stop validates strict registry readability (`stop_session.sh:169-173`), refuses purge without a row (`124-126`), resolves cwd/root canonically before checking containment (`145-154`), and leaves registry bytes untouched (`156-164`). The safety and exit-code cases are covered by the new tests and the stop skill table (`SKILL.md:58-67`).
+- The bash sanitizer is defined once (`lib.sh:44-82`), uses verified hash fallbacks, and errors when no conversion/hash tool is available. On macOS Bash 3.2, names containing `İ`, `-n`, and a trailing newline matched Python under `LC_ALL=C` and `LC_ALL=C.UTF-8`.
+- Registry migration updates all named rows and format metadata (`registry_format.py:35-66`) before caller mutation under `BEGIN IMMEDIATE` (`atomic_yaml.py:78-88`); stale YAML is repaired from DB state (`127-138`). `atomic_dump_yaml` is the only sanctioned registry YAML writer. Future versions are not downgraded. The migration entry point’s output/error contract is documented and implemented in `registry_format.py:17-25,69-88`.
+- StallWatch computes the normalized herdr name once and passes it to its source (`stall_watch.py:229`); its unchanged test passes.
+- S11’s baseline `0fc162e` exists and is an ancestor of this head. Python 3.9.6 and Bash 3.2.57 are the host versions used. The scope excludes Issue #72’s update skill.
+
+## Verification
+
+Commands used the required `PYTHONDONTWRITEBYTECODE=1`, `-p no:cacheprovider`, and `--basetemp` outside the validation checkout.
+
+- Head combined review run (all requested focused and adjacent suites): **461 passed, 1 skipped** in 1295.97s. This included `test_issue71_herdr_names.py`, `test_issue66_stall_watch_sanitized_name.py`, tier 1/2/3, Issues 23/24, 50, 21, 63, 60, layout, and skill blocks.
+- Base Issue #71 regression run from the temporary base snapshot: **68 failed, 2 passed** in 121.85s, matching the expected base behavior.
+- Unicode/name parity probe under C and C.UTF-8: outputs matched Python.
+- `git diff --check`: clean.
+
+[VERDICT: PASS]

.agents/reports/reviewer-agy-01/report-0a1bb7e7.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261026T133440Z-c8961b",
+  "base_sha": "29cc4fd90478936f15387a7665e2c95d13a3f14c",
+  "head_sha": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "tree_sha": "98d57bdc60920238c115ece90c90cc694f2744bc",
+  "review_commit": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "reviewer": "reviewer-agy-01",
+  "job_id": "0a1bb7e7",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-26T17:32:11Z"
+}

.agents/reports/reviewer-agy-01/report-0a1bb7e7.md

@@ -0,0 +1,128 @@
+# PR #73 (`fix/issue-71`) Review Report — `agy` (`herdr:reviewer-agy-01`)
+
+- **Job ID**: `0a1bb7e7`
+- **Loop ID**: `loop-20261026T133440Z-c8961b` (iteration 2)
+- **Issue / PR**: Issue #71 / PR #73 (`fix/issue-71`, 14 commits)
+- **Base Commit**: `29cc4fd90478936f15387a7665e2c95d13a3f14c` (`main`, `v4.10.1`)
+- **Head Commit**: `5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26` (tree `98d57bdc60920238c115ece90c90cc694f2744bc`)
+- **Review Worktree**: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2`
+- **Host Environment**: macOS Darwin arm64 (`Darwin 25.3.0`), `/bin/bash 3.2.57(1)-release`, `/usr/bin/python3 3.9.6`
+
+---
+
+## 1. Executive Summary
+
+PR #73 resolves Issue #71 across all 10 scope items and review refinements (`A`–`F`):
+1. Unifies `attach_command` construction in [`lib_py/agents/sanitize.py::attach_command`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/agents/sanitize.py#L34-L42) (`herdr --session <server> agent attach <sanitized_name>`) across `create_session.sh`, `update_yaml_resumed.sh` (both branches), and `reconcile.sh`, and teaches the `lib.sh` shim's `herdr agent attach` branch to resolve its target via `_resolve_herdr_target`.
+2. Removes `kill_command` and `start_command` from newly written rows, `status.sh --json`, and `SKILL.md` examples, and replaces direct `herdr kill-session` cleanup hints in `create_session.sh` (exit 43) and `id_order.py` with `stop_session.sh --session <name> --herdr-session <srv>`.
+3. Adds row-less session closing (`stop_rowless`) to [`stop_session.sh`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh#L123-L165) with strict registry readability gating (`load_state_json strict`), workspace boundary enforcement (`os.path.realpath` prefix-safe check, exit 5 on foreign workspace), server selection parity with `create_session.sh`, and registry immutability.
+4. Consolidates `_sanitize_herdr_agent_name` into a single definition in [`lib.sh`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib.sh#L40-L85) injected into the generated shim via `declare -f`, achieving exact parity with Python's `sanitize_herdr_agent_name` across ASCII, non-ASCII/multibyte, option-like (`-n`, `-e`), and newline-containing names, while failing closed (nonzero, stderr) when no hash tool or `python3` is available instead of emitting `00000000` or truncated names.
+5. Introduces registry format version 2 (`registry_format: 2`) in [`lib_py/registry_format.py`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/registry_format.py#L1-L92) and [`lib_py/atomic_yaml.py`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/atomic_yaml.py#L121-L138), migrating under the writer lock (`BEGIN IMMEDIATE`) and repairing stale YAML copies on retry.
+6. Computes `herdr_name` once in `StallWatch.__init__` and passes it as a required keyword-only argument `name` to `HerdrSource`.
+
+All 10 review checklist items, macOS `/bin/bash 3.2.57` and `/usr/bin/python3 3.9.6` compatibility checks, negative regression on `base` (`68 failed, 2 passed`), and 461 functional/integration tests on `head` (`461 passed, 1 skipped, 0 failed`) pass on macOS Darwin arm64.
+
+---
+
+## 2. Checklist Verification (Items 1–10)
+
+### 1. Completion Criteria & Scope Discipline (Issue #71 & Scope Comment Items 1–10)
+- **Verified (`PASS`)**:
+  - Every requirement in Issue #71 and the "범위 정리" comment (items 1–10) is implemented and covered by regression tests.
+  - Out-of-scope Issue #72 (`multi-agent-mux-update` skill) is not pulled into this PR; only the `python3 -m lib_py.registry_format --yaml <path>` entry point specified in item 9 is provided for #72 to call. `MAM_VERSION` (`4.10.1`) and `VERSIONS.md` are untouched as intended.
+
+### 2. Regression Suite `tests/test_issue71_herdr_names.py` (Base vs Head & Reconcile Pane Precondition)
+- **Verified (`PASS`)**:
+  - **Base (`29cc4fd90478936f15387a7665e2c95d13a3f14c`)**: Checked out into an isolated temporary directory outside the review worktree and ran `tests/test_issue71_herdr_names.py` (70 tests): **68 failed, 2 passed in 104.17s** (the only 2 passing tests on `base` are `test_the_names_need_converting_and_the_plain_one_does_not` and `test_wrapper_attach_calls_herdr_with_the_herdr_name[lab-plain-creator-claude]`, matching the PR description).
+  - **Head (`5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26`)**: All **70 passed** (including all 4 `hashers` parameterizations: `shasum`, `sha1sum`, `openssl`, `python3`).
+  - **Reconcile test precondition**: [`test_reconcile_registers_with_the_attach_command`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/tests/test_issue71_herdr_names.py#L128-L141) seeds `mock_herdr` with `agents={name: {"agent": "claude", "status": "running", "cwd": str(mam_sandbox), "workspace_id": "w1", "pid": 9999, "pane_id": "w1:p71", "command": "claude", "buffer": "Ready"}}` and asserts `len(rows) == 1` and `rows[0]["last_visible_note"] == "auto-registered by monitor"` before checking `_assert_new_form(rows[0], rows[0]["herdr_session"])`.
+
+### 3. `attach_command` (`lib_py/agents/sanitize.py`) & `lib.sh` Wrapper `agent attach`
+- **Verified (`PASS`)**:
+  - [`lib_py/agents/sanitize.py:34-42`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/agents/sanitize.py#L34-L42) defines:
+    ```python
+    def attach_command(server, name):
+        return "herdr --session %s agent attach %s" % (
+            shlex.quote(server or "default"), shlex.quote(sanitize_herdr_agent_name(name)))
+    ```
+  - Always writes `--session default` when `server` is `"default"` or empty/falsy, and applies `shlex.quote` to both the server and sanitized agent name.
+  - Used by all three writers:
+    - `create`: [`create_session.sh:512, 566`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-create/scripts/create_session.sh#L512-L566)
+    - `resume` (new row and existing row): [`update_yaml_resumed.sh:119, 150, 160`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-resume/scripts/update_yaml_resumed.sh#L119-L160)
+    - `reconcile`: [`reconcile.sh:569, 676`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh#L569-L676)
+  - In [`lib.sh:605-613`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib.sh#L605-L613), the shim's `agent attach` branch shifts `<target>` (`t="$1"; shift`), resolves `tgt=$(_resolve_herdr_target "$t" || true)`, fails with exit 1 if empty, and invokes `_real_herdr agent attach "$tgt" "$@"`, preserving trailing flags such as `--takeover`.
+
+### 4. Removal of `kill_command` & `start_command` and Updated Cleanup Hints
+- **Verified (`PASS`)**:
+  - `git grep -E 'kill_command|start_command'` across the repository confirms no production code, skill doc, or active schema assertion reads or writes `kill_command` or `start_command` (the only remaining mentions are in `registry_format.py` to drop them during v1 -> v2 migration and in `test_issue71_herdr_names.py` / `test_tier2_component.py` asserting their absence).
+  - [`status.sh:221-231`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-status/scripts/status.sh#L221-L231) and [`multi-agent-mux-status/SKILL.md:94-101`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-status/SKILL.md#L94-L101) no longer include `start_command`, and nothing in the codebase reads `start_command` from `status.sh --json`.
+  - The shim's `new-session` and `kill-session` translation branches in `lib.sh` are properly retained because `create_session.sh`, `resume_session.sh`, `stop_session.sh`, and `reconcile.sh` call them internally.
+  - Both user-facing cleanup hints now point to `stop_session.sh`:
+    - [`create_session.sh:364`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-create/scripts/create_session.sh#L364): `bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session $SESSION_NAME --herdr-session ${HERDR_SESSION_NAME:-default}`
+    - [`lib_py/agents/id_order.py:359-360`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/agents/id_order.py#L359-L360): `bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session {m['session']} --herdr-session {srv}`
+
+### 5. Row-less `stop` (`stop_session.sh`) & Strict Registry Read (`load_state_json strict`)
+- **Verified (`PASS`)**:
+  - **Strict registry read gate**: [`stop_session.sh:170-193`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh#L170-L193) calls `STATE_JSON=$(load_state_json strict)` first. In [`lib.sh:1597-1631`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib.sh#L1597-L1631), `load_state_json strict` re-raises `sqlite3.OperationalError` on missing `state` or `sessions` tables as well as corrupt DB / malformed YAML, printing to `stderr` and exiting `1`. Furthermore, `MAPPED_DATA` exits `7` **only** when `d.get('herdr_sessions', [])` was validly iterated and had no matching dict row; non-dict rows (`herdr_sessions: [- 42]`) exit `1` (`cannot read the row`).
+  - **Workspace boundary check**: [`stop_rowless` (`stop_session.sh:145-155`)](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh#L145-L155) resolves both `PANE_CWD` and `WORKSPACE_ROOT` via `os.path.realpath` and checks `cwd == root or cwd.startswith(root + os.sep)`. Verified on macOS that this prevents prefix confusion (`/tmp/ws` vs `/tmp/ws-other`), handles symlinks (`/var` -> `/private/var`), and normalizes trailing slashes; out-of-workspace sessions are refused with exit code `5` before any `kill-session`.
+  - **Server selection order**: Matches `create_session.sh:184-188`: `--herdr-session` (`HERDR_SERVER_OPT`) -> ambient `HERDR_SESSION_NAME` (when non-empty and `!= "default"`) -> workspace server via `resolve_herdr_session`.
+  - **`--purge-conversation` and exit codes**: Refuses `--purge-conversation` on a row-less session with exit `1`, exits `6` if `herdr has-session` still succeeds after `kill-session`, never mutates `agent-sessions.yaml` or `agent-sessions.db`, and matches [`multi-agent-mux-stop/SKILL.md:59-67`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-stop/SKILL.md#L59-L67).
+
+### 6. Single Sanitize Rule in `lib.sh` & macOS BSD / Locale Parity
+- **Verified (`PASS`)**:
+  - [`lib.sh:40-85`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib.sh#L40-L85) has the single definition of `_sanitize_herdr_agent_name`. [`_init_herdr_isolation` (`lib.sh:179-182`)](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib.sh#L179-L182) writes `declare -f _sanitize_herdr_agent_name` into the generated shim (`$wrapper_dir/herdr`).
+  - Removed the duplicate definition in the shim heredoc, removed `"00000000"` and `${s:0:32}` fallbacks, and removed `has-session`'s relative-path `sys.path.insert(0, os.path.abspath(".agents/skills"))` + `lambda s: s.lower()[:32]` fallback (`lib.sh:633-647` now computes `ssess=$(_sanitize_herdr_agent_name "$sess") || exit 1` in bash and passes `TARGET_SAN="$ssess"`).
+  - **macOS `/bin/bash 3.2.57`, BSD `tr`/`sed`, and locale (`LC_ALL=C` and `LC_ALL=en_US.UTF-8`) verification**:
+    - Pure-ASCII check uses `LC_ALL=C tr -d '\000-\177'`. For ASCII inputs, `printf '%s' "$n" | tr '\n' '-' | tr '[:upper:]' '[:lower:]' | sed -E 's/[^a-z0-9_-]/-/g'` avoids `echo` flag parsing (`-n`, `-e`, `-En`) and converts `\n` to `-` before `sed` or command substitution `$(...)` can strip trailing newlines.
+    - For non-ASCII inputs (`İ`, `é`, `ü`, `K`, CJK/Hangul, emoji), it delegates lowercasing and `re.sub(r"[^a-z0-9_-]", "-", ...)` to `python3` so character-by-character replacement and Unicode case folding (`\u0130`.lower() -> `'i\u0307'` -> `'i-'`) match `lib_py.agents.sanitize.sanitize_herdr_agent_name` byte-for-byte, and fails closed (exit 1, stderr) if `python3` is unavailable.
+
+### 7. Registry Format Version 2 (`lib_py/registry_format.py`, `lib_py/atomic_yaml.py`)
+- **Verified (`PASS`)**:
+  - Inside [`atomic_dump_yaml_main` (`lib_py/atomic_yaml.py:121-138`)](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/atomic_yaml.py#L121-L138), after acquiring the flock and `BEGIN IMMEDIATE` and loading `state` + `sessions`, if `from_version < registry_format.CURRENT` (`2`), `registry_format.migrate(d)` runs before the caller's mutation and sets `force_yaml = True`.
+  - Migrates all rows in `herdr_sessions` (`running`, `stopped`, `terminated`, `archived`), drops `kill_command` and `start_command`, recomputes `attach_command`, and sets `d["registry_format"] = 2`.
+  - If the DB was already at format 2 (`elif row:`) but an earlier YAML `os.replace` failed after `conn.commit()`, `force_yaml = registry_format.stored_version(y) < registry_format.CURRENT` detects the stale YAML and rewrites it on the next write.
+  - **Future format preservation**: Verified that when `registry_format` > 2 (e.g., `3`), `stored_version(d)` returns `3`, `from_version < CURRENT` is `False`, and `force_yaml` is `False` — the writer neither downgrades `registry_format` nor clobbers future fields.
+  - **Other registry paths**: Checked all references to `agent-sessions.yaml` across `.agents/skills/`; `atomic_dump_yaml` is the sole writer in production (`create_session.sh`, `update_yaml_resumed.sh`, `stop_session.sh`, `reconcile.sh`, `orc_onboard.sh`), while `load_state_json` (`lib.sh` / `lib_py/state.py`) is strictly read-only.
+  - **CLI entry point**: `PYTHONPATH=.agents/skills python3 -m lib_py.registry_format --yaml <path>` prints `registry-format: <from> -> <to>, rows changed: <n>` and exits `0` (or nonzero with `registry-format: error: ...` on stderr when missing/failing), matching its module docstring contract.
+
+### 8. `stall_watch.py` Single Sanitization Point
+- **Verified (`PASS`)**:
+  - In [`.agents/skills/lib_py/stall_watch.py:158-163, 229-230`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/lib_py/stall_watch.py#L158-L230), `StallWatch.__init__` computes `self.herdr_name = sanitize_herdr_agent_name(args.target)` once and passes `name=self.herdr_name` (required keyword-only parameter) to `HerdrSource`.
+  - `tests/test_issue66_stall_watch_sanitized_name.py` is unmodified in `git diff` and all 7 of its tests pass.
+
+### 9. Test Updates, `skill_code_blocks.json`, and `test_s11` Anchor (`0fc162e`)
+- **Verified (`PASS`)**:
+  - `tests/test_issue50_pane_lock.py`, `tests/test_issue21_worktree_prereqs.py`, `tests/test_tier1_unit.py`, `tests/test_tier2_component.py`, and `tests/test_tier3_integration.py` preserve their original test intent after replacing assertions on removed `start_command`/`kill_command` fields.
+  - `tests/data/skill_code_blocks.json` and `tests/test_issue42_skill_blocks.py` pass all 96 skill-block verification tests.
+  - In [`tests/test_issue23_24_startup_path.py:306-335`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/tests/test_issue23_24_startup_path.py#L306-L335), `test_s11_this_branch_does_not_change_the_generated_shim` pins `base = os.environ.get("MAM_BASE_SHA", "0fc162e")` and extracts both `_sanitize_herdr_agent_name() { ... }` and the `cat <<'EOF'` heredoc body in `_heredoc_body`. Commit `0fc162e` is an ancestor of `HEAD` (`5f60653`) on `fix/issue-71`; when merged into `main` via merge commit (as documented in PR #73), `0fc162e` remains reachable in git history so `test_s11` actively verifies the shim rather than skipping. (The `if show.returncode != 0: pytest.skip(...)` guard is pre-existing for shallow/archive checkouts without history.)
+
+### 10. macOS Compatibility (`/usr/bin/python3 3.9.6`, `/bin/bash 3.2.57`, BSD Userland, SQLite WAL)
+- **Verified (`PASS`)**:
+  - Parsed all 16 modified/added Python files with `/usr/bin/python3` (`3.9.6`) `ast.parse(..., feature_version=(3, 9))` and imported `lib_py.agents.sanitize`, `lib_py.registry_format`, `lib_py.atomic_yaml`, and `lib_py.stall_watch` under system Python 3.9.6.
+  - Checked all 7 modified bash scripts and the generated `.mam/shim/herdr` with `/bin/bash -n` (`GNU bash 3.2.57(1)-release`); no bash 4+ constructs (`declare -A`, `${var,,}`, `mapfile`, `readarray`) are used.
+  - In `tests/test_issue71_herdr_names.py:514-527`, `test_stop_does_not_take_an_unreadable_registry_for_no_row` unlinks `agent-sessions.db*` / `agent-sessions.db-*` before writing corrupt DB/YAML fixtures, properly accounting for macOS SQLite's persistent `-wal`/`-shm` sidecars.
+
+---
+
+## 3. Test Execution Summary on macOS
+
+| Suite / Command | Target | Result |
+|---|---|---|
+| `git diff --check 29cc4fd..5f60653` | Review worktree `/2` | Clean (exit 0) |
+| `/bin/bash -n` on all 7 modified `.sh` scripts | `/bin/bash 3.2.57` | All 7 OK (exit 0) |
+| `/usr/bin/python3` (`3.9.6`) AST + import + `LC_ALL=C`/`en_US.UTF-8` sanitize & path checks | System Python 3.9.6 + `/bin/bash 3.2.57` | `ALL_LOCALE_AND_MULTIBYTE_PARITY_OK`, `FUTURE_FORMAT_PRESERVED_OK`, `STOP_ROWLESS_PATH_BOUNDARY_CHECKS_OK` (exit 0) |
+| `pytest tests/test_issue71_herdr_names.py` | **Base** (`29cc4fd` in temp dir) | **68 failed, 2 passed** in 104.17s |
+| `pytest tests/test_issue71_herdr_names.py tests/test_issue66_stall_watch_sanitized_name.py tests/test_layout.py tests/test_issue42_skill_blocks.py` | **Head** (`5f60653`, worktree `/2`) | **152 passed, 1 skipped** in 150.63s (all 70 in `test_issue71` and all 7 in `test_issue66` passed) |
+| `pytest tests/test_issue60_linux_fixes.py tests/test_tier1_unit.py tests/test_tier2_component.py tests/test_tier3_integration.py tests/test_issue23_24_startup_path.py tests/test_issue50_pane_lock.py tests/test_issue21_worktree_prereqs.py tests/test_issue63_same_cwd_ids.py` | **Head** (`5f60653`) | **309 passed, 0 failed** |
+
+---
+
+## 4. Defects & Observations
+
+### Blocking Defects
+- None.
+
+### Non-Blocking Observations
+- In [`.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job:1021`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2/.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job#L1021), the informational message after `send-keys` prints `(연결하려면: HERDR_SESSION_NAME=$HERDR_SESSION_NAME herdr agent attach $sess — lib.sh를 source한 셸에서 실행)`. Because PR #73 updated the `lib.sh` shim's `herdr agent attach` handler to resolve `$sess` via `_resolve_herdr_target`, this command works as stated when `lib.sh` is sourced, though a future cleanup could also print the native `herdr --session ... agent attach ...` form.
+
+[VERDICT: PASS]

.agents/reports/reviewer-agy-01/report-927ed539.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261025T023502Z-d6f876",
+  "base_sha": "0461a632eb667c7988fd33be92e9a4b36151f22a",
+  "head_sha": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "tree_sha": "15a72c9a1933c64018a2f2d9aa9707348905bb4d",
+  "review_commit": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "reviewer": "reviewer-agy-01",
+  "job_id": "927ed539",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-25T03:40:44Z"
+}

.agents/reports/reviewer-agy-01/report-927ed539.md

@@ -0,0 +1,79 @@
+# PR #70 (`fix/issue-66`) Review Report — `agy` (`herdr:reviewer-agy-01`)
+
+- **Job ID**: `927ed539`
+- **Issue / PR**: Issue #66 / PR #70 (`fix/issue-66`)
+- **Base Commit**: `0461a632eb667c7988fd33be92e9a4b36151f22a`
+- **Head Commit**: `bb496fde785133ad1dbec288aa7431766efb6eb5` (tree `15a72c9a1933c64018a2f2d9aa9707348905bb4d`)
+- **Review Worktree**: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1`
+- **Host Environment**: macOS Darwin arm64 (`Darwin 25.3.0`), `/bin/bash 3.2.57(1)-release`, `/usr/bin/python3 3.9.6`
+
+---
+
+## 1. Executive Summary
+
+PR #70 fixes Issue #66, where `lib_py.stall_watch` passed the unsanitized `--target` session name to `herdr agent get|read|prompt|wait`, causing `stall_watch` to immediately fail with `stall_watch:agent_not_found` (exit code 2) whenever the session name had been transformed by `_sanitize_herdr_agent_name` / `sanitize_herdr_agent_name` at session creation time (e.g. names > 32 characters such as worktree-scoped loop agents, uppercase characters, punctuation, or non-letter leading characters).
+
+All 7 review checklist items, static/Python 3.9 compatibility checks, negative regression checks on `base` (`0461a632eb667c7988fd33be92e9a4b36151f22a`), and functional/regression test runs on `head` (`bb496fde785133ad1dbec288aa7431766efb6eb5`) pass cleanly with zero blocking or non-blocking defects.
+
+---
+
+## 2. Detailed Checklist Verification
+
+### 1. Does `stall_watch.py` use `sanitize_herdr_agent_name` for every `herdr` call (`agent get`, `agent read`, `agent prompt`, `agent wait`)?
+- **Verified (`PASS`)**:
+  - In [`.agents/skills/lib_py/stall_watch.py`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1/.agents/skills/lib_py/stall_watch.py#L158-L212), `HerdrSource.__init__` computes `self.name = sanitize_herdr_agent_name(target)` while preserving `self.target = target`:
+    - `HerdrSource.agent_get` (line 183): `self._herdr("agent", "get", self.name)`
+    - `HerdrSource.input_empty` (line 206): `self._herdr("agent", "read", self.name)`
+    - `HerdrSource.prompt` (line 211): `self._herdr("agent", "prompt", self.name, text)`
+    - (`HerdrSource.agent_pid` at line 187 and `HerdrSource.blocked_text` at line 193 take `pane_id` (`wN:pM`) returned by `agent get`, not the agent name; `_herdr` at line 168 passes `self.session` to `--session`, which is the herdr server session `--herdr-session`.)
+  - In [`StallWatch.__init__`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1/.agents/skills/lib_py/stall_watch.py#L225-L234) and [`StallWatch.run`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1/.agents/skills/lib_py/stall_watch.py#L331), `self.herdr_name = sanitize_herdr_agent_name(args.target)` is passed to `watcher.wait_once(self.herdr_name, until=until, timeout_ms=tmo, session=self.args.herdr_session)`.
+  - Confirmed that `lib_py.agents.sanitize.sanitize_herdr_agent_name` and `lib.sh::_sanitize_herdr_agent_name` produce identical outputs across empty strings, lowercase/uppercase names, leading digits/dashes, >32-char names (`{s[:23]}-{sha1(s)[:8]}`), and special characters.
+
+### 2. Are there any other places where `stall_watch.py` calls `herdr` with an unsanitized agent name?
+- **Verified (`PASS`)**:
+  - Inspected all occurrences of `_herdr`, `herdr`, `wait_once`, `self.target`, and `self.args.target` across [`.agents/skills/lib_py/stall_watch.py`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1/.agents/skills/lib_py/stall_watch.py) and [`.agents/skills/lib_py/loop/watcher.py`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1/.agents/skills/lib_py/loop/watcher.py). No `herdr` invocation uses an unsanitized agent name.
+
+### 3. Does `stall_watch.py` still keep the original `target` name for human-facing log lines and notifications?
+- **Verified (`PASS`)**:
+  - All log lines in `StallWatch` (`stall_watch.py:373`, `397`, `405-406`) continue to format `self.args.target` (the original unsanitized session name):
+    - `[stall-watch] idle detected for {self.args.target} (job {self.args.job_id}); sending nudge`
+    - `[stall-watch] blocked detected for {self.args.target} (job {self.args.job_id}): {text}`
+    - `[stall-watch] cannot judge input box for {self.args.target} (agent={self.kind}, job {self.args.job_id}); nudge withheld`
+  - Progress notifications (`notify_progress`) continue to publish `stalled:idle`, `stalled:blocked ...`, `stalled:unverified_input ...`, and `stall_watch:...` keyed by `--job` (`self.args.job_id`).
+
+### 4. Does `resolve_agent(agent, target)` still receive the original `target` name?
+- **Verified (`PASS`)**:
+  - Both `HerdrSource.__init__` (`stall_watch.py:163`) and `StallWatch.__init__` (`stall_watch.py:230`) pass the original `target` (`args.target`) to `resolve_agent(...)`.
+  - When `--agent` is omitted, `resolve_agent` infers the agent kind from the `-<agent>` suffix of `target` (e.g., `mam-wt-issue-66-very-long-creator-codex` -> `codex`). Passing the sanitized name (`mam-wt-issue-66-very-lo-823a0a24`) would have lost the `-codex` suffix due to 32-character truncation + SHA-1 suffixing. Keeping `resolve_agent` on the original `target` is verified by `test_the_kind_of_a_long_name_comes_from_its_original_suffix`.
+
+### 5. In `tests/conftest.py`, is the `strict_agent_names` opt-in clean and backward-compatible with existing tests?
+- **Verified (`PASS`)**:
+  - In [`tests/conftest.py`](file:///var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1/tests/conftest.py#L473-L476), `_match_agent(k, target)` checks `if state.get("strict_agent_names"): return k == target` and otherwise falls back to the existing substring match (`k == target or target in k or k in target`).
+  - When `strict_agent_names` is enabled and an agent is not found, `cmd2 == "get"` (`tests/conftest.py:1058-1061`) and `cmd2 == "read"` (`tests/conftest.py:1153-1156`) emit `{"error": {"code": "agent_not_found", "message": "agent " + name + " not found"}}` on `stderr` with exit code 1, matching `wait`, `prompt`, and real `herdr`.
+  - Existing tests that do not set `strict_agent_names` retain identical behavior.
+
+### 6. Are the new tests in `tests/test_issue66_stall_watch_sanitized_name.py` genuine behavioral tests that would fail without the fix in `stall_watch.py`?
+- **Verified (`PASS`)**:
+  - Executed `tests/test_issue66_stall_watch_sanitized_name.py` + updated `tests/conftest.py` against `base` (`0461a632eb667c7988fd33be92e9a4b36151f22a`, without the `stall_watch.py` fix):
+    - **5 failed, 2 passed**: Every test case where `sanitize_herdr_agent_name(target) != target` (`creator-claude-fix-issue-99-long-branch`, `Creator-Claude-T`, and `mam-wt-issue-66-very-long-creator-codex`) failed on `base` (`stall_watch:agent_not_found` instead of blocked notice, or empty prompt list instead of idle nudge), while the 2 control tests (`test_the_names_change_and_the_strict_mock_answers_only_the_sanitized_one` and `test_an_idle_agent_is_nudged_through_the_sanitized_name[creator-claude-t]`) passed.
+  - On `head` (`bb496fde785133ad1dbec288aa7431766efb6eb5`), all **7 passed**.
+
+### 7. Is the one-off failure in `test_issue17_item4_decisions.py::test_c_finalize_ends_with_an_unreaped_wrapper[broker_unavailable-3-0]` unrelated to this diff?
+- **Verified (`PASS`)**:
+  - Inspected `tests/test_issue17_item4_decisions.py:204-221` and `565-601`: that test stubs `*lib_py.stall_watch*` in its `$PY` wrapper to `exit 0` immediately and tests `finalize_unfinished` re-observing a live `lib_py.delegation.wrapper` process across a 3-second `broker_unavailable` window (`touch ready` + `time.sleep(2)` in `_terminate_unreaped`). It never imports or executes `lib_py.stall_watch` or `strict_agent_names`.
+  - Both `test_c_finalize_ends_with_an_unreaped_wrapper[broker_unavailable-3-0]` and `[timeout-2-10]` passed on `head` during our verification run.
+
+---
+
+## 3. Verification Summary
+
+| Check | Command / Scope | Result |
+|---|---|---|
+| Whitespace / patch hygiene | `git diff --check 0461a632eb667c7988fd33be92e9a4b36151f22a..bb496fde785133ad1dbec288aa7431766efb6eb5` | Clean (exit 0) |
+| macOS system Python 3.9 syntax & import | `/usr/bin/python3` (`3.9.6`) `ast.parse(..., feature_version=(3, 9))` + `import lib_py.stall_watch` | `PY39_AND_SANITIZE_EQUIV_OK` (exit 0) |
+| Bash vs Python sanitizer equivalence | `lib.sh::_sanitize_herdr_agent_name` vs `sanitize_herdr_agent_name` across 8 edge cases | Exact match (exit 0) |
+| Negative regression on `base` (`0461a63`) | `pytest tests/test_issue66_stall_watch_sanitized_name.py` on `0461a63` + strict mock | `5 failed, 2 passed` (reproduces `stall_watch:agent_not_found`) |
+| Behavioral & regression suites on `head` (`bb496fd`) | `pytest tests/test_issue66_stall_watch_sanitized_name.py tests/test_issue30_stall_watch.py tests/test_issue30_stall_watch_stop.py tests/test_issue17_item4_decisions.py -k "..."` | `91 passed, 1 skipped` in 399.91s (exit 0) |
+| Worktree cleanliness | `git status --short` in review worktree | Clean (no untracked or modified files) |
+
+[VERDICT: PASS]

.agents/reports/reviewer-agy-01/report-99090752.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261020T133532Z-a1684a",
+  "base_sha": "ff8b381520ae04e80c73a9e18bfad73d47e853c9",
+  "head_sha": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "tree_sha": "0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a",
+  "review_commit": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "reviewer": "reviewer-agy-01",
+  "job_id": "99090752",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-20T15:51:16Z"
+}

.agents/reports/reviewer-agy-01/report-99090752.md

@@ -0,0 +1,59 @@
+# Code Review Report — Job `99090752` (Issue #40: Auto-Pin of Post-Discovered Session IDs on `completed`)
+
+- **Reviewer**: `herdr:reviewer-agy-01` (`agy`)
+- **Iteration**: 1
+- **Verification Worktree**: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261020T133532Z-a1684a/1`
+- **Branch / Commit Range**: `fix/issue-40-auto-pin` (`ff8b381520ae04e80c73a9e18bfad73d47e853c9..feccfd5e0356c8acf0438bc68bce7ea36ce2588e`, 1 commit)
+
+---
+
+## 1. Summary of Changes Reviewed
+
+The implementation resolves Issue #40 by unifying post-discovered session ID capture and pinning across the `completed`-receiving control-plane paths and `reconcile.sh` drift C, while eliminating `agy`'s cross-workspace / cross-session conversation ID contamination:
+
+1. **Adapter Contract & Lifecycle Classification (`.agents/skills/lib_py/agents/base.py`, `claude.py`, `grok.py`, `agy.py`)**:
+   - Introduces `PRE_ASSIGNED` (`claude`, `grok`) and `POST_DISCOVERED` (`agy`, `opencode`, `codex`, `hermes` via `BaseAgentAdapter.id_lifecycle` default).
+   - Adds `BaseAgentAdapter.capture_active_session_id(ctx)` (read-only), returning `capture_result(status, session_id=..., reason=..., candidates=...)`. For `opencode`, `codex`, and `hermes`, a session ID is captured only when `discover(ctx)` yields **exactly one** candidate accepted by `verify_session_uuid(..., mode="discover")` and not claimed in `ctx.row["_sibling_claimed_uuids"]`.
+   - `AgyAgentAdapter.verify_artifact` (`mode="discover"`) now:
+     - Rejects any UUID mapped by `cache/last_conversations.json` to another workspace (`workspace_key(k) != workspace_key(ctx.cwd)`).
+     - Rejects any UUID in `ctx.row.get("_sibling_claimed_uuids")` unconditionally (eliminating the previous `if not cache_match:` bypass that allowed two `agy` sessions in the same `cwd` to cross-pin the same cached conversation ID).
+   - `AgyAgentAdapter.capture_active_session_id(ctx)` treats `last_conversations.json[cwd]` strictly as a proposal and requires `_owner_check(uuid, ctx)` (`lsof -t` on `presence/<uuid>.lock`, `<uuid>.db`, `-wal`, `-shm` held by `pane.pid` or a descendant in `ps -eo pid=,ppid=`).
+2. **Control-Plane Auto-Pin Handler (`.agents/skills/lib_py/agents/autopin.py`, `.agents/skills/lib.sh`)**:
+   - Implements `claimed_elsewhere`, `capture`, `pin_row`, `resume_dry_run`, `tui_viewport`, `handle_completed`, and CLI `python -m lib_py.agents.autopin`.
+   - Enforces security and trust boundaries (#15/#20/#21): only the receiving/verifying side mutates `.mam/agent-sessions.yaml` via `atomic_dump_yaml`; `publish_event.py` / `publisher.py` never touch the session registry.
+   - Deduplicates per `(job_id, dispatch_token, attempt_id)` under `fcntl.flock` (`<job_dir>/autopin.lock`) + atomic `os.replace` marker (`<job_dir>/autopin.json`).
+   - Skips remote (`transport == "remote"` / `remote:*`), `human`, non-`completed`, or stale-dispatch-token records; leaves `PRE_ASSIGNED` and already-pinned rows untouched; records failure/ambiguity reasons in `last_visible_status` without failing the completed job.
+3. **Call Sites & Reconcile Unification (`create_session.sh`, `multi-agent-mux-delegate-job`, `runner.py`, `reconcile.sh`)**:
+   - `create_session.sh`: invokes `delegate_autopin_completed "$DELEGATE_JOB_ID" "$DELEGATE_JOB_TOKEN" "$task_reg_dir"` upon onboarding `completed`.
+   - `multi-agent-mux-delegate-job`: invokes `delegate_autopin_completed "$JOB_ID" "$_disp_tok" "$REGISTRY_DIR"` when direct job finishes `completed`.
+   - `lib_py/loop/runner.py`: invokes `self._autopin(job_id)` in `wait_for_job` when `status == "completed"` as an idempotent recovery path (preserving `G9` import isolation via subprocess invocation).
+   - `reconcile.sh`: replaces the separate drift C blocks for `agy` (which previously globbed `conversations/*.db` across all workspaces), `hermes`, `opencode`, and `codex` with a single loop calling `autopin.capture(s, agent, d, home_dir=home)` and `autopin.pin_row` / `autopin.resume_dry_run`.
+
+---
+
+## 2. Verification & Test Evidence
+
+All verification was executed against the isolated worktree `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261020T133532Z-a1684a/1` with temporary `HOME` and `--basetemp` directories (no real user/agent state databases opened):
+
+1. **Issue #40 Completion Conditions (`tests/test_issue40_auto_pin.py`)**:
+   - **Condition 1 (No cross-workspace `agy` pinning)**: `test_agy_verify_rejects_id_cached_for_another_workspace`, `test_reconcile_does_not_pin_another_workspaces_agy_conversation`, `test_autopin_does_not_pin_another_workspaces_agy_conversation` — **PASSED**.
+   - **Condition 2 (First completed job pins without daemon)**: `test_completed_onboarding_pins_agy_without_daemon`, `test_completed_first_job_pins_opencode_codex_hermes[opencode|codex|hermes]`, `test_reconcile_pins_agy_owned_by_the_pane`, `test_lib_sh_helper_pins_through_the_cli`, `test_create_onboard_pins_without_daemon` — **PASSED**.
+   - **Condition 3 (Idempotency per job/token/attempt, ambiguity & ownership handling)**: `test_agy_same_cwd_sibling_never_cross_pins`, `test_agy_capture_requires_presence_owned_by_pane` (4 parametrized cases), `test_agy_holder_pids_reads_lsof`, `test_wrapper_and_loop_recovery_pin_once`, `test_loop_recovery_pins_when_the_wrapper_did_not`, `test_ambiguous_candidates_leave_reason_without_pin` — **PASSED**.
+   - **Condition 4 (Pre-assigned & existing IDs untouched, ineligible/stale skipped, publisher boundary)**: `test_preassigned_and_existing_ids_are_untouched`, `test_ineligible_jobs_pin_nothing` (4 parametrized cases), `test_stale_dispatch_token_pins_nothing`, `test_call_sites_and_publisher_boundary` — **PASSED**.
+2. **Regression & Component Suites**:
+   - `pytest tests/test_issue40_auto_pin.py tests/test_issue64_ro_connect.py tests/test_issue60_linux_fixes.py tests/test_issue60_opencode_v2.py tests/test_a4_adapter_contract.py tests/test_tier1_unit.py -v` → all 27 tests in `tests/test_issue40_auto_pin.py` and all unit/adapter/ro_connect tests **PASSED** (`237 passed, 0 failed`).
+   - `pytest tests/test_issue40_auto_pin.py tests/test_issue64_ro_connect.py tests/test_issue60_linux_fixes.py tests/test_issue60_opencode_v2.py tests/test_a4_adapter_contract.py tests/test_tier1_unit.py tests/test_tier2_component.py -k "opencode or codex or agy or hermes or autopin or capture or lifecycle or ro_connect or issue40"` → **131 passed** (`0` failed).
+3. **Negative Regression Verification Against Base (`ff8b381520ae04e80c73a9e18bfad73d47e853c9`)**:
+   - Exported `ff8b381520ae04e80c73a9e18bfad73d47e853c9` via `git archive` to a temporary directory and ran `tests/test_issue40_auto_pin.py` tests (`test_adapter_id_lifecycle_classification`, `test_agy_verify_rejects_id_cached_for_another_workspace`, `test_reconcile_does_not_pin_another_workspaces_agy_conversation`, `test_call_sites_and_publisher_boundary`) → **4 failed (`BASE_RC=1`)**, confirming the tests directly catch the pre-fix behavior (including `reconcile.sh` pinning `proj-B`'s `UB` onto `proj-A`'s row).
+4. **Static & Hygiene Checks**:
+   - `git diff --check ff8b381520ae04e80c73a9e18bfad73d47e853c9..feccfd5e0356c8acf0438bc68bce7ea36ce2588e` → clean (exit `0`).
+   - `bash -n` on `.agents/skills/lib.sh`, `create_session.sh`, `multi-agent-mux-delegate-job`, and `reconcile.sh` → clean (exit `0`).
+   - `git status --short` in verification worktree → clean.
+
+---
+
+## 3. Findings
+
+No blocking issues, regressions, or defects found.
+
+[VERDICT: PASS]

.agents/reports/reviewer-agy-01/report-a967e100.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261027T201245Z-63c71b",
+  "base_sha": "1d63e882bc1c46e9af8484647d5091b296d8fa3f",
+  "head_sha": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "tree_sha": "fbadb24de60ccdae684b23e2e0a41cdf23ab81eb",
+  "review_commit": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "reviewer": "reviewer-agy-01",
+  "job_id": "a967e100",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-27T21:06:27Z"
+}

.agents/reports/reviewer-agy-01/report-a967e100.md

@@ -0,0 +1,115 @@
+# Code Review Report — PR #75 Follow-up Round (`1d63e88..ec7f5c4`, Issue #72)
+
+- **Job ID**: `a967e100`
+- **Reviewer**: `agy` (`herdr:reviewer-agy-01`)
+- **Loop ID**: `loop-20261027T201245Z-63c71b` (Round 1)
+- **Review Snapshot Path**: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1`
+- **Branch**: `fix/issue-72`
+- **Base Commit**: `1d63e882bc1c46e9af8484647d5091b296d8fa3f` (cumulative base: `0e1e2e87dea7fcaab69d6ac388121c35b02b7dab`)
+- **Head Commit**: `ec7f5c4e57286fb3c4238b8220f39094f4640391`
+- **Tree Hash**: `fbadb24de60ccdae684b23e2e0a41cdf23ab81eb`
+
+---
+
+## 1. 확인한 것 (Files & Line Ranges Inspected in Review Snapshot)
+
+- **`1d63e88..ec7f5c4` 변경분 집중 검증**:
+  - `.agents/skills/lib.sh:2278-2317` (`_start_watchdog_legacy`):
+    - `MAM_DELEGATION_PY=0` 경로에서 `case $- in *m*) had_m=1 ;; esac`, `set -m`으로 `nohup bash "$monitor_script" --subscribe --idle-timeout 0 </dev/null >> "$log_file" 2>&1 &`를 실행한 뒤 `[ "$had_m" = 1 ] || set +m`으로 호출자의 job-control 옵션을 복원(`lib.sh:2303-2309`).
+    - macOS(`/bin/bash` 3.2, `setsid(1)` 없음)에서도 `set -m` 아래 백그라운드 작업이 자체 프로세스 그룹(`pgid == pid`)으로 기동되어 호출자의 프로세스 그룹에서 분리됨을 확인.
+    - 기존 동작(`_monitor_pids` 중복 방지, `MAM_NO_SUBSCRIBER_DAEMON=1` opt-out, `echo "$pid"` 보고, `</dev/null`, `>> "$log_file" 2>&1`)이 그대로 보존됨을 확인.
+  - `tests/test_issue72_update.py:184-195, 221-241, 697-726`:
+    - `_descendants(pid)`(`184-186`) 및 읽기 전용 `_processes_naming(path)`(`189-193`) 추가.
+    - `box` fixture teardown(`221-241`)에서 패턴 기반 `pkill -KILL -f <ws>`를 완전히 제거하고, 테스트가 직접 띄운 `b.helpers` 프로세스 그룹(`os.killpg`)과 `_exact_monitor_pids(ws / MONITOR_REL)` + 그 자식(`_descendants(pid)`)만 `SIGKILL`로 정리한 뒤 `_until(lambda: not _processes_naming(ws), timeout=10)`으로 잔존 프로세스가 없음을 검증.
+    - `test_every_restart_starts_a_real_monitor_in_both_delegation_modes`(`697-726`): 6개 조합(`mode` `0`/`1` × `installed`/`killed`/`rolled-back`) 모두에서 `assert all(os.getpgid(int(p)) != os.getpgrp() for p in box.monitor_pids())`로 모니터의 PGID가 호출자의 PGID와 다름을 검증.
+- **누적 변경분(`0e1e2e8..ec7f5c4`) 정합성 확인**:
+  - `.agents/skills/lib.sh:24-35, 2238-2317, 3299-3379`
+  - `.agents/skills/lib_py/delegation/daemon.py:40-79`
+  - `.agents/skills/lib_py/pane_lock.py:1-130`
+  - `.agents/skills/lib_py/update.py:1-428`
+  - `.agents/skills/multi-agent-mux-update/SKILL.md:1-30`
+  - `.agents/skills/multi-agent-mux-update/scripts/{update.sh,install_phase.sh,post_update.sh}`
+  - `.agents/skills/multi-agent-mux-{create,resume,stop,loop,orc-onboard,delegate-job}` 및 `deploy/{install.sh,install_mam.sh,remove.sh}`
+
+---
+
+## 2. 결정 1–10, U1–U4, Attach 댓글 및 완료 조건 대조표
+
+| 항목 | 요구사항 요약 | 구현 위치 | 테스트 커버리지 | 상태 |
+|---|---|---|---|---|
+| 결정 1 | 활성 세션(레지스트리 `running` + 모든 실행 중 herdr 서버의 워크스페이스 내 라이브 에이전트)·루프·열린 잡(`pending`/`dispatched`/`running`, 타 제어 평면은 본 레지스트리 대상 잡만) 있으면 거부 및 해제 명령 안내 | `lib_py/update.py:150-267`, `update.sh:124-162` | `tests/test_issue72_update.py` (`test_every_refusal_condition_blocks_and_leaves_the_workspace_untouched` 외 9개) | 충족 |
+| 결정 2 | 모니터 데몬(`reconcile.sh --subscribe`) 자동 정지(`SIGTERM`→`SIGKILL`)·설치/타임아웃/롤백 후 호출자 프로세스 그룹에서 분리하여 재기동(`MAM_DELEGATION_PY=0/1` 모두 정확 매칭 및 별도 PGID); `resume` 시 모니터 보장 | `update.sh:100-116,165-212`, `post_update.sh:37-46`, `install_phase.sh:57-69`, `resume_session.sh:215-225,250,299`, `daemon.py:40-79`, `lib.sh:2238-2317` | `tests/test_issue72_update.py` (`test_every_restart_starts_a_real_monitor_in_both_delegation_modes` 외), `tests/test_issue72_resume_monitor.py` | 충족 |
+| 결정 3 | 설치 실패 시 `.agents`, `.mam_deploy`, 루트 문서, `.venv`, 설치기 관리 `.mam` 항목, 레지스트리 전체 되돌리기 | `update.sh:240-262`, `install_phase.sh:27-44,104-115` | `tests/test_issue72_update.py` (`test_a_failing_install_rolls_back_the_entire_workspace_and_restarts_the_monitor` 외) | 충족 |
+| 결정 4 | 업데이트 완료 후 새 코드로 레지스트리 변환(`lib_py.registry_format`), 레지스트리 없으면 생략, 실패 시 설치 유지 + 0 아닌 종료 | `post_update.sh:27-35` | `tests/test_issue72_update.py` (`test_a_conversion_failure_keeps_the_new_install_and_exits_nonzero` 외) | 충족 |
+| 결정 5 | 2단계 분리: 워크스페이스 밖 임시 복사본(`install_phase.sh`)을 `exec`(같은 PID 유지)한 뒤 새 트리의 `post_update.sh`를 별도 프로세스로 실행 | `update.sh:214-215,264-267`, `install_phase.sh:118-129` | `tests/test_issue72_update.py` (`test_the_clean_update_runs_both_phases_converts_the_registry_and_restarts_the_monitor`) | 충족 |
+| 결정 6 | `deploy/update.sh` 제거, `multi-agent-mux-update` 스킬로 일원화, `deploy/install.sh` 제자리 재실행 정리(없어진 파일 삭제·수정 파일 보존, `install_state` 제자리 갱신) | `deploy/install.sh:191-196,403-448,632-653`, `deploy/update.sh`(삭제) | `tests/test_issue72_installer.py`, `tests/test_deploy_layout.py`, `tests/test_issue8_update_state.py` | 충족 |
+| 결정 7 | 호출 에이전트 자신(`(caller_server, HERDR_PANE_ID)`)과 그 `running` 행·실행 중인 잡 1개는 차단 대상에서 제외 | `lib_py/update.py:192-219,229-230,244-250`, `lib_py/pane_lock.py:25-39` | `tests/test_issue72_update.py` (`test_the_calling_agent_its_row_and_its_running_job_are_excluded` 외 3개) | 충족 |
+| 결정 8 | 업데이트 입장 잠금(`.mam/update-admission.lock` 공유/배타 + `.mam/update-in-progress` 표식): `create`·`resume`·`run_loop`·`delegate submit`·`stop`·`orc-onboard` 차단, 자식 프로세스 fd 누수 방지 | `lib.sh:3312-3379`, `lib_py/pane_lock.py:42-115`, `lib_py/update.py:277-322` | `tests/test_issue72_admission.py` (21개 케이스) | 충족 |
+| 결정 9 | `update.sh [-y|--yes]`: TTY면 프롬프트, 비-TTY에서 `-y` 없으면 거부(`exit 1`) | `update.sh:30-60` | `tests/test_issue72_update.py` (`test_confirmation_prompt_and_non_tty_refusal`) | 충족 |
+| 결정 10 | 되돌리기 범위에서 작업 기록(`jobs`, `delegate_job_logs`, `state`, `worktrees`, `locks`) 보존 및 레지스트리 백업(`sqlite3.backup` + YAML/bak) 복원 | `update.sh:241-256`, `lib_py/update.py:342-366`, `install_phase.sh:37-44` | `tests/test_issue72_update.py` (`test_rollback_restores_every_item_the_installer_can_touch_and_leaves_work_records`) | 충족 |
+| U1 | attach 안내 헬퍼는 추가하지 않고 기존 행의 `attach_command`(`ATTACH_CMD`)를 그대로 사용 | `create_session.sh:654`, `multi-agent-mux-delegate-job:680-687` | `tests/test_issue72_attach_hints.py` | 충족 |
+| U2 | `.mam` 없는 트리에서 입장 잠금 헬퍼가 `.mam`이나 잠금 파일을 만들지 않고 통과 | `lib.sh:3315` | `tests/test_issue72_admission.py` (`test_a_tree_without_mam_stays_clean`) | 충족 |
+| U3 | `MAM_UPDATE_MONITOR_STOP_S`를 `mam_int_knob`으로 읽고 `test_issue26_ints.py` 표에 등록 | `update.sh:189`, `tests/test_issue26_ints.py:67` | `tests/test_issue26_ints.py` | 충족 |
+| U4 | 이전 업데이트가 남긴 `.mam/update-backup/` 상태별 처리(`backing-up`/`installed`/빈 상태 삭제, `installing`은 `--skip-registry`로 파일만 복원, 알 수 없는 상태 거부) | `update.sh:218-237`, `install_phase.sh:36` | `tests/test_issue72_update.py` (`test_a_leftover_backup_from_a_killed_update_is_handled_by_state`) | 충족 |
+| 댓글 #926, #930 | `multi-agent-mux-delegate-job` 및 `create_session.sh`의 attach 안내가 `--session <server>`를 포함한 `attach_command`를 출력 | `create_session.sh:654`, `multi-agent-mux-delegate-job:680-687` | `tests/test_issue72_attach_hints.py` (8개 케이스) | 충족 |
+| 첫 전환 (완료 조건 5) | 옛 `update.sh`가 있는 설치본에서 첫 전환 시 새 `install.sh`를 거쳐 `multi-agent-mux-update` 스킬과 레지스트리 변환까지 도달 | `deploy/install.sh:191-196,403-405`, `tests/test_issue72_update.py:909-966` | `tests/test_issue72_update.py` (`test_the_first_transition_from_the_old_updater_reaches_the_skill_and_conversion`) | 충족 |
+
+빠진 완료 조건: **없음**.
+
+---
+
+## 3. 실행한 테스트와 결과 (macOS 실측)
+
+검증 경로(`/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1`)에서 브리프의 격리 실행 명령으로 새·바뀐 테스트 파일과 watchdog 관련 테스트(`test_issue5_phase1_delegation.py`, `test_issue19_subscriber_daemon_lifecycle.py`)를 모두 실행했습니다.
+
+### 명령 1 (`tests/test_issue72_update.py`, `tests/test_issue72_resume_monitor.py`, `tests/test_issue42_skill_blocks.py`)
+```bash
+BT="$(mktemp -d "${TMPDIR:-/tmp}/mam-rev-a967e100-1.XXXXXX")"
+trap 'rm -rf "$BT"' EXIT
+cd /var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1 && \
+env -u HERDR_SOCKET_PATH -u HERDR_PANE_ID -u HERDR_TAB_ID -u HERDR_WORKSPACE_ID -u HERDR_SESSION_NAME -u HERDR_SESSION -u WORKSPACE_ROOT -u MAM_ENV_FILE -u MAM_JOBS_DIR -u DELEGATE_JOB_LOGS_DIR \
+PYTHONDONTWRITEBYTECODE=1 /Users/godopu16/PuKi/laa/canary_projects/multi-agent-mux/.venv/bin/python -m pytest -p no:cacheprovider --basetemp="$BT/pytest" \
+  tests/test_issue72_update.py \
+  tests/test_issue72_resume_monitor.py \
+  tests/test_issue42_skill_blocks.py
+```
+- **결과**: `95 passed, 1 skipped in 379.90s (0:06:19)` (exit code `0`)
+
+### 명령 2 (watchdog 관련 스위트 2종 + 나머지 변경·신규 테스트 7종)
+```bash
+BT="$(mktemp -d "${TMPDIR:-/tmp}/mam-rev-a967e100-2.XXXXXX")"
+trap 'rm -rf "$BT"' EXIT
+cd /var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1 && \
+env -u HERDR_SOCKET_PATH -u HERDR_PANE_ID -u HERDR_TAB_ID -u HERDR_WORKSPACE_ID -u HERDR_SESSION_NAME -u HERDR_SESSION -u WORKSPACE_ROOT -u MAM_ENV_FILE -u MAM_JOBS_DIR -u DELEGATE_JOB_LOGS_DIR \
+PYTHONDONTWRITEBYTECODE=1 /Users/godopu16/PuKi/laa/canary_projects/multi-agent-mux/.venv/bin/python -m pytest -p no:cacheprovider --basetemp="$BT/pytest" \
+  tests/test_issue5_phase1_delegation.py \
+  tests/test_issue19_subscriber_daemon_lifecycle.py \
+  tests/test_deploy_layout.py \
+  tests/test_issue26_ints.py \
+  tests/test_issue8_update_state.py \
+  tests/test_version_consistency.py \
+  tests/test_issue72_attach_hints.py \
+  tests/test_issue72_installer.py \
+  tests/test_issue72_admission.py
+```
+- **결과**: `219 passed in 509.96s (0:08:29)` (exit code `0`)
+
+### 명령 3 (`/bin/bash -n` 구문 검사 및 프로세스·워크트리 무결성 확인)
+- 변경된 모든 셸 스크립트(13개) `/bin/bash -n` 통과 (`exit 0`).
+- `git status --short`: 출력 없음 (검증 스냅샷 깨끗함).
+- `ps -ef`: 본 체크아웃의 기존 `reconcile.sh --subscribe` 데몬(PID `3714`)만 정상 유지 중이며, 테스트가 남긴 자식·더미 프로세스 없음.
+
+---
+
+## 4. 발견 사항 (차단 / 비차단)
+
+- **차단 (Blocking)**: 없음.
+- **비차단 (Non-Blocking)**: 없음.
+
+---
+
+## 5. 사용자 확인 필요
+
+- 없음.
+
+[VERDICT: PASS]

.agents/reports/reviewer-agy-01/report-cae1ea73.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261023T035928Z-2ccc02",
+  "base_sha": "dc886ecd6b38c01032a55a2d1c230c73362ae630",
+  "head_sha": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "tree_sha": "f1af6fdd548ee5d6f6b81e2202833edfaca98188",
+  "review_commit": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "reviewer": "reviewer-agy-01",
+  "job_id": "cae1ea73",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-23T05:16:58Z"
+}

.agents/reports/reviewer-agy-01/report-cae1ea73.md

@@ -0,0 +1,74 @@
+# PR #69 (Issue #63) Round 3 Code Review Report — `agy` (`reviewer-agy-01`)
+
+- **Job ID**: `cae1ea73`
+- **Branch / Range**: `fix/issue-63` (`dc886ecd6b38c01032a55a2d1c230c73362ae630..1614af5b673d7519d3a38f63e3636055592b4f14`, 13 commits)
+- **Tree**: `f1af6fdd548ee5d6f6b81e2202833edfaca98188`
+- **Verification Worktree**: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261023T035928Z-2ccc02/1`
+- **Environment**: macOS (`Darwin arm64`), `/bin/bash 3.2.57(1)-release`, `/usr/bin/python3 3.9.6`, `.venv/bin/python 3.9.6`
+- **Summary**: **PASS** (`P0: 0`, `P1: 0`, `P2: 0`)
+
+---
+
+## 1. 2·3차 리뷰 후속 커밋 (`ede9c62`, `8f64174`, `7cac6f6`, `1614af5`) 집중 검증 결과
+
+### 1.1 권위 있는 "세션 없음" 응답에서만 고아 마커 삭제 (`8f64174`, `id_order.py:58-90,225-227`)
+- `herdr_session_state(server, session, timeout)` (`id_order.py:58-90`)는 `MAM_NO_AUTOSTART="1"` 및 `HERDR_SESSION_NAME=server or "default"` 환경에서 `source "$1" && _herdr agent list`를 실행합니다.
+- `res.returncode == 0`이고 `json.loads(res.stdout)["result"]["agents"]`가 리스트이며, 그 안에 `session` 및 `sanitize_herdr_agent_name(session)`이 모두 없을 때에만 `False`를 반환합니다 (`id_order.py:74-83`).
+- `_read_and_prune_markers` (`id_order.py:225-227`)는 `drop = live is False`로 판정하여, 조회 실패·타임아웃·파싱 실패(`live is None`) 시에는 마커를 삭제하지 않고 `_orphan = "unknown"`으로 유지합니다.
+
+### 1.2 `server_not_running` 불확실 처리 및 `MAM_ID_ORDER_WAIT_S=0` 무프로브 보장 (`7cac6f6`, `id_order.py:58-90,280-291,330-346`)
+- `server_not_running`을 포함한 모든 비정상 종료(`res.returncode != 0`)에서 `herdr_session_state`가 `None`을 반환하므로 서버 다운 상태에서도 고아 마커가 삭제되지 않고 fail-closed로 차단됩니다.
+- `bounded_probe` (`id_order.py:285-290`)가 `deadline - time.monotonic()`을 `timeout`으로 전달하고, `herdr_session_state` 첫 줄(`if timeout <= 0: return None`, `id_order.py:64-65`)에서 즉시 반환하므로:
+  - 다수의 죽은 마커가 있더라도 전체 프로브 시간이 `MAM_ID_ORDER_WAIT_S` 상한 안에 엄격히 묶입니다 (`test_id_order_herdr_probes_stay_within_the_wait_cap`).
+  - `MAM_ID_ORDER_WAIT_S=0`(`cap == 0`)일 때는 herdr 서브프로세스를 전혀 호출하지 않고 즉시 거부하며 `(MAM_ID_ORDER_WAIT_S=0 leaves no time to ask herdr)` 안내를 출력합니다 (`id_order.py:336-338`).
+- `answers: Dict[str, bool]` (`id_order.py:283,287-289,333`)가 이전 폴링에서 확인된 확정 응답을 보존하여 마지막 폴링 시점에 예산이 소진되더라도 `"its herdr session is alive"` 메시지를 정확히 유지합니다.
+
+### 1.3 동일 세션 이름(`sess == me`)의 죽은 owner 마커에 동일한 고아 규칙 적용 (`1614af5`, `id_order.py:180-235,305`)
+- `_read_and_prune_markers`에서 `sess == me`일 때 무조건 삭제하던 분기를 제거하여(`id_order.py:217-227`), 이전 `create`/`resume`이 pane을 띄운 직후 죽어 고아 세션을 남긴 상태에서 **같은 세션 이름**으로 재시도하더라도:
+  - 고아 herdr 세션이 살아 있거나 확인 불가(`True`/`None`)이면 마커를 유지하고 차단합니다 (`blockers()`는 `m_sess == me`를 건너뛰지 않음, `id_order.py:130-145`).
+  - herdr가 해당 세션이 사라졌음을 확인(`False`)하면 죽은 마커를 삭제하고 새 시도의 마커로 교체(`owner_pid == my_pid`)하여 정상 진입합니다 (`test_id_order_dead_owner_marker_blocks_while_its_unregistered_herdr_session_is_alive`, `test_id_order_real_probe_against_mock_herdr_fails_closed`).
+
+### 1.4 세 수정 간 정합성 및 일반 사용(정상 create/resume, 재시도) 600초 대기 미발생 검증
+- **정상 `create` 후 진행 중**: 첫 세션이 YAML 행을 `status: "running"` 및 `herdr_session_epoch > prev_epoch`로 등록하면 `_registered_for_attempt` (`id_order.py:174-177`)가 `True`를 반환해 herdr 프로브 없이 마커가 즉시 삭제되고, 이후에는 YAML 행의 `own_id` 기록 여부에 따라 대기가 결정됩니다.
+- **정상 `stop` 후 후속 `create`/`resume`**: 세션이 정상 중지되면 `own_id`가 기록되거나(`pinned_for_attempt == True`) `stopped_at_epoch > max(m_at, prev_end_epoch)`(`ended_after_attempt == True`)가 성립하므로 `blockers()` (`id_order.py:150-163`)가 이를 차단 목록에서 즉시 제외하여 600초 대기가 발생하지 않습니다.
+- **`create` 실패·롤백(`exit 42`) 후 재시도**: `create_session.sh`의 `cleanup_herdr_on_error` 트랩(`create_session.sh:337-368`)이 실행 중인 워크스페이스 herdr 서버에서 세션을 즉시 종료하므로, 재시도 시 첫 폴링의 `_herdr agent list`가 빈 에이전트 목록(`False`)을 반환해 죽은 마커를 즉시 정리하고 대기 없이 통과합니다.
+
+---
+
+## 2. 전체 체크리스트 (1~8) 점검 요약
+
+| # | 점검 항목 | 결과 | 근거 파일 및 라인 |
+|---|---|---|---|
+| 1 | 완료 조건 1~8 및 테스트 커버리지 | **PASS** | `session_ids.py:116-297`, `id_order.py:1-382`, `tests/test_issue63_same_cwd_ids.py` (총 27개 테스트) |
+| 2 | `#40` `autopin.capture` 재사용 (판정 단일화) | **PASS** | `session_ids.py:19,176,272` (`from lib_py.agents.autopin import OWN_KEYS, capture, claimed_elsewhere`), `lib.sh` 구 `capture_conversation_id` 제거 |
+| 3 | `id_order.py` 잠금·만료·비차단 조건·`MAM_ID_ORDER_WAIT_S` | **PASS** | `fcntl.flock` (`id_order.py:293`), `wait_s` (`id_order.py:36-41`), `herdr_session_state` (`id_order.py:58-83`), `_read_and_prune_markers` (`id_order.py:180-235`) |
+| 4 | `resume`: `--drop-stale-id`, 사전 거부(exit 1), 이미 실행 중 분기, `SKILL.md` | **PASS** | `resume_session.sh:132-170,243,270-276`, `update_yaml_resumed.sh:21,66-197`, `multi-agent-mux-resume/SKILL.md:59-83,165-171` |
+| 5 | `stop`: kill 전 ID 판정, 죽은 herdr 미기록+이유 기록, purge 재검증 | **PASS** | `stop_session.sh:104-179,233-286,308-358`, `multi-agent-mux-stop/SKILL.md:38-55,98-115` |
+| 6 | 삭제된 심볼 잔존 참조 없음 (`capture_conversation_id`, `CAPTURE_ID`) | **PASS** | `git grep` 결과 코드·문서·테스트 내 잔존 참조 0건 |
+| 7 | macOS 호환성 (`/bin/bash 3.2.57`, `/usr/bin/python3 3.9.6`) | **PASS** | 수정된 셸 6개 `/bin/bash -n` 통과, Python 3.9 AST 파싱 및 모듈 import(`PY39_IMPORT_OK`) 통과 |
+| 8 | `test_issue34_job_tree.py::test_t5b_a_*[False]` 관련성 여부 | **PASS** | 본 브랜치는 루프·잡 트리(`lib_py/loop`, `delegate-job`)를 전혀 수정하지 않으며, 해당 테스트는 본 변경과 무관함 |
+
+---
+
+## 3. 실행한 검증 명령 및 결과
+
+1. **정적 검사 (`git diff --check`, `/bin/bash -n`, `/usr/bin/python3` 3.9.6 import)**:
+   - Exit `0` (`PY39_IMPORT_OK`).
+2. **Issue #63 `id_order` 및 이식성 테스트 + 실제 `herdr` 호출 감시(Spy) 검증**:
+   - `pytest tests/test_issue63_same_cwd_ids.py -k "test_id_order or test_c6_id_order_markers or test_portability" -v`
+   - 결과: **`8 passed`**, `SPY_LOG` 비어 있음 (`0` calls).
+3. **Herdr 격리 및 Skill 블록 인벤토리 정합성 테스트**:
+   - `pytest tests/test_herdr_real_server_leak.py tests/test_issue42_skill_blocks.py -v`
+   - 결과: **`40 passed, 1 skipped in 1.52s`**.
+4. **Negative Regression 검증**:
+   - Base(`dc886ec`): `test_issue63_same_cwd_ids.py` 12개 실패 확인.
+   - `ede9c62` 대비: `test_id_order_real_probe_against_mock_herdr_fails_closed`가 `protocol_mismatch`에서 `assert 0 == 1`로 실패하고 `HEAD`에서 통과함을 확인.
+   - `7cac6f6`(`HEAD~1`) 대비: `1614af5`의 동일 세션 이름 고아 마커 검증(`assert wait_same() == 1`)이 `HEAD~1`에서 `assert 0 == 1`로 실패하고 `1614af5`(`HEAD`)에서 통과함을 확인.
+
+---
+
+## 4. 발견 사항
+
+- 차단 결함(P0/P1) 및 비차단 결함(P2) 없음.
+
+[VERDICT: PASS]

.agents/reports/reviewer-grok-01/report-7b602181.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261025T023502Z-d6f876",
+  "base_sha": "0461a632eb667c7988fd33be92e9a4b36151f22a",
+  "head_sha": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "tree_sha": "15a72c9a1933c64018a2f2d9aa9707348905bb4d",
+  "review_commit": "bb496fde785133ad1dbec288aa7431766efb6eb5",
+  "reviewer": "reviewer-grok-01",
+  "job_id": "7b602181",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-25T03:40:44Z"
+}

.agents/reports/reviewer-grok-01/report-7b602181.md

@@ -0,0 +1,86 @@
+# Review 7b602181 — PR #70 / Issue #66, Mac pass
+
+PASS. Head `bb496fd` calls herdr with `sanitize_herdr_agent_name` of the session. `agent get`, `agent read`, `agent prompt`, and `agent wait` all use that name. The agent kind is still taken from `--agent` or from the original session suffix. Log lines keep the original session name. A name that is already legal is left as it is.
+
+Reviewed only the snapshot `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261025T023502Z-d6f876/1` (`loop-20261025T023502Z-d6f876`). Head `bb496fde785133ad1dbec288aa7431766efb6eb5`, tree `15a72c9a1933c64018a2f2d9aa9707348905bb4d`. Base `0461a632eb667c7988fd33be92e9a4b36151f22a` (main, v4.10.0) is an ancestor and is the control-plane HEAD. One commit, 3 files, +150/−5. No uncommitted changes. `git diff --check` is clean. Snapshot porcelain is empty and the snapshot has no `.mam`. Control-plane porcelain is empty. No product file was edited. The source worktree `mam-wt-pr70` was not run.
+
+The commit is `bb496fd` `fix(stall_watch): call herdr with the sanitized agent name`.
+
+Host tools: control-plane venv Python 3.9.6, `/bin/bash` 3.2.57(1)-release. The real agent databases were not opened.
+
+## Herdr name and kind
+
+`HerdrSource` keeps the original string on `self.target` and stores `self.name = sanitize_herdr_agent_name(target)` (`stall_watch.py:158-165`). `agent_get`, `agent read`, and `agent prompt` pass `self.name` (`182-184`, `206`, `210-211`). `StallWatch.herdr_name` is the same function of `args.target` (`229`). `watcher.wait_once` receives that name, and `args.herdr_session` stays the server (`331`).
+
+`build_argv` puts a non-default server on `herdr --session` and the target on `agent wait <target>` (`loop/watcher.py:131-139`). `HerdrSource._herdr` does the same split (`stall_watch.py:167-168`). The server argument is not run through the agent-name sanitizer.
+
+`resolve_agent` still reads `--agent`, then its first hyphen piece, then `agent_of_row` on the original session name (`stall_watch.py:140-146`, `registry.py:30-49`, `base.py:326-330`). Measured on this snapshot: `resolve_agent("", "mam-wt-issue-66-very-long-creator-codex")` is `codex`. The sanitized form `mam-wt-issue-66-very-lo-d55dfa83` does not end in `-codex`, and `resolve_agent` of that string with an empty `--agent` is `None`. `resolve_agent("claude", <39-character name>)` is `claude`. `resolve_agent("claude-code", ...)` is `claude`. The long-name test passes `--agent ""` and still nudges, which is the codex input-box path (`test_issue66_stall_watch_sanitized_name.py:111-127`).
+
+No remaining herdr agent-name argument in `stall_watch.py` uses `self.target` or `args.target`. Those strings appear in the log lines (`373`, `397`, `406`). Pane calls use the pane id (`186-193`).
+
+`_notify` publishes `progress` with the detail it is given (`237-244`). Idle publishes `stalled:idle` (`408`). Blocked publishes `stalled:blocked` plus the dialog line (`374`). Those details contain the stall reason. The original session name is in the matching log line (`agent <original> idle for`, `agent <original> is blocked`). The tests lock both (`79-85`, `101-106`).
+
+## Sanitizer
+
+`sanitize_herdr_agent_name` (`lib_py/agents/sanitize.py:4-30`) lowercases, replaces characters outside `[a-z0-9_-]` with `-`, prefixes `x-` when the result does not start with a letter, and when the result is longer than 32 characters keeps 23 characters, a hyphen, and 8 hex digits of SHA-1.
+
+The function `lib.sh` runs is the definition at `lib.sh:293-316` (an earlier copy at `36-61` is replaced when the file is sourced; every call site is below 316). It was executed on its own, without sourcing `lib.sh`. On this Mac, with `shasum` present, it returned the same strings as the Python function:
+
+| input | result |
+| --- | --- |
+| `creator-claude-fix-issue-99-long-branch` (39) | `creator-claude-fix-issu-e6fc18ae` |
+| `Creator-Claude-T` | `creator-claude-t` |
+| `creator-claude-t` | `creator-claude-t` |
+| `mam-wt-issue-66-very-long-creator-codex` | `mam-wt-issue-66-very-lo-d55dfa83` |
+| empty | `agent` |
+| `1abc` | `x-1abc` |
+| `A B` | `a-b` |
+| 33 `x` | `xxxxxxxxxxxxxxxxxxxxxxx-60bbb3c8` |
+| `planner-agy` | `planner-agy` |
+
+The earlier shell copy produced the same three long, codex, and `1abc` results. Python 3.9.6 imports `stall_watch`. The new code adds no `match` statement and no evaluated `X | Y` annotation. The module already has `from __future__ import annotations`.
+
+## Mock
+
+`strict_agent_names` is off unless a test sets it. `_match_agent` then keeps the previous comparison (`conftest.py:470-476`). With the flag set, the mock answers only an exact registered name. `agent get` and `agent read` then print `agent_not_found` JSON (`1057-1062`, `1152-1158`). `agent wait` and `agent prompt` already did (`1089-1096`, `1187-1194`). Existing tests that leave the flag unset keep the old not-found text on get and read.
+
+## Tests
+
+`test_the_names_change_and_the_strict_mock_answers_only_the_sanitized_one` registers the sanitized name and checks that get, read, wait, and prompt reject the original name with `agent_not_found` and accept the sanitized name (`51-65`).
+
+`test_an_idle_agent_is_nudged_through_the_sanitized_name` covers the 39-character name, `Creator-Claude-T`, and `creator-claude-t`. Every get, read, prompt, and wait uses the sanitized name, one nudge is sent, the progress detail is `stalled:idle`, and the log contains `agent <original> idle for` (`68-85`).
+
+`test_a_blocked_agent_is_reported_with_the_original_name` uses the sanitized name on the herdr calls, sends no prompt, publishes `stalled:blocked` plus the dialog line, and logs `agent <original> is blocked` (`90-106`).
+
+`test_the_kind_of_a_long_name_comes_from_its_original_suffix` passes an empty `--agent`. The sanitized name does not end in `-codex`. The watcher still nudges and every herdr call uses the sanitized name (`111-127`).
+
+## Results
+
+Pytest used the control-plane venv, `PYTHONDONTWRITEBYTECODE=1`, `-p no:cacheprovider`, and `--basetemp` `/tmp/mam7b6-7b602181-pytest` (head) and `/tmp/mam7b6-7b602181-base-pytest` (base). Neither path contains `mam-review` or `shim`. Inherited `HERDR_*`, `MAM_*`, `MQTT_*`, `SKS_*`, `DELEGATE_JOB_LOGS_DIR`, `HOME_DIR`, `CLAUDE_*`, `CODEX_HOME`, `PYTHONPATH`, `WORKSPACE_ROOT`, `MAM_ENV_FILE`, `MAM_JOBS_DIR`, `AGENT_SESSIONS_YAML`, the four `XDG_*` homes, and `AGENT_PYTHON_BIN` were dropped.
+
+Head, cwd the snapshot: `tests/test_issue66_stall_watch_sanitized_name.py`, `test_issue30_stall_watch.py`, `test_issue30_stall_watch_stop.py`. **66 passed, 1 skipped** in 356.72 s. Exit 0. The log closed at 2026-10-25 12:31:50. The skip is `test_s6_the_heartbeat_timer_is_not_a_background_child`, marked for Linux because it reads `/proc` (`test_issue30_stall_watch.py:39-40`, `340-341`). That test is outside this delta. The seven Issue #66 tests passed inside the 66.
+
+Base, this turn: a throwaway `git clone --shared` checked out at `0461a632eb667c7988fd33be92e9a4b36151f22a`, with only `tests/test_issue66_stall_watch_sanitized_name.py` copied from head. Base `stall_watch.py` has no `sanitize_herdr` use. **6 failed, 1 passed** in 37.05 s. Exit 1. The pass is `test_an_idle_agent_is_nudged_through_the_sanitized_name[creator-claude-t]`, the name that needs no conversion. The six failures are the long name, the uppercase name, and the long codex name. On that tree get, read, and wait are invoked with `creator-claude-fix-issue-99-long-branch` and `Creator-Claude-T`. The snapshot was not checked out. Snapshot porcelain stayed empty.
+
+## Issue #17 timing failure
+
+`tests/test_issue17_item4_decisions.py::test_c_finalize_ends_with_an_unreaped_wrapper[broker_unavailable-3-0]` is outside this diff. The test sends `SIGTERM` to a delegate wrapper during finalize and expects exit `-15` within 4.5 seconds, an empty call log, and an unchanged job record (`583-601`). The diff names only `stall_watch.py`, `tests/conftest.py`, and the new Issue #66 test. It does not touch the wrapper, `finalize_unfinished`, or that test. A miss on that timing assertion is a cleanup race in the wrapper test, separate from the herdr agent name.
+
+## Blocking defects
+
+None.
+
+## Non-blocking
+
+- `lib.sh` contains two copies of `_sanitize_herdr_agent_name` (`36-61` and `293-316`). Sourcing the file uses the second. On this host, with `shasum` present, both copies matched Python for the names checked above. The first copy's missing-hasher path truncates to 32 characters with no hash. This commit does not change `lib.sh`.
+- Progress details stay `stalled:idle` and `stalled:blocked <dialog>`. They carry the stall reason. The original session name is on the log line beside that notice.
+
+## Host check
+
+No process has a first command token of `opencode` or a path ending in `/opencode`. `lsof` on `~/.local/share/opencode/opencode.db` exited 1. That database was not opened. Its mtime is 1792641027 and its size is 36712448. `opencode.log` is absent. `~/.config/opencode/service.json` mtime is 1792246838 and its size is 64. `~/.local/state/opencode/service.json` is absent. The herdr config mtime is 1784456394. `~/.local/state/mam` mtime is 1792846843. `~/.local/state/mam/id-order` is a directory, mtime 1792846886. These stats match the check taken before the suite.
+
+Five herdr processes were running immediately before the suite. After the suite log closed at 2026-10-25 12:31:50, the 12:31:59 check still found five. One pid from the before-set was gone. The replacement is `/opt/homebrew/bin/herdr` with `--session multi-agent-mux`, elapsed time about 15 seconds at 12:31:59, so it started near 12:31:44, during the last seconds of the suite. No herdr command line contained the review basetemp, the snapshot path, or `d6f876`. This review did not start or stop a herdr server.
+
+After this report file was written, the same check was repeated at 2026-10-25 12:33:25. Snapshot porcelain is empty and the snapshot has no `.mam`. Control-plane porcelain is empty at `0461a632eb667c7988fd33be92e9a4b36151f22a`. No process has a first command token of `opencode` or a path ending in `/opencode`, and `lsof` still reports no database holder. The database mtime is still 1792641027 and its size is still 36712448. `opencode.log` is still absent. The config service file mtime is still 1792246838. The state service file is still absent. The herdr config mtime is still 1784456394. `~/.local/state/mam` mtime is still 1792846843, and `id-order` is still the same directory (mtime 1792846886). Five herdr processes were present. The pid set differs from the 12:31:59 set by one homebrew herdr process whose arguments include `--session multi-agent-mux`; its elapsed time was about 41 seconds, so that process had turned over again. No herdr command line contained the review basetemp, the snapshot path, or `d6f876`. This review did not start or stop it.
+
+[VERDICT: PASS]

.agents/reports/reviewer-grok-01/report-a43bca93.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261027T201245Z-63c71b",
+  "base_sha": "1d63e882bc1c46e9af8484647d5091b296d8fa3f",
+  "head_sha": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "tree_sha": "fbadb24de60ccdae684b23e2e0a41cdf23ab81eb",
+  "review_commit": "ec7f5c4e57286fb3c4238b8220f39094f4640391",
+  "reviewer": "reviewer-grok-01",
+  "job_id": "a43bca93",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-27T21:06:27Z"
+}

.agents/reports/reviewer-grok-01/report-a43bca93.md

@@ -0,0 +1,71 @@
+# PR #75 (Issue #72) 리뷰 — 라운드 5
+
+검증 경로 `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261027T201245Z-63c71b/1` 만 봤다. HEAD `ec7f5c4e57286fb3c4238b8220f39094f4640391`, tree `fbadb24de60ccdae684b23e2e0a41cdf23ab81eb`, base `1d63e882bc1c46e9af8484647d5091b296d8fa3f` (HEAD 의 부모이자 조상), porcelain 0. 스냅샷에는 `.venv` 가 없다. 테스트 뒤에도 HEAD·tree·porcelain 은 같았다. 제어 평면의 입장 잠금과 업데이트 표식은 없었고, 체크아웃 모니터 pid 3714 (`reconcile.sh --subscribe --idle-timeout 0`) 는 그대로였다.
+
+이번 커밋은 `ec7f5c4` 하나다. `1d63e88..ec7f5c4` 는 `lib.sh` 와 `tests/test_issue72_update.py` 이고 `git diff --check` 는 깨끗했다. diff 에 `mapfile`, `declare -A`, `local -n`, `[[ -v`, `sed -i`, `stat -c`, `readlink -f`, `date -d` 는 없다. `setsid(1)` 도 호출하지 않는다.
+
+## 확인한 것
+
+R2. `MAM_DELEGATION_PY=0` 의 기동도 호출자 프로세스 그룹 밖에 둔다.
+
+- `lib.sh:2297-2310`. 이미 떠 있는 모니터가 없을 때만, 호출자가 이미 `-m` 이었는지 기억하고 `set -m` 으로 잡은 뒤 `nohup bash <reconcile.sh> --subscribe --idle-timeout 0` 을 백그라운드로 띄운다. stdin 은 `/dev/null`, 로그는 append, 그 다음 호출자의 `-m` 을 되돌린다. 중복 확인(`lib.sh:2291` `_monitor_pids`)과 `MAM_NO_SUBSCRIBER_DAEMON=1` (`lib.sh:2295-2296`) 은 그 앞에 그대로다. PID 출력은 `lib.sh:2314-2315` 이다.
+- 이 함수를 쓰는 재시작은 세 곳이다. 설치 성공은 `post_update.sh:41`, 정지 시간 초과는 `update.sh:106`, 롤백과 상태 기록 실패는 `install_phase.sh:64` 의 `bash -c` 가 복구된 트리의 `start_watchdog` 를 부른다. `lib.sh:2567-2573` 에서 `MAM_DELEGATION_PY=0` 이면 레거시, 아니면 Python `start_new_session` 이다.
+- tty 없이 `set -euo pipefail` 인 bash 3.2 에서 `set -m` 으로 띄운 `sleep` 의 PGID 는 그 PID 와 같고 부모 PGID 와 달랐다. 부모가 끝난 뒤에도 그 프로세스는 남아 있었고, 확인 뒤에 그 PID 만 종료했다.
+- `test_issue72_update.py:697-725`. `MAM_DELEGATION_PY` 0 과 1, 설치 성공·TERM 무시 후 KILL·롤백 여섯 조합에서 새 모니터의 PGID 가 이 테스트 프로세스 그룹과 다른지 본다. `box.update` 는 프로세스 그룹을 바꾸지 않으므로 그 그룹이 호출자 그룹이다.
+
+정리. 테스트는 패턴으로 죽이지 않는다.
+
+- `tests/test_issue72_update.py` 에 `pkill` 과 `killall` 은 없다.
+- `test_issue72_update.py:221-240`. 이 테스트가 `helper` 로 띄운 프로세스 그룹만 `os.killpg` 하고, 이 임시 작업공간의 `reconcile.sh --subscribe` 명령줄과 그 `pgrep -P` 자식만 `os.kill` 한다. 그 다음 10초 동안 그 작업공간 경로를 명령줄에 가진 프로세스가 남아 있으면 실패한다 (`_processes_naming`, `184-193`). 읽는 용도이고, 다른 작업공간의 모니터는 경로가 다르므로 대상이 아니다.
+
+이전 라운드에서 맞던 중복 방지, opt-out, PID 보고, 로그 append 는 이 diff 가 그 순서를 바꾸지 않았다. Python 쪽 세션 분리는 `tests/test_issue5_phase1_delegation.py:697-699` 가 그대로 본다.
+
+## 실행한 테스트
+
+작업 디렉터리는 스냅샷이다. 인터프리터는 제어 평면 `/Users/godopu16/PuKi/laa/canary_projects/multi-agent-mux/.venv/bin/python` (Python 3.9.6). `--basetemp=/tmp/mam-i72-a43bca93`.
+
+```
+env -u HERDR_SOCKET_PATH -u HERDR_PANE_ID -u HERDR_TAB_ID -u HERDR_WORKSPACE_ID \
+  -u HERDR_SESSION_NAME -u HERDR_SESSION -u WORKSPACE_ROOT -u MAM_ENV_FILE \
+  -u MAM_JOBS_DIR -u DELEGATE_JOB_LOGS_DIR \
+  PYTHONDONTWRITEBYTECODE=1 \
+  /Users/godopu16/PuKi/laa/canary_projects/multi-agent-mux/.venv/bin/python -m pytest \
+  -p no:cacheprovider --basetemp=/tmp/mam-i72-a43bca93 \
+  tests/test_issue72_admission.py tests/test_issue72_attach_hints.py \
+  tests/test_issue72_installer.py tests/test_issue72_resume_monitor.py \
+  tests/test_issue72_update.py tests/test_issue8_update_state.py \
+  tests/test_deploy_layout.py tests/test_issue42_skill_blocks.py \
+  tests/test_issue26_ints.py tests/test_version_consistency.py \
+  tests/test_issue5_phase1_delegation.py \
+  tests/test_issue19_subscriber_daemon_lifecycle.py \
+  -q --tb=line
+```
+
+결과: **314 passed, 1 skipped**, 888.47s, 종료 코드 0. PGID 여섯 조합과 watchdog 수명 주기가 이 안에 들어 있다.
+
+건너뛴 한 건은 `tests/test_issue42_skill_blocks.py:266` (`.claude/skills` 가 이 체크아웃에 없음). 같은 파일만 `--basetemp=/tmp/mam-i72-a43bca93-skip -rs` 로 다시 돌리면 39 passed, 1 skipped, 0.07s 이다.
+
+basetemp 경로를 가진 프로세스는 종료 뒤에 남아 있지 않았다.
+
+## 발견 사항
+
+차단: 없음. 설계를 다시 잡아야 하는 결함도 없다.
+
+비차단:
+
+- 레거시 경로는 새 프로세스 그룹이다 (`set -m`). Python 경로는 `start_new_session` 으로 새 세션이다. 이번 라운드가 요구한 것은 호출자 프로세스 그룹에서 벗어나는 것이고, 둘 다 그렇게 한다. `nohup` 이 SIGHUP 을 무시하는 것은 그대로다.
+- `lib.sh:2310`. 모니터를 띄운 뒤 원래 디렉터리로 돌아가지 못하면 함수는 1 을 반환한다. 그 시점에는 이미 `set +m` 이 실행됐고 데몬은 떠 있다. 호출자는 PID 를 받지 못한다. 디렉터리가 사라진 경우에만 해당한다.
+- 앞 라운드의 비차단 항목(롤백 재시작이 `mam_monitor_started` 를 호출하지 않음, SIGKILL 자식 PID 재확인, 이미 떠 있는 resume 의 잠금 범위, 호출자의 실행 중 잡이 둘일 때)은 이 커밋이 건드리지 않았고 이번 수정 범위 밖이다.
+
+전용 테스트가 없는 조건:
+
+| 조건 | 코드 | 테스트 |
+| --- | --- | --- |
+| 레거시 모니터가 호출자와 다른 세션인지 | `lib.sh:2306-2308` 은 프로세스 그룹만 분리 | 이번 테스트는 PGID 만 비교 (`test_issue72_update.py:724`) |
+| 앞 라운드 표의 세 조건 | 변경 없음 | 이번 범위 밖 |
+
+## 사용자 확인 필요
+
+없음.
+
+[VERDICT: PASS]

.agents/reports/reviewer-grok-01/report-dee00bc0.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261023T035928Z-2ccc02",
+  "base_sha": "dc886ecd6b38c01032a55a2d1c230c73362ae630",
+  "head_sha": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "tree_sha": "f1af6fdd548ee5d6f6b81e2202833edfaca98188",
+  "review_commit": "1614af5b673d7519d3a38f63e3636055592b4f14",
+  "reviewer": "reviewer-grok-01",
+  "job_id": "dee00bc0",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-23T05:16:58Z"
+}

.agents/reports/reviewer-grok-01/report-dee00bc0.md

@@ -0,0 +1,102 @@
+# Review dee00bc0 — PR #69 / Issue #63, fourth Mac pass
+
+PASS. Head `1614af5` keeps a dead-owner marker whose session name is the caller's own until herdr returns a parsed agent list that omits that name, or until the row is registered for the attempt. A live owner of that name is kept. An empty session name is still dropped. A failed lookup, `server_not_running` included, and a wait cap of 0 leave the marker in place. A normal create or resume whose `has-session` already sees the name returns before this wait. A retry whose probe says the session is gone returns on that probe.
+
+Reviewed only the snapshot `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261023T035928Z-2ccc02/1` (`loop-20261023T035928Z-2ccc02`). Head `1614af5b673d7519d3a38f63e3636055592b4f14`, tree `f1af6fdd548ee5d6f6b81e2202833edfaca98188`. Base `dc886ecd6b38c01032a55a2d1c230c73362ae630` (main, v4.9.9) is an ancestor and is the control-plane HEAD. Thirteen commits, 14 files, +2234/−102. Against the previous review head `7cac6f6` the delta is 2 files, +42/−16: `.agents/skills/lib_py/agents/id_order.py` and `tests/test_issue63_same_cwd_ids.py`. No uncommitted changes. `git diff --check` is clean. Snapshot porcelain is empty and the snapshot has no `.mam`. Control-plane porcelain is empty. No product file was edited. The source worktree `mam-wt-pr69` was not run.
+
+The new commit is `1614af5` `fix(id_order): a dead-owner marker on the caller's own session follows the orphan rules`. It closes the residual recorded on `7cac6f6`, where a dead owner of the waiter's own session name was dropped before herdr was asked. `8f64174` and `7cac6f6` stay underneath it. HEAD still prunes only on an authoritative gone, still treats `server_not_running` as unknown, and still asks herdr nothing at cap 0. The same-name case now uses that branch.
+
+Host tools: control-plane venv Python 3.9.6, sqlite 3.51.0, `/bin/bash` 3.2.57(1)-release. The real agent databases were not opened.
+
+## Same-name orphan
+
+`_read_and_prune_markers` no longer takes the waiter session name (`id_order.py:183-186`, call at `308-309`). A dead owner's marker (`id_order.py:217-229`):
+
+- A missing owner pid, or an owner pid equal to this waiter, drops the marker (`219-220`).
+- A live owner keeps it, including a live attempt on the caller's session (`221-222`).
+- An empty session name drops it (`223-224`).
+- A row registered for the attempt drops it without a probe. Registered means status `running` and `herdr_session_epoch` greater than the marker's `prev_epoch` (`177-180`, `225-226`).
+- Otherwise the probe runs. `drop` is true only when it returns false. True and `None` keep the marker, and `_orphan` is `"alive"` or `"unknown"` (`227-229`). A marker left by an earlier attempt on the caller's own session name takes this path.
+
+`herdr_session_state` (`id_order.py:58-86`) is unchanged in this commit. False is only a successful, parsed `_herdr agent list` whose agents omit the session name and `sanitize_herdr_agent_name` of that name (`84-86`). A non-zero exit, a timeout, an `OSError`, or JSON that has no `result.agents` list returns `None` (`75-83`). `timeout <= 0` returns `None` before any subprocess (`64-65`). Measured on this snapshot: `herdr_session_state(..., 0)` and `herdr_session_state(..., -1)` are both `None`. `wait_s({})` is 600, `wait_s` of `"0"` is 0, and `wait_s` of `"abc"` is 600 (`36-41`).
+
+The child environment sets `MAM_NO_AUTOSTART=1` and `HERDR_SESSION_NAME` to the marker's server, or `default` when that field is empty (`67`). The shim skips autostart when that variable is `1` (`lib.sh:203-208`). `bounded_probe` passes the time left on the deadline (`287-291`). The call sits inside `fcntl.flock(LOCK_EX)`. macOS has no `flock(1)`. The ordering tests passed with `fcntl`.
+
+`blockers` includes a kept marker of the caller's own session when that row is absent (`133-147`). The waiter then holds until the marker is pruned or the cap expires (`325-347`). On cap expiry the message uses the last definite answer from this wait (`333-344`). An unknown orphan at cap 0 adds `MAM_ID_ORDER_WAIT_S=0 leaves no time to ask herdr`.
+
+## Ordinary create, resume, and retry
+
+Create calls `has-session` and exits 3 when the name is already present (`create_session.sh:168-170`). The id-order wait is later (`287`). Resume sets `HERDR_ALIVE` from `has-session` (`resume_session.sh:125-128`) and, when the session is alive, updates the row and exits (`158-169`) before the wait (`243`). The mock `has-session` exits 0 when the agent name is in its state (`conftest.py:1345-1355`). A retry that herdr still lists under that name therefore stops at `has-session` and does not enter the 600-second cap.
+
+The wait itself returns 0 on the first lock hold when `blockers` is empty (`310-323`). That is a create or resume with no live same-cwd marker and no running row that still lacks an id. The default 600 is the cap for a marker that stays, and the function does not sleep it out on an empty blocker list.
+
+When the caller has already passed `has-session` and a dead-owner marker of the same name remains:
+
+- A parsed list that omits the name removes the marker and returns 0 on that pass (`228-229`, then `310-323`). The real-probe test does this with cap 2 on the marker's own session name and checks that the replacement marker's owner pid is the waiter (`test_issue63_same_cwd_ids.py:1315-1317`).
+- A parsed list that contains the name keeps the dead owner's pid and returns 1 inside the cap (`1290-1292`). The unit test at `wait_s_val=0` with an injected `pane_state` prints `its herdr session is alive` and `kill-session -t same-agy` (`1133-1140`).
+- `None`, which covers a failed lookup, `server_not_running`, and a real cap of 0, keeps the marker and the waiter uses the cap. That is the same rule `7cac6f6` already applies to every other orphan. The real-probe cap-0 assertion is on the other session name in the same test (`1306-1310`); the same-name branch calls the same `herdr_session_state`.
+
+The head suite finished in 1301.73 s, in line with the previous pass on `7cac6f6` (1263.90 s). A common create or resume that now slept out 600 seconds would have stretched that run. It did not.
+
+## Tests for this commit
+
+`no_herdr_probe` (`test_issue63_same_cwd_ids.py:32-36`) makes an in-process `herdr_session_state` return false unless the test passes `pane_state`. The shell tests start a child, and that child runs the real function.
+
+`test_id_order_dead_owner_marker_blocks_while_its_unregistered_herdr_session_is_alive` (`1047`) still covers another session's orphan: alive keeps and prints the kill line, unknown keeps, a registered running row drops the marker with an empty probe list, and a false answer admits the next session. The same-name block (`1120-1148`) keeps a live owner's pid, keeps a dead owner's pid while the injected probe returns true or `None`, and on false replaces the owner pid with the waiter's pid.
+
+`test_id_order_real_probe_against_mock_herdr_fails_closed` (`1250`) sources the sandbox `lib.sh` and calls `mam_id_order_wait`. A listed agent returns 1 for both the other session name and the marker's own name, and the dead owner's pid stays (`1287-1292`). `protocol_mismatch` and `server_not_running` return 1 with `herdr could not tell whether its session is gone` (`1294-1304`). The mock exits 1 for `force_error_code` before the subcommand (`conftest.py:486-488`). Cap 0 returns 1 with `MAM_ID_ORDER_WAIT_S=0 leaves no time to ask herdr` and keeps the marker (`1306-1310`). An unlisted agent returns 0 for the other name, and a following wait on the marker's own name returns 0 with a new owner pid (`1312-1317`). The mock `agent list` prints `{"result": {"agents": [...]}}` with each agent's `name` (`conftest.py:794-806`). A parsed list that contains the name is what prints `its herdr session is alive`.
+
+`mock_herdr` prepends its bin (`conftest.py:1411`). These shell tests passed in the head run below. The unlisted own-name case returning 0, and the listed own-name case returning 1, are the evidence the probe reached the mock.
+
+`test_id_order_create_waits_for_orphan_herdr_session_of_a_killed_create` (`1160`) and `test_id_order_herdr_probes_stay_within_the_wait_cap` (`1207`) are unchanged by this commit and passed. The create test uses a different session name and cap 3. The cap test's cap 0 finishes with every budget `<= 0` and both markers still on disk.
+
+## Rest of base..head
+
+The twelve commits through `7cac6f6` are the tree reviewed in job 737239ab. This commit does not change `session_ids.py`, `lib.sh`, the stop, resume, or create scripts, or the skill exit tables. `session_ids.py` still uses `#40`'s `capture` and `claimed_elsewhere`. Stop still decides the id before kill. Resume still resolves the id and refuses a claimed id before spawn. `git grep` for `capture_conversation_id` and `CAPTURE_ID`, excluding `.agents/reports` and `IMPROVEMENTS.md`, finds no caller. The diff names no loop or job-tree file, so the author's one-off `tests/test_issue34_job_tree.py::test_t5b_a_*[False]` failure is outside this change. `/bin/bash -n` accepts the snapshot `lib.sh`. Python 3.9.6 imports `id_order`. The annotations sit behind `from __future__ import annotations`.
+
+## Results
+
+Pytest used the control-plane venv, `PYTHONDONTWRITEBYTECODE=1`, `-p no:cacheprovider`, and `--basetemp` `/tmp/mamdee-dee00bc0-pytest` (head) and `/tmp/mamdee-dee00bc0-base-pytest` (base). Neither path contains `mam-review` or `shim`. Inherited `HERDR_*`, `MAM_*`, `MQTT_*`, `SKS_*`, `DELEGATE_JOB_LOGS_DIR`, `HOME_DIR`, `CLAUDE_*`, `CODEX_HOME`, `PYTHONPATH`, `WORKSPACE_ROOT`, `MAM_ENV_FILE`, `MAM_JOBS_DIR`, `AGENT_SESSIONS_YAML`, the four `XDG_*` homes, and `AGENT_PYTHON_BIN` were dropped.
+
+Head, cwd the snapshot: `tests/test_issue63_same_cwd_ids.py`, `test_issue40_auto_pin.py`, `test_issue64_ro_connect.py`, `test_issue10_13_purge.py`, `test_issue31_purge_residual.py`, `test_issue42_skill_blocks.py`, `test_tier1_unit.py`, `test_tier2_component.py`, `test_uuid_target.py`, `test_issue24_resume_dialogs.py`. **359 passed, 1 skipped** in 1301.73 s. Exit 0. The log closed at 2026-10-23 14:09:03. `.claude/skills` is absent in this snapshot, and `test_claude_skills_link_resolves_to_agents_skills` skips in that case (`test_issue42_skill_blocks.py:266`). That file is outside this delta. The same-name assertions are inside the two existing probe tests, so the pass count matches the previous head.
+
+Base, this turn: a throwaway `git clone --shared` checked out at `dc886ecd6b38c01032a55a2d1c230c73362ae630`, with only `tests/test_issue63_same_cwd_ids.py` copied from head. `id_order.py` is absent there. **27 errors** in 0.11 s. Exit 1. Each error is `ImportError: cannot import name 'id_order' from 'lib_py.agents'` at setup of `no_herdr_probe`, including `test_id_order_dead_owner_marker_blocks_while_its_unregistered_herdr_session_is_alive`, `test_id_order_real_probe_against_mock_herdr_fails_closed`, and `test_c4`. The snapshot was not checked out. Snapshot porcelain stayed empty.
+
+The behavioral base result for this same base, on the test file from before that fixture imported `id_order`, remains the one recorded by job ba3eeb7b: **22 failed, 1 passed** in 181.15 s. The pass was `test_c4_pinned_post_discovered_and_preassigned_agents_unchanged`. On that run the second stop row received A's id, purge printed `purged:`, the unpinned resume carried A's id, and cap 0 still spawned. Those tests passed on this head inside the 359.
+
+1. Stop order A→B and B→A, including herdr already dead, records only a verified own id. `test_c1_stop_same_cwd_agy_sessions_records_only_verified_owner` passed on head.
+2. Purge of B leaves A's files. `test_c2_purge_never_deletes_another_rows_conversation` passed on head.
+3. Resume of an unpinned B stays off A's conversation, and the already-running branch keeps the epoch. `test_c3_resume_unpinned_second_agy_row_starts_fresh_and_running_branch_keeps_epoch` passed on head.
+4. A row that already has an own id, and claude/grok, stay on the previous path. `test_c4_pinned_post_discovered_and_preassigned_agents_unchanged` passed on head, along with `test_issue40_auto_pin.py`, `test_issue64_ro_connect.py`, and `test_issue10_13_purge.py`.
+5. A same-cwd create waits while another post-discovered row of the same agent has no id. `test_c6_create_waits_or_refuses_while_same_cwd_post_discovered_row_has_no_id` passed on head. The orphan tests cover a dead owner, including one on the caller's own session name, whose herdr session is alive, unknown, or gone.
+6. Resume refuses before spawn when the resolved id belongs to another row. `test_c7_resume_refuses_when_recorded_id_is_claimed_by_another_row` passed on head.
+
+## Blocking defects
+
+None.
+
+## Non-blocking
+
+- While herdr keeps failing the lookup, the orphan marker stays, and every later create or resume that reaches the wait — a retry of the marker's own session name included — waits out `MAM_ID_ORDER_WAIT_S` again (`id_order.py:75-76`, `227-229`). The wait is bounded. Create and resume still return at `has-session` when that command already sees the name (`create_session.sh:168-170`, `resume_session.sh:158-169`). The cap message names `herdr kill-session`.
+- The probe holds the id-order lock until it returns. The budget is the time left on the deadline, and at most 30 seconds (`id_order.py:73`, `287-309`).
+- An empty `herdr_server` is probed on the `default` server (`id_order.py:67`). Create and resume export `HERDR_SESSION_NAME` before they write a new marker (`create_session.sh:185-186`, `resume_session.sh:111-114`). The cap line prints `default` for an empty server and leaves the server and session unquoted (`id_order.py:335-344`).
+- A successful agent list that is briefly empty while a pane is still registering would prune the marker. The tests cover a list that already contains the name, and a list that does not.
+- One remaining same-type row with herdr dead still uses `find_workspace_uuid` (`session_ids.py:274-275`).
+- A running row with an empty own id and a missing pane pid blocks until the cap (`id_order.py:128-131`). The unit test asserts that return of 1 (`test_issue63_same_cwd_ids.py:1150-1154`).
+- A marker whose owner pid has been reused by an unrelated live process stays until that process exits (`id_order.py:221-222`).
+- With herdr alive, a recorded id that fails revalidation is still returned (`session_ids.py:240-241`).
+- An unparsable `MAM_ID_ORDER_WAIT_S` becomes 600 (`id_order.py:36-41`).
+- `stop_session.sh:220` uses `eval "$(mam_session_ids stop ...)" || true`. A normal decision returns 0. A crashed helper leaves the captured fields empty and the stop continues.
+- `--no-onboard` waits out the cap. Presence-lock id discovery is not in this PR. Both are the deferrals named by the issue and the PR body.
+- `resolve_session_id.sh:4-5` still describes an empty line and exit 0. The script calls `mam_session_ids` under `set -euo pipefail` (line 10). The resume skill exit table documents exit 1 when another row claims the id.
+- Read-only connect residuals from #64 (immutable race, `mode=ro` sidecar rewrite, purge DELETE staying read-write) are outside this diff. `_ro_connect` is unchanged.
+
+## Host check
+
+No process has a first command token of `opencode` or a path ending in `/opencode`. `lsof` on `~/.local/share/opencode/opencode.db` exited 1. That database was not opened. Its mtime is 1792641027 and its size is 36712448. `opencode.log` is absent. `~/.config/opencode/service.json` mtime is 1792246838 and its size is 64. `~/.local/state/opencode/service.json` is absent. The herdr config mtime is 1784456394. `~/.local/state/mam` mtime is 1791810241. `~/.local/state/mam/id-order` is absent. These stats match the check taken before the suite.
+
+Eight herdr processes were running immediately before the suite. After the suite log closed at 2026-10-23 14:09:03, the 14:09:37 check found seven. Two pids from the before-set were gone: one `/opt/homebrew/bin/herdr` whose session argument was `multi-agent-mux` (about 40 seconds old at suite start) and one whose session argument was `mam-pylecturenotes` (about 3 seconds old at suite start). The new process is `/opt/homebrew/bin/herdr` with `--session multi-agent-mux`, elapsed time about 54 seconds at 14:09:37, so it started near 14:08:43, during the last half-minute of the suite. No herdr command line contained the review basetemp, the snapshot path, or the test session names `probe-ws` and `orphan-ws`. This review did not start or stop a herdr server.
+
+After this report file was written, the same check was repeated at 2026-10-23 14:11:38. Snapshot porcelain is empty and the snapshot has no `.mam`. Control-plane porcelain is empty at `dc886ecd6b38c01032a55a2d1c230c73362ae630`. No process has a first command token of `opencode` or a path ending in `/opencode`, and `lsof` still reports no database holder. The database mtime is still 1792641027 and its size is still 36712448. `opencode.log` is still absent. The config service file mtime is still 1792246838. The state service file is still absent. The herdr config mtime is still 1784456394. `~/.local/state/mam` mtime is still 1791810241, and `id-order` is still absent. Seven herdr processes were present. The pid set differs from the 14:09:37 set by one homebrew herdr process whose arguments include `--session multi-agent-mux`; its elapsed time was about 54 seconds, so that process had turned over again. No herdr command line contained the review basetemp, the snapshot path, or `probe-ws` or `orphan-ws`. This review did not start or stop it.
+
+[VERDICT: PASS]

.agents/reports/reviewer-grok-01/report-f02af611.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261020T133532Z-a1684a",
+  "base_sha": "ff8b381520ae04e80c73a9e18bfad73d47e853c9",
+  "head_sha": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "tree_sha": "0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a",
+  "review_commit": "feccfd5e0356c8acf0438bc68bce7ea36ce2588e",
+  "reviewer": "reviewer-grok-01",
+  "job_id": "f02af611",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-20T15:51:16Z"
+}

.agents/reports/reviewer-grok-01/report-f02af611.md

@@ -0,0 +1,80 @@
+# Review f02af611 — Issue #40
+
+PASS. Commit `feccfd5` pins a post-discovered session id when the receiving side has verified `completed`, and agy no longer records another workspace's conversation. The four completion conditions fail on base `ff8b381` and pass on this head. Related tests: 76 passed.
+
+Reviewed only the snapshot `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261020T133532Z-a1684a/1` (`loop-20261020T133532Z-a1684a`). Head `feccfd5e0356c8acf0438bc68bce7ea36ce2588e`, tree `0f0f33cc22f5e492a0ddfccb6bac5be888c10d1a`, base `ff8b381520ae04e80c73a9e18bfad73d47e853c9` is an ancestor and is the control-plane HEAD. One commit, 19 files, +1128/−338. `git diff --check` is clean. Snapshot porcelain is empty and the snapshot has no `.mam`. Control-plane porcelain is empty. No product file was edited. The source worktree was not run.
+
+The commit is `feccfd5` `fix(agents): pin post-discovered session ids on a verified completed; agy never takes another workspace's or session's conversation (Issue #40)`.
+
+Host tools: control-plane venv Python 3.9.6, sqlite 3.51.0, bash 3.2.57(1)-release. `bash -n` accepts `lib.sh`, `create_session.sh`, `reconcile.sh`, and `multi-agent-mux-delegate-job`. Linux was not executed here. The real agent databases were not opened.
+
+## When a pin happens
+
+Class A adapters (`agy`, `opencode`, `codex`, `hermes`) keep `id_lifecycle` `post_discovered`. Class B (`claude`, `grok`) return `pre_assigned`. The default on `BaseAgentAdapter` is `post_discovered`.
+
+`capture_active_session_id` is read-only. The default (`base.py:384-400`) keeps a `discover()` candidate only when `verify_session_uuid` accepts it and no other row already records that id. Zero verified candidates is `no-candidate`. Two or more is `ambiguous`. Agy replaces that method (`agy.py:129`): `last_conversations.json` may propose the one id mapped to this cwd, `verify_session_uuid` must accept it, and a holder of that conversation's presence lock or database must be the row's pane process or a descendant (`agy.py:202-231`). A cache entry alone is not enough, because one cwd has one cache slot.
+
+The write lives in `lib_py.agents.autopin`, which the agent process does not run. `handle_completed` runs only for a local job record whose status is `completed`. Remote transport, a `remote:` session, and a human job return `skipped`. A dispatch token passed by the caller must match the record. The pin key is `job_id:dispatch_token:attempt_id`, stored in `<registry>/<job>/autopin.json` under a flock on `autopin.lock`. A second call with the same key returns the stored result and does not capture again.
+
+Callers:
+
+- `delegate_autopin_completed` in `lib.sh` (the shell only launches `python -m lib_py.agents.autopin`).
+- The delegate-job wrapper, after `finalize_unfinished`, when `job_status` is `completed` (`multi-agent-mux-delegate-job` beside the audit-log echo).
+- `create_session.sh`, in the onboarding `completed` branch.
+- `LoopRunner.wait_for_job`, immediately after it observes `completed` (`runner.py:676-679`, `_autopin` at `:690`). This call does not pass `--expect-dispatch-token`; the marker key still uses the token stored on the record.
+
+`pin_row` (`autopin.py:73-78`) sets the agent's own key, `session_id_source` `discovered`, `session_id_verified` true, and `last_visible_status` `pinned`, then the caller replaces that status with the resume dry-run result. A captured id is pinned when `verify_tui_viewport` returns 0, and also when it returns something other than 1 (the old degraded pin). Return 1 leaves the id empty and records `viewport-mismatch`. Any other capture status except `pre-assigned`, `already-set`, and `skipped` writes `last_visible_status` `autopin <status> (job <id>): <reason>` and still stores the marker, so that job is not tried again. The function's exit status stays 0 (`|| true` in the shell helper; `main` returns 0).
+
+Reconcile drift C for agy, hermes, opencode, and codex calls the same `autopin.capture` (`reconcile.sh:795`) and the same `pin_row` (`:728`). Ambiguous capture sets `ambiguous: N candidates` and does not pin. A single `captured` id still goes through `verify_tui_viewport`. Claude drift C is unchanged and still scans its own jsonl directory.
+
+## What changed, and what stayed
+
+| File | Why |
+| --- | --- |
+| `lib_py/agents/base.py` | `PRE_ASSIGNED`, `POST_DISCOVERED`, `capture_result`, default `id_lifecycle`, default `capture_active_session_id` |
+| `lib_py/agents/autopin.py` | Receiving-side capture, pin, dedup marker, CLI |
+| `adapters/agy.py` | Discover mode rejects an id the cache maps to another cwd, and rejects a sibling id even when the cache names this cwd. Capture adds the pane-owner check |
+| `adapters/claude.py`, `adapters/grok.py` | `id_lifecycle` is `pre_assigned` |
+| `lib.sh`, delegate-job wrapper, `create_session.sh` | Call the handler after a verified `completed` |
+| `loop/runner.py` | Same handler after `wait_for_job` sees `completed` |
+| `reconcile.sh` | Class A drift C is the shared capture. The agy `*.db` glob and the hermes, opencode, and codex SQL in the shell are gone |
+| create and monitor `SKILL.md`, `docs/NEW_AGENT_INTEGRATION_GUIDE.md` | The new adapter fields and who writes the registry |
+| `tests/test_issue40_auto_pin.py` | The four completion conditions |
+| `test_issue64_ro_connect.py`, `test_issue60_linux_fixes.py`, `test_issue60_opencode_v2.py`, `test_tier1_unit.py`, `test_tier2_component.py` | Assertions that drift C now goes through `autopin.capture`, and the Issue #64 cross-workspace assert is now false |
+
+`publish_event.py` and `publisher.py` have no autopin and no session-registry write. `test_call_sites_and_publisher_boundary` checks that and passed. Purge deletes stay read-write. Status still opens hermes, opencode, and codex with `_ro_connect`. Adapter queries still use `_ro_connect`. `reconcile.sh` contains neither `_ro_connect` nor `sqlite3.connect`; the adapters open the databases. `VERSIONS.md` is unchanged.
+
+Stop's own capture path is unchanged. A new pin from this handler records `session_id_source: discovered` and `session_id_verified: true`. An id that stop recorded earlier can still disagree with those two fields. The issue comment asked for that stop cleanup only if it stayed small, and it is outside this diff.
+
+`_pin_and_verify_resume` now records source and verified for claude too, because it calls `pin_row`. Claude's candidate scan is the same as before.
+
+## Completion conditions
+
+Pytest used the control-plane venv, `PYTHONDONTWRITEBYTECODE=1`, `-p no:cacheprovider`, and `--basetemp` `/tmp/mamf02-f02af611-pybase` (head) and `/tmp/mamf02-f02af611-pybase-base` (base). Neither path contains `mam-review` or `shim`. Inherited `HERDR_*`, `MAM_*`, `MQTT_*`, `SKS_*`, `DELEGATE_JOB_LOGS_DIR`, `HOME_DIR`, `CLAUDE_PROJECT_DIR`, `CLAUDE_CONFIG_DIR`, `CLAUDE_CODE_TMPDIR`, `CODEX_HOME`, `PYTHONPATH`, `WORKSPACE_ROOT`, `MAM_ENV_FILE`, `MAM_JOBS_DIR`, `AGENT_SESSIONS_YAML`, and the four `XDG_*` homes were dropped. Sandbox tests point `HOME` and `HOME_DIR` at the temporary tree.
+
+Head, cwd the snapshot: `tests/test_issue40_auto_pin.py`, `tests/test_issue64_ro_connect.py`, `test_status_and_reconcile_open_the_database_read_only`, `test_status_and_reconcile_read_session_v2`, `test_opencode_shell_and_scripts_integration`, `test_comp_opencode_create_and_reconcile_and_stop`, and `test_comp_codex_create_and_reconcile_and_stop`. 76 passed in 130.63 s. Exit 0. No skip and no error.
+
+Base proof is a throwaway `git clone --shared` checked out at `ff8b381`, with `tests/test_issue40_auto_pin.py` and `tests/test_issue64_ro_connect.py` taken from `feccfd5`. The snapshot was not checked out. Result: 15 failed, 13 errors in 19.80 s. Exit 1.
+
+1. Another workspace's agy id is not recorded. On base, `test_agy_verify_rejects_id_cached_for_another_workspace` got `True` from `verify_session_uuid`. `test_reconcile_does_not_pin_another_workspaces_agy_conversation` found workspace B's id written on A's row. `test_unpinned_agy_reconcile_leaves_other_workspace_clean_db_without_sidecars` still asserted the old `True`. On head all three pass, and the directory stays the one database file.
+2. The first completed job pins the session's own id with `MAM_NO_SUBSCRIBER_DAEMON=1`. On base, `test_completed_onboarding_pins_agy_without_daemon` errors because `_holder_pids` is absent, the three `test_completed_first_job_pins_opencode_codex_hermes` cases cannot import `autopin`, `test_reconcile_pins_agy_owned_by_the_pane` leaves the id empty, `delegate_autopin_completed` is not a command, and `test_create_onboard_pins_without_daemon` finds no `autopin.json`. On head, agy pins the id the cache maps to A's cwd when A's pane holds it, and opencode, codex, and hermes pin the session in their own workspace. The lib.sh helper, the loop recovery, and `create --onboard` do the same.
+3. One pin per job, and ambiguity pins nothing. On base, `test_wrapper_and_loop_recovery_pin_once` and `test_ambiguous_candidates_leave_reason_without_pin` cannot import `autopin`, and `test_loop_recovery_pins_when_the_wrapper_did_not` leaves the id empty. On head the wrapper call and the loop call share one marker, the yaml mtime does not move the second time, and two opencode sessions in one cwd leave `autopin ambiguous (job amb): 2 candidates` with the own id empty.
+4. Pre-assigned rows and rows that already have an id stay as they were. On base, `test_preassigned_and_existing_ids_are_untouched` errors in the owner fixture, and `test_call_sites_and_publisher_boundary` does not find the wrapper call. On head the claude, grok, already-pinned agy, and already-set opencode rows compare equal before and after, and remote, human, error, and still-running jobs return `skipped` without a marker. A stale `--expect-dispatch-token` also writes no marker.
+
+## Remaining risk
+
+Agy will not pin from the cache unless `lsof` shows the presence lock or the database held by the pane process or a descendant. No holder, a missing `lsof`, or a pane pid of 0 or 1 is `unverifiable-owner`. That result is stored on the job marker, so the loop recovery does not try the same job again. Reconcile does not read the marker and will try on a later cycle. A worktree creator has no monitor, so a completed turn whose files are already closed stays unpinned until a later completed job. The tests stub `lsof` and `ps`; a live agy process was not used.
+
+`claimed_elsewhere` treats every own id on every other row, including a stopped row, as taken. The old drift C list was the live same-cwd siblings. An id that still sits on a stopped row is not given to a new row.
+
+Codex drift C now uses `discover()` plus `verify_artifact`, so the epoch check is the rollout file mtime. The removed SQL compared the state-db timestamp. Hermes and opencode still filter cwd and epoch in `discover()`, and opencode still requires `parent_id IS NULL`.
+
+The resume dry-run and the viewport check run while `atomic_dump_yaml` holds the registry lock, which is the same arrangement the old `_pin_and_verify_resume` used. `resume_session.sh --dry-run` returns before `update_yaml_resumed.sh` when herdr already has the session. `verify_tui_viewport` reads the pane and does not take that lock.
+
+A `mode=ro` open that already has both sidecars can still rewrite `-shm` bytes, and the immutable open can miss a wal created after the exists check. Those are the Issue #64 residuals. This commit removes the reconcile path that opened every agy database.
+
+The user's background service stayed up. Its pid is 23630 and the command is `/Users/godopu16/.opencode/bin/opencode serve --service`. The real database mtime is 1792420196 and its size is 36712448. `~/.config/opencode/service.json` mtime is 1792246838. `~/.local/state/opencode/service.json` mtime is 1792365227. The real `opencode.log` mtime is 1792420391 and its size is 2699345. The herdr config mtime is 1784456394.
+
+After the report, snapshot porcelain is still empty, the snapshot still has no `.mam`, and control-plane porcelain is still empty at `ff8b381520ae04e80c73a9e18bfad73d47e853c9`. The herdr config mtime is still 1784456394. The opencode database mtime is still 1792420196 and its size is still 36712448. The opencode log mtime is still 1792420391 and its size is still 2699345. Service pid 23630 is still `opencode serve --service`.
+
+[VERDICT: PASS]

.agents/reports/reviewer-grok-01/report-fd90992c.identity.json

@@ -0,0 +1,14 @@
+{
+  "loop_id": "loop-20261026T133440Z-c8961b",
+  "base_sha": "29cc4fd90478936f15387a7665e2c95d13a3f14c",
+  "head_sha": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "tree_sha": "98d57bdc60920238c115ece90c90cc694f2744bc",
+  "review_commit": "5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26",
+  "reviewer": "reviewer-grok-01",
+  "job_id": "fd90992c",
+  "verdict": "PASS",
+  "transport": "herdr",
+  "evidence": "review-tree",
+  "isolation": "worktree",
+  "verified_at": "2026-10-26T17:32:11Z"
+}

.agents/reports/reviewer-grok-01/report-fd90992c.md

@@ -0,0 +1,102 @@
+# Review: PR #73 / Issue #71 (macOS, snapshot 2)
+
+Job fd90992c. Reviewer only. Checks ran on the review snapshot. The source worktree and the control-plane checkout were not edited.
+
+## Identity
+
+- Snapshot: `/var/folders/q_/68sxgw3j073dgjg8wl9s08vw0000gn/T/mam-review/loop-20261026T133440Z-c8961b/2`
+- Loop: `loop-20261026T133440Z-c8961b`
+- Base: `29cc4fd90478936f15387a7665e2c95d13a3f14c` (main, v4.10.1)
+- Head: `5f6065344f800c2c5ad6f802e95e9e8ff5cc7b26`
+- Tree: `98d57bdc60920238c115ece90c90cc694f2744bc`
+- 14 commits, base is an ancestor, porcelain 0, no `.mam` in the snapshot, `git diff --check` clean
+- Diff: 28 files, +953/−176
+- Host: `/usr/bin/python3` 3.9.6, bash 3.2.57(1)-release, sqlite 3.51.0, `LANG=en_US.UTF-8`
+
+`tests/test_issue66_stall_watch_sanitized_name.py` has an empty diff against `29cc4fd`. Commit `0fc162e` is an ancestor. The diff file list has no `multi-agent-mux-update` skill. `MAM_VERSION` stays `4.10.1`.
+
+Issue #71, the "범위 정리" comment (items 1–10), and PR #73 were read. The registry entry point is documented for #72 and is not wired to an update skill.
+
+## What was checked
+
+### attach_command
+
+`lib_py/agents/sanitize.py:34` builds `herdr --session <server> agent attach <sanitized name>`. An empty server becomes `default`, and both the server and the name go through `shlex.quote`, so `default` is written as `--session default` and a server that needs quotes is quoted.
+
+The three writers call it:
+
+- create, `create_session.sh:566`
+- resume, `update_yaml_resumed.sh:151` (new row) and `:161` (existing row whose server is set)
+- reconcile, `reconcile.sh:676`, on the row whose note is `auto-registered by monitor`
+
+The shim `agent attach` (`lib.sh:605-613`) resolves the target with `_resolve_herdr_target` and runs `_real_herdr agent attach "$tgt" "$@"`. Options after the name stay in `"$@"`.
+
+### Removed fields and the stop hints
+
+`kill_command` and `start_command` remain only as fields the migration pops and as assertions that they are absent. `status.sh` no longer emits `start_command`. The shim still has the fake `new-session` and `kill-session` verbs, which create, stop, and reconcile use. `kill-session` sanitizes the name and exits 1 when that fails.
+
+Create exit 43 (`create_session.sh:364`) and `id_order.py:330` and `:344` tell the user to run `stop_session.sh --session <name> --herdr-session <server>`. The row-less tests below run that script.
+
+### Row-less stop
+
+`stop_rowless` (`stop_session.sh:123`) runs only when the row lookup exits 7 (`:189`). A strict read failure exits 1 before that (`:170`). `--purge-conversation` with no row exits 1 (`:124`). A cwd outside this workspace exits 5. A session that survives `kill-session` exits 6. Those codes match `multi-agent-mux-stop/SKILL.md:58-66`.
+
+Server order: `--herdr-session`, else a non-default `HERDR_SESSION_NAME` captured before resolve (`:109`, `:128`), else the workspace server. `lib.sh` stamps an unset name as `default`, and the row-less path treats that stamp as unset.
+
+The cwd check realpaths both sides and accepts the workspace itself or a child (`root + os.sep`). That rejects a sibling prefix and a symlink whose target is outside the workspace, and it treats a trailing slash as the same directory. `/tmp` and `/private/tmp` are the same path on this Mac. The row-less tests compare registry bytes before and after and passed.
+
+`load_state_json strict` (`lib.sh:1594`) is the bash reader. A missing `state` or `sessions` table raises in strict mode and the function exits 1. The argument-free call still prints `{}`.
+
+### One name rule
+
+`lib.sh` has one `_sanitize_herdr_agent_name` (`:44`). `00000000` and `lower()[:32]` are absent. The shim receives the function through `declare -f` (`:181`).
+
+The function was extracted with `sed` and run under `/bin/bash` 3.2 without sourcing `lib.sh`. Against `sanitize_herdr_agent_name` there were 0 mismatches under `LC_ALL=C` and `LC_ALL=en_US.UTF-8` for empty, `Upper-Case`, `-n`, `-e`, a 33-character name, the long branch name, `İstanbul-creator-claude`, a newline, `a\nb`, café, the kelvin sign, Japanese, Korean `한글`, and `A B`. Korean is two characters; the non-ASCII path uses `python3` `str.lower()` and the same regex, so the replacement follows characters, and the result matched Python.
+
+With `PATH` limited to `tr`, `sed`, `awk`, and `cut`, the long name exits 1 with `no shasum, sha1sum, openssl or python3 to hash it` and prints no name. `한글` exits 1 with `not ASCII`.
+
+`/usr/bin/python3` is 3.9.6. The diff adds no `mapfile`, `${var,,}`, `declare -A`, `match`, or `tomllib`. A throwaway SQLite database opened with `PRAGMA journal_mode=WAL`, written, and closed still had a `-wal` (0 bytes) and a `-shm` (32768 bytes).
+
+### Registry format 2
+
+`atomic_yaml.py:118-137` migrates under the lock, after `BEGIN IMMEDIATE` and before the caller mutation, when `stored_version < 2`. Migration sets `force_yaml`, so YAML is rewritten even if the mutation changes no session. If the DB is already current and the YAML copy is still older, the next write rewrites the YAML. `migrate` (`registry_format.py:50-66`) updates every named row, including stopped and terminated, and sets `registry_format` to 2. A version already greater than 2 is not less than `CURRENT`, so the writer does not call `migrate`.
+
+The entry point `python -m lib_py.registry_format --yaml <path>` prints `registry-format: <from> -> <to>, rows changed: <n>` and exits 0, or `registry-format: error:` and a nonzero status when neither file exists. The only `yaml.safe_dump` under `.agents/skills` is the writer. Readers (`lib_py/state.py` and the argument-free bash loader) do not migrate.
+
+### stall_watch and the edited tests
+
+`stall_watch.py:229` computes `self.herdr_name` once and passes it into `HerdrSource`. The issue #66 test file is unchanged and is in the passing run.
+
+Edited assertions keep the old intent: pane-lock uses `session_id_source` (create sets it at `create_session.sh:579`) to tell a create row from a monitor row; the worktree test looks for a leaked `WORKSPACE_ROOT=` in `attach_command`; tier 2 checks the new attach string and the absence of the two dropped keys; tier 1 and tier 3 plant a row with no agent so "cannot infer agent" still exits 2. `skill_code_blocks.json` moved with the docs, and `test_issue42_skill_blocks.py` expects stop exits `0` through `6`. That file passed aside from the skills-link skip.
+
+S11 (`test_issue23_24_startup_path.py:306-310`) compares the shim with `0fc162e`. That commit is in this checkout, so the comparison ran as part of the passing file. If the object is missing, the test calls `pytest.skip` with a message that names the commit. That skip is intentional: the PR says a squash would drop `0fc162e`, and it asks for a merge commit.
+
+The reconcile tests plant a mock pane (`test_issue71_herdr_names.py:127-140`) and require one new row. They passed, so registration ran.
+
+## Tests
+
+Pytest was `PYTHONDONTWRITEBYTECODE=1` with the control-plane venv, `-p no:cacheprovider`, and `--basetemp=/tmp/mamfd9-fd90992c-pytest`. Inherited `HERDR_*`, `MAM_*`, `MQTT_*`, `WORKSPACE_ROOT`, `DELEGATE_JOB_LOGS_DIR`, `PYTHONPATH`, the four `XDG_*` homes, and `AGENT_SESSIONS_YAML` were unset. `AGENT_PYTHON_BIN` pointed at the control-plane venv. The snapshot was the working directory and was not checked out.
+
+Head, the files named in the brief plus `test_b19_headless_reconcile_fixes.py`, `test_b4_session_created.py`, and `test_issue30_stall_watch.py`: **546 passed, 2 skipped** in 1458.68s, exit 0. `tests/test_issue71_herdr_names.py` collects 70 tests and they are in that pass. The two skips, confirmed with `-rs` on those two tests, are `test_claude_skills_link_resolves_to_agents_skills` (`.claude/skills` absent, `test_issue42_skill_blocks.py:266`) and `test_s6_the_heartbeat_timer_is_not_a_background_child` (Linux `/proc`, `test_issue30_stall_watch.py:340`).
+
+Base: a `--shared` clone at `/tmp/mamfd9-fd90992c-base`, detached at `29cc4fd`, with only this test file copied in. Same pytest flags, `--basetemp=/tmp/mamfd9-fd90992c-base-pytest`. **68 failed, 2 passed** in 98.42s, exit 1. The two passes are `test_the_names_need_converting_and_the_plain_one_does_not` and the plain-name `test_wrapper_attach_calls_herdr_with_the_herdr_name`. The long and uppercase wrapper cases failed.
+
+## Residuals (non-blocking)
+
+- Readers stay read-only. An old registry keeps a format-1 `attach_command` until the next writer, or until `python -m lib_py.registry_format` runs. The module docstring describes that window. The explicit entry point is left for #72.
+- `VERSIONS.md` is unchanged. The release sentence from the scope comment is in the PR body.
+- `migrate` skips a row with no `name` (`registry_format.py:57-58`), so that row can keep `kill_command` after the format key becomes 2.
+- `lib_py/state.py` `load_state_json` still returns `{}` on a read error. Stop uses the bash strict reader.
+- The SKILL.md exit-0 cell describes a stop or an already-stopped no-op. The pre-flight paragraph and the script header also describe the row-less close as exit 0. The pre-flight sentence names `--herdr-session` and `HERDR_SESSION_NAME`; the code also uses the workspace server when both are absent.
+- A direct call to `migrate` on a format already greater than 2 would write the key back to 2. The writer does not call it in that case.
+- S11 skips only when `0fc162e` cannot be resolved. A squash merge would take that path. The PR forbids squash for that reason.
+
+## Host
+
+Checked before the suite at 2026-10-27 01:43:34 and again after it at 02:08:54. No process whose first command token was `opencode`. `lsof` of the user opencode database returned exit 1. Database mtime 1792641027, size 36712448. `opencode.log` absent. Config `service.json` mtime 1792246838, size 64. State `service.json` absent. Herdr config mtime 1784456394, size 19. `~/.local/state/mam` directory mtime 1792846843, size 128. `id-order` is a directory, mtime 1792846886, size 128; its entries were not listed. The same two herdr servers were present before and after: pid 11655 (`/opt/homebrew/bin/herdr server`) and pid 69309 (`/opt/homebrew/bin/herdr --session multi-agent-mux server`). No server argv contained the scratch prefix, the snapshot path, or the loop id. The database was not opened.
+
+After the suite the snapshot was still head `5f60653`, tree `98d57bdc`, porcelain 0, no `.mam`. The control-plane checkout was still `29cc4fd`, porcelain 0.
+
+Rechecked after this report was written, at 2026-10-27 02:09:37. The snapshot was still head `5f60653`, tree `98d57bdc`, porcelain 0, with no `.mam`. The control plane was still `29cc4fd`, porcelain 0. Opencode first-token count 0, database `lsof` exit 1, and the database, log, service files, herdr config, `~/.local/state/mam`, and `id-order` mtimes and sizes were the same as the pre-suite reading. Herdr servers were still pid 11655 and pid 69309. No server argv contained the scratch prefix, the snapshot path, or the loop id.
+
+[VERDICT: PASS]

.agents/skills/lib.sh

@@ -29,33 +29,54 @@ export WORKSPACE_ROOT
 # Framework semantic version. Single runtime source of truth; kept in lockstep
 # with VERSIONS.md and the 8 SKILL.md frontmatters by tests/test_version_consistency.py.
 # NOTE: unlike other MAM_* variables this one is intentionally NOT env-overridable.
-MAM_VERSION="4.9.8"
+MAM_VERSION="4.12.0"
 export MAM_VERSION
 AGENT_SESSIONS_YAML="${AGENT_SESSIONS_YAML:-$WORKSPACE_ROOT/.mam/agent-sessions.yaml}"
 
+# The one bash form of lib_py.agents.sanitize.sanitize_herdr_agent_name
+# (Issue #71). The herdr shim gets this same definition: _init_herdr_isolation
+# writes it in with `declare -f`. A long name needs its SHA-1 suffix; with no
+# shasum, sha1sum, openssl or python3 to make it, this fails (stderr, nonzero)
+# rather than return a name herdr never registered. A name that is not ASCII
+# is lowercased and replaced by python3 (tr/sed differ from str.lower() there),
+# and fails the same way without it. Line breaks become '-' before sed (which
+# works line by line) and before $(...) could drop a trailing one.
 _sanitize_herdr_agent_name() {
   local n="$1"
   if [ -z "$n" ]; then
     printf 'agent\n'
     return 0
   fi
-  local s
+  local s=""
-  s=$(echo "$n" | tr '[:upper:]' '[:lower:]' | sed -E 's/[^a-z0-9_-]/-/g')
+  if [ -z "$(printf '%s' "$n" | LC_ALL=C tr -d '\000-\177')" ]; then
+    s=$(printf '%s' "$n" | tr '\n' '-' | tr '[:upper:]' '[:lower:]' | sed -E 's/[^a-z0-9_-]/-/g')
+  elif command -v python3 >/dev/null 2>&1; then
+    s=$(python3 -c 'import re,sys; sys.stdout.write(re.sub(r"[^a-z0-9_-]", "-", sys.argv[1].lower()))' "$n") || s=""
+  fi
+  if [ -z "$s" ]; then
+    echo "ERROR: cannot make the herdr name of '$n': it is not ASCII and there is no python3 to convert it" >&2
+    return 1
+  fi
   if [[ ! "$s" =~ ^[a-z] ]]; then s="x-$s"; fi
   if [ "${#s}" -gt 32 ]; then
     local h=""
     if command -v shasum >/dev/null 2>&1; then
       h=$(printf '%s' "$s" | shasum 2>/dev/null | awk '{print $1}' | cut -c 1-8)
-    elif command -v sha1sum >/dev/null 2>&1; then
+    fi
+    if [ "${#h}" -ne 8 ] && command -v sha1sum >/dev/null 2>&1; then
       h=$(printf '%s' "$s" | sha1sum 2>/dev/null | awk '{print $1}' | cut -c 1-8)
-    elif command -v openssl >/dev/null 2>&1; then
+    fi
+    if [ "${#h}" -ne 8 ] && command -v openssl >/dev/null 2>&1; then
       h=$(printf '%s' "$s" | openssl sha1 2>/dev/null | awk '{print $NF}' | cut -c 1-8)
     fi
-    if [ -n "$h" ]; then
+    if [ "${#h}" -ne 8 ] && command -v python3 >/dev/null 2>&1; then
-      s="${s:0:23}-$h"
+      h=$(python3 -c 'import hashlib,sys; print(hashlib.sha1(sys.argv[1].encode("utf-8")).hexdigest()[:8])' "$s" 2>/dev/null || true)
-    else
-      s="${s:0:32}"
     fi
+    if [ "${#h}" -ne 8 ]; then
+      echo "ERROR: cannot make the herdr name of '$n': no shasum, sha1sum, openssl or python3 to hash it" >&2
+      return 1
+    fi
+    s="${s:0:23}-${h}"
   fi
   printf '%s\n' "$s"
 }
@@ -155,8 +176,10 @@ _init_herdr_isolation() {
   fi
 
   local tmp_file="$wrapper_dir/herdr.tmp.$$.$RANDOM"
-  cat <<'EOF' > "$tmp_file"
+  {
-#!/usr/bin/env bash
+  printf '%s\n' '#!/usr/bin/env bash'
+  declare -f _sanitize_herdr_agent_name
+  cat <<'EOF'
 # Herdr-to-Herdr translation shim wrapper
 set -euo pipefail
 
@@ -290,31 +313,6 @@ _real_herdr() {
   fi
 }
 
-_sanitize_herdr_agent_name() {
-  local n="$1"
-  if [ -z "$n" ]; then
-    printf 'agent\n'
-    return 0
-  fi
-  local s
-  s=$(echo "$n" | tr '[:upper:]' '[:lower:]' | sed -E 's/[^a-z0-9_-]/-/g')
-  if [[ ! "$s" =~ ^[a-z] ]]; then s="x-$s"; fi
-  if [ "${#s}" -gt 32 ]; then
-    local h=""
-    if command -v shasum >/dev/null 2>&1; then
-      h=$(printf '%s' "$s" | shasum 2>/dev/null | awk '{print $1}' | cut -c 1-8)
-    elif command -v sha1sum >/dev/null 2>&1; then
-      h=$(printf '%s' "$s" | sha1sum 2>/dev/null | awk '{print $1}' | cut -c 1-8)
-    elif command -v openssl >/dev/null 2>&1; then
-      h=$(printf '%s' "$s" | openssl sha1 2>/dev/null | awk '{print $NF}' | cut -c 1-8)
-    else
-      h=$(python3 -c "import hashlib,sys; print(hashlib.sha1(sys.argv[1].encode()).hexdigest()[:8])" "$s" 2>/dev/null || echo "00000000")
-    fi
-    s="${s:0:23}-${h}"
-  fi
-  printf '%s\n' "${s:0:32}"
-}
-
 # ---------------------------------------------------------------------------
 # Workspace scoping (ISSUE-3).
 #
@@ -441,7 +439,7 @@ sys.exit(1)
     [ -n "$resolved_ws" ] && target_ws="$resolved_ws"
   fi
   local sat pid=""
-  sat=$(_sanitize_herdr_agent_name "$target")
+  sat=$(_sanitize_herdr_agent_name "$target") || return 1
 
   local cand get_ws
   if [ "$#" -ge 2 ]; then
@@ -534,7 +532,7 @@ case "$cmd" in
     _resolve_herdr_target() {
       local raw="$1"
       local sat
-      sat=$(_sanitize_herdr_agent_name "$raw")
+      sat=$(_sanitize_herdr_agent_name "$raw") || return 1
       if [ -n "$(_herdr_agent_get_scoped "$sat" 2>/dev/null || true)" ]; then
         echo "$sat"
         return 0
@@ -604,6 +602,15 @@ sys.exit(1)
         exit 1
       fi
       _real_herdr agent read "$tgt" "$@"
+    elif [ "$sub" = "attach" ] && [ $# -ge 1 ]; then
+      t="$1"
+      shift
+      tgt=$(_resolve_herdr_target "$t" || true)
+      if [ -z "$tgt" ]; then
+        echo "Error: no in-scope herdr agent for '$t'" >&2
+        exit 1
+      fi
+      _real_herdr agent attach "$tgt" "$@"
     else
       _real_herdr agent "$sub" "$@"
     fi
@@ -623,19 +630,15 @@ sys.exit(1)
         *) shift ;;
       esac
     done
-    if [ -n "$(_herdr_agent_get_scoped "$(_sanitize_herdr_agent_name "$sess")" 2>/dev/null || true)" ] \
+    ssess=$(_sanitize_herdr_agent_name "$sess") || exit 1
+    if [ -n "$(_herdr_agent_get_scoped "$ssess" 2>/dev/null || true)" ] \
        || [ -n "$(_herdr_agent_get_scoped "$sess" 2>/dev/null || true)" ]; then
       exit 0
     fi
-    if _real_herdr agent list 2>/dev/null | TARGET_NAME="$sess" TARGET_WS="$(_herdr_ws_scope)" python3 -c '
+    if _real_herdr agent list 2>/dev/null | TARGET_NAME="$sess" TARGET_SAN="$ssess" TARGET_WS="$(_herdr_ws_scope)" python3 -c '
 import sys, json, os
-try:
-    sys.path.insert(0, os.path.abspath(".agents/skills"))
-    from lib_py.agents.sanitize import sanitize_herdr_agent_name
-except Exception:
-    sanitize_herdr_agent_name = lambda s: s.lower()[:32] if s else "agent"
 tn = os.environ.get("TARGET_NAME", "")
-stn = sanitize_herdr_agent_name(tn)
+stn = os.environ.get("TARGET_SAN", "")
 tws = os.environ.get("TARGET_WS", "")
 try:
     d = json.loads(sys.stdin.read())
@@ -682,6 +685,7 @@ sys.exit(1)
         *) run_cmd="$1"; shift ;;
       esac
     done
+    agent_name=$(_sanitize_herdr_agent_name "$name") || exit 1
     if [ -z "$run_cmd" ]; then
       run_cmd="${SHELL:-/bin/bash}"
     fi
@@ -896,7 +900,6 @@ except Exception:
     res=""
     success=0
     backoffs=(0.5 1 2)
-    agent_name=$(_sanitize_herdr_agent_name "$name")
     for i in $(seq 0 2); do
       if [ -n "$final_cmd" ]; then
         res=$(eval "_real_herdr agent start \"$agent_name\" --kind \"$kind\" --pane \"$target_pane\" -- $final_cmd" 2>&1 || true)
@@ -967,7 +970,7 @@ except Exception:
     # `herdr session list`), not individual agent panes — `session stop/delete
     # "$sess"` with a MAM session name always fails (silently, via `|| true`).
     # Resolve the real pane_id via `agent get` and close just that pane instead.
-    agent_target=$(_sanitize_herdr_agent_name "$sess")
+    agent_target=$(_sanitize_herdr_agent_name "$sess") || exit 1
     pane_id=$(_resolve_herdr_pane_id "$sess" 2>/dev/null || true)
     if [ -n "$pane_id" ]; then
       _real_herdr pane close "$pane_id" >/dev/null 2>&1 || true
@@ -1002,7 +1005,7 @@ except Exception:
     # there is no top-level "pane" key, and no "pid" field at all (only
     # "pane_id", herdr's own wN:pN identifier). The real OS pid requires a
     # second call to `pane process-info --pane <pane_id>`.
-    agent_target=$(_sanitize_herdr_agent_name "$sess")
+    agent_target=$(_sanitize_herdr_agent_name "$sess") || exit 1
     info=$(_real_herdr agent get "$agent_target" 2>/dev/null || _real_herdr agent get "$sess" 2>/dev/null || true)
     pane_id="" cwd="" cmd=""
     if [ -n "$info" ]; then
@@ -1072,7 +1075,7 @@ except Exception:
         *) shift ;;
       esac
     done
-    agent_target=$(_sanitize_herdr_agent_name "$sess")
+    agent_target=$(_sanitize_herdr_agent_name "$sess") || exit 1
     pane_id=$(_resolve_herdr_pane_id "$sess" 2>/dev/null || true)
     if [ -n "$pane_id" ]; then
       _real_herdr pane read "$pane_id" --source visible --lines 100 2>/dev/null \
@@ -1103,7 +1106,7 @@ except Exception:
     fi
     # `pane send-keys` requires a real pane_id ("wN:pN"), not an agent name —
     # resolve it via `agent get` first (agent-level commands accept names).
-    agent_target=$(_sanitize_herdr_agent_name "$sess")
+    agent_target=$(_sanitize_herdr_agent_name "$sess") || exit 1
     pane_id=$(_resolve_herdr_pane_id "$sess" 2>/dev/null || true)
     if [ -n "$pane_id" ]; then
       _real_herdr pane send-keys "$pane_id" "$key" >/dev/null 2>&1 || true
@@ -1387,6 +1390,7 @@ for name, pid in rows:
     ;;
 esac
 EOF
+  } > "$tmp_file"
   chmod +x "$tmp_file" 2>/dev/null || true
   mv -f "$tmp_file" "$wrapper_dir/herdr" 2>/dev/null || rm -f "$tmp_file" 2>/dev/null || true
   if [[ ":$PATH:" != *":$wrapper_dir:"* ]]; then
@@ -1587,10 +1591,14 @@ herdr() {
 # ---------------------------------------------------------------------------
 # NOTE: Retained as small inline PYEOF block (39 lines) per Plan Rev.2 (Job 98393a97).
 # Small blocks have minimal overhead and high local cohesion; extraction into lib_py is reserved for large blocks (>200 lines).
+# `load_state_json strict` (Issue #71) fails (stderr, exit 1) when the YAML or
+# DB cannot be read, a DB table missing included, instead of printing {} - for
+# a caller that acts on a session being absent.
 load_state_json() {
-  env_python "$AGENT_SESSIONS_YAML" <<'PYEOF'
+  env_python "$AGENT_SESSIONS_YAML" "MAM_STATE_READ=${1:-}" <<'PYEOF'
 import os, sys, sqlite3, json, yaml
 yaml_path = os.environ['YAML_PATH']
+strict = os.environ.get('MAM_STATE_READ') == 'strict'
 db_path = os.path.splitext(yaml_path)[0] + '.db'
 d = {}
 db_sessions = []
@@ -1603,20 +1611,24 @@ try:
             if row:
                 d = json.loads(row[0])
         except sqlite3.OperationalError:
-            pass
+            if strict:
+                raise
         try:
             cursor = conn.execute('SELECT data FROM sessions')
             for r in cursor.fetchall():
                 db_sessions.append(json.loads(r[0]))
             d['herdr_sessions'] = db_sessions
         except sqlite3.OperationalError:
-            pass
+            if strict:
+                raise
         conn.close()
     elif os.path.exists(yaml_path):
         with open(yaml_path) as f:
             d = yaml.safe_load(f) or {}
-except Exception:
+except Exception as e:
-    pass
+    if strict:
+        print('ERROR: cannot read the registry %s: %s' % (yaml_path, e), file=sys.stderr)
+        sys.exit(1)
 # Clean lone surrogates to prevent UnicodeEncodeError on stdout print
 def clean_surrogates(obj):
     if isinstance(obj, str):
@@ -1659,6 +1671,22 @@ print(resolved)
 "
 }
 
+# session_attach_command <session_name> [server]
+#
+# Issue #72: the attach hint a script prints - the session row's
+# attach_command, else the one lib_py.agents.sanitize.attach_command builds for
+# <server> (default: `default`).
+session_attach_command() {
+  MAM_STATE_JSON="$(load_state_json)" SESSION_NAME="$1" ATTACH_SERVER="${2:-default}" python3 -c "
+import os, json
+from lib_py.agents.sanitize import attach_command
+name = os.environ['SESSION_NAME']
+d = json.loads(os.environ.get('MAM_STATE_JSON') or '{}')
+row = next((s for s in d.get('herdr_sessions', []) if s.get('name') == name), {})
+print(row.get('attach_command') or attach_command(os.environ['ATTACH_SERVER'], name))
+"
+}
+
 # resolve_herdr_session <session_name> [workspace]
 #
 # returns the isolated herdr *session* name (socket/daemon) to use for this MAM session row,
@@ -2024,18 +2052,31 @@ PYEOF
 }
 
 # ---------------------------------------------------------------------------
-# capture_conversation_id <agent> <workdir> [session_name]
+# mam_session_ids <stop|resume> [args...]
-#
+# Issue #63: stop/purge/resume conversation-id decision (lib_py.agents.session_ids).
-# Thin wrapper over find_workspace_uuid: resolves THIS workspace's conversation
-# id (claude jsonl sessionId / agy db uuid) and prints it on stdout (empty line
-# if none). find_workspace_uuid is already a workspace-scoped, 2-tier, race-free
-# resolver (per-row own id -> workspace-scoped disk scan),
-# so recording its result into the row before kill guarantees tier-1 on the next
-# resume. Pass session_name to prefer that specific row's recorded id. Always exits 0.
 # ---------------------------------------------------------------------------
-capture_conversation_id() {
+mam_session_ids() {
-  local agent="$1" workdir="$2" session_name="${3:-}"
+  env_python "$AGENT_SESSIONS_YAML" "$@" <<'PYEOF'
-  find_workspace_uuid "$workdir" "$agent" "$session_name"
+import sys
+from lib_py.agents.session_ids import main
+sys.exit(main(sys.argv[1:]))
+PYEOF
+}
+
+# ---------------------------------------------------------------------------
+# mam_id_order_wait <workspace> <agent> <session> [uuid]
+# Issue #63: same-cwd creation/resume ordering for post-discovered agents.
+# ---------------------------------------------------------------------------
+mam_id_order_wait() {
+  local workspace="$1" agent="$2" session_name="$3" uuid="${4:-}"
+  local abs; abs="$(mam_abs_workspace "$workspace")"
+  env_python "$AGENT_SESSIONS_YAML" wait --cwd "$abs" --agent "$agent" \
+    --session "$session_name" --owner-pid "$$" --uuid "$uuid" \
+    --herdr-server "${HERDR_SESSION_NAME:-}" <<'PYEOF'
+import sys
+from lib_py.agents.id_order import main
+sys.exit(main(sys.argv[1:]))
+PYEOF
 }
 
 # ---------------------------------------------------------------------------
@@ -2194,6 +2235,41 @@ _delegate_publish_event_legacy() {
   "$py_bin" "$pub" --job "$job_id" --event "$event" --detail "$detail" ${extra[@]+"${extra[@]}"} || true
 }
 
+# _monitor_pids <monitor_script>
+# Issue #72: PIDs whose command line is exactly `<bash> <monitor_script>
+# --subscribe[ ...]` - the shell twin of lib_py.delegation.daemon.find_running,
+# so both start_watchdog branches recognise the same daemons. Not a `pgrep -f`
+# regex: that also matched another workspace's daemon (an unescaped `.`) and a
+# process that only names the path in an argument.
+_monitor_pids() {
+  ps -A -ww -o pid= -o args= | MAM_MONITOR_WANT="$1 --subscribe" awk '
+    { line = $0; sub(/^ +/, "", line)
+      i = index(line, " "); if (!i) next
+      pid = substr(line, 1, i - 1); args = substr(line, i + 1)
+      j = index(args, " "); if (!j) next
+      n = split(substr(args, 1, j - 1), a0, "/"); rest = substr(args, j + 1)
+      want = ENVIRON["MAM_MONITOR_WANT"]
+      if (a0[n] == "bash" && (rest == want || index(rest, want " ") == 1)) print pid }'
+}
+
+# mam_monitor_started <workspace> <pid...>
+# Issue #72: 0 once one of the PIDs start_watchdog printed is WORKSPACE's
+# monitor (_monitor_pids), so a restart is only reported when it happened.
+# Polled for up to 5 s: a daemon just started from the shell carries its
+# parent's command line until it execs bash.
+mam_monitor_started() {
+  local script="$1/.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh" n=0 p
+  shift
+  while [ "$n" -lt 50 ]; do
+    for p in $(_monitor_pids "$script"); do
+      case " $* " in *" $p "*) return 0 ;; esac
+    done
+    sleep 0.1
+    n=$((n + 1))
+  done
+  return 1
+}
+
 # start_watchdog <job_id> [workdir]
 # Spawns a watchdog process to monitor a delegate-job JOB in the background.
 # The watchdog re-spawns the subscriber every 2 minutes (or whatever hard
@@ -2212,7 +2288,7 @@ _start_watchdog_legacy() {
   
   # Check if reconcile.sh --subscribe is already running on this workspace
   local pid
-  pid=$(pgrep -f "bash $monitor_script --subscribe" || true)
+  pid=$(_monitor_pids "$monitor_script" || true)
   
   # Issue #19: MAM_NO_SUBSCRIBER_DAEMON=1 reports a running daemon but never
   # starts one (test sandboxes; externally supervised monitors).
@@ -2221,10 +2297,16 @@ _start_watchdog_legacy() {
   elif [ -z "$pid" ]; then
     # Start the wildcard monitor subscriber daemon with --idle-timeout 0 (never idle out)
     # and ensure it runs with $workdir as cwd to anchor relative log paths.
-    local orig_pwd="$PWD"
+    # Issue #72 (decision 2): job control (`set -m`) starts it in its own
+    # process group, out of the caller's, as the python body's new session
+    # does; macOS has no setsid(1). The caller's option is restored.
+    local orig_pwd="$PWD" had_m=0
+    case $- in *m*) had_m=1 ;; esac
     cd "$workdir" || return 1
+    set -m
     nohup bash "$monitor_script" --subscribe --idle-timeout 0 </dev/null >> "$log_file" 2>&1 &
     pid=$!
+    [ "$had_m" = 1 ] || set +m
     cd "$orig_pwd" || return 1
   fi
   
@@ -2467,6 +2549,18 @@ delegate_wait_terminal() {
       --job "$job_id" --registry-dir "$reg_dir" --timeout "$timeout_s" --watch-pid "$$"
 }
 
+# delegate_autopin_completed <job_id> [dispatch_token] [registry_dir]
+# Issue #40: once this side has seen the job `completed`, pin the session's
+# post-discovered id (lib_py.agents.autopin decides and writes; remote, human
+# and pre-assigned sessions are left alone, one job/token/attempt is handled
+# once). Reports on stderr; never changes the job's result or this exit code.
+delegate_autopin_completed() {
+  local job_id="$1" token="${2:-}" reg_dir="${3:-${MAM_JOBS_DIR:-${WORKSPACE_ROOT:-$PWD}/.mam/jobs}}"
+  PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" HOME_DIR="${HOME_DIR:-$HOME}" LIB_SH="$SKILL_DIR/lib.sh" \
+      "$(_delegate_py_bin)" -m lib_py.agents.autopin --job "$job_id" --registry-dir "$reg_dir" \
+      --yaml "$AGENT_SESSIONS_YAML" ${token:+--expect-dispatch-token "$token"} >&2 || true
+}
+
 # delegate_onboard_exit <status>
 # Issue #50: create's exit code for an onboarding status (0, 44 or 45).
 delegate_onboard_exit() {
@@ -2762,7 +2856,7 @@ wait_for_agent_idle() {
   fi
 
   local target
-  target=$(_sanitize_herdr_agent_name "$sess")
+  target=$(_sanitize_herdr_agent_name "$sess") || return 3
 
   local raw_status="" agent_st=""
   raw_status="$(_sks_herdr agent get "$target" 2>/dev/null || _sks_herdr agent get "$sess" 2>/dev/null || true)"
@@ -2887,7 +2981,7 @@ send_keys_safe() {
   fi
 
   local agent_target
-  agent_target=$(_sanitize_herdr_agent_name "$sess")
+  agent_target=$(_sanitize_herdr_agent_name "$sess") || return 1
 
   # Busy gate: wait up to SKS_BUSY_TIMEOUT only if wait_for_agent_idle returned 3 (unknown)
   if [ "${_SKS_IDLE_RC:-0}" = "3" ]; then
@@ -3194,3 +3288,92 @@ mam_control_plane_prefix() {
   [ -n "${1:-}" ] || return 0
   PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" "$(_delegate_py_bin)" -m lib_py.control_plane prefix "$1"
 }
+
+# ---------------------------------------------------------------------------
+# Issue #72 (decision 8): the update admission gate.
+#
+# The update skill publishes .mam/update-in-progress (pid + lstart, loop_lock.sh
+# rules) while it holds .mam/update-admission.lock exclusively, then runs its
+# pre-check. Every entry that starts something the pre-check must see - create,
+# resume, run_loop.sh, delegate submit - or writes the registry - stop,
+# orc-onboard - takes that lock shared on fd 7, refuses while the marker is
+# `live` or `unknown`, and keeps fd 7 until its record is written
+# (mam_update_admit_release). An update therefore either waits for that record
+# and sees it, or publishes first and the entry refuses. The lock is a BSD
+# flock taken by lib_py.pane_lock on the open fd: it ends when every process
+# holding fd 7 has ended, however that ends, so nothing long-lived may inherit
+# fd 7 (`7>&-` on such a child, as pane_lock's fd 9). The wait is bounded by
+# MAM_UPDATE_ADMISSION_WAIT_S (default 120).
+#
+# mam_update_admit [workspace [fd]]: rc 0 admitted (fd 7, or the given one,
+# held unless the workspace has no .mam), 1 refused (stderr). Delegate submit
+# also takes the workspaces its target is in on fds 20 and up, create and
+# resume those their pane's cwd is in (mam_update_admit_at).
+mam_update_admit() {
+  local root="${1:-$WORKSPACE_ROOT}" fd="${2:-7}"
+  local lock="$root/.mam/update-admission.lock" marker="$root/.mam/update-in-progress" st
+  # No .mam: not an installed workspace, which is all the update runs in (and a
+  # checkout running its own scripts gets no .mam from this).
+  [ -d "$root/.mam" ] || return 0
+  if ! eval "exec $fd>>\"\$lock\""; then
+    echo "ERROR: cannot open the update admission lock $lock" >&2
+    return 1
+  fi
+  case "$(PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" python3 -m lib_py.pane_lock acquire --fd "$fd" --shared --wait-env MAM_UPDATE_ADMISSION_WAIT_S)" in
+    locked) ;;
+    timeout)
+      mam_update_admit_release "$fd"
+      echo "ERROR: an update of $root holds its admission lock (MAM_UPDATE_ADMISSION_WAIT_S passed); try again when it has finished" >&2
+      return 1 ;;
+    *)
+      mam_update_admit_release "$fd"
+      echo "ERROR: the update admission lock $lock could not be decided (lib_py.pane_lock)" >&2
+      return 1 ;;
+  esac
+  [ -f "$marker" ] || return 0
+  # shellcheck disable=SC1091
+  declare -F _mam_lock_holder_state >/dev/null || source "$SKILL_DIR/multi-agent-mux-loop/scripts/loop_lock.sh"
+  st="$(_mam_lock_holder_state "$marker")"
+  case "$st" in
+    stale)
+      echo "NOTE: stale update marker $marker (its update is gone); ignored" >&2
+      return 0 ;;
+  esac
+  mam_update_admit_release "$fd"
+  echo "ERROR: an update of $root is in progress (marker $marker, holder $st); try again when it has finished" >&2
+  return 1
+}
+
+mam_update_admit_release() {
+  eval "exec ${1:-7}>&-"
+}
+
+# mam_update_admit_at <cwd>: what create and resume take for an agent they
+# start in <cwd> - mam_update_admit for the control root (fd 7) and for every
+# other installed workspace at or above <cwd> (fds 20 and up), whose update
+# counts that agent (decision 1). rc 1 refused, nothing held.
+# mam_update_admit_release_all drops them all; a long-lived child started
+# while they are held runs it first.
+MAM_UPDATE_ADMIT_FDS=""
+mam_update_admit_at() {
+  local roots root fd=20
+  roots="$(PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" "$(_delegate_py_bin)" -m lib_py.update target-workspaces \
+    --workspace "$WORKSPACE_ROOT" --cwd "$1")" \
+    || { echo "ERROR: cannot resolve the installed workspaces at or above $1" >&2; return 1; }
+  mam_update_admit || return 1
+  while IFS= read -r root; do
+    [ -n "$root" ] || continue
+    if ! mam_update_admit "$root" "$fd"; then
+      mam_update_admit_release_all
+      return 1
+    fi
+    MAM_UPDATE_ADMIT_FDS="$MAM_UPDATE_ADMIT_FDS $fd"; fd=$((fd + 1))
+  done <<< "$roots"
+}
+
+mam_update_admit_release_all() {
+  local fd
+  mam_update_admit_release
+  for fd in $MAM_UPDATE_ADMIT_FDS; do mam_update_admit_release "$fd"; done
+  MAM_UPDATE_ADMIT_FDS=""
+}

.agents/skills/lib_py/agents/adapters/agy.py

@@ -1,6 +1,43 @@
-import os, sys, json, shutil
+import os, sys, json, shutil, subprocess
-from typing import Optional, Any
+from typing import Optional, Any, Dict, List
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, _ro_connect, conversation_in_use
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, _ro_connect, capture_result, conversation_in_use
+from lib_py.verify_session import verify_session_uuid, workspace_key
+
+
+def _holder_pids(paths: List[str]) -> Optional[List[int]]:
+    """PIDs holding any of `paths` open (lsof -t), [] when none does, None
+    when lsof cannot answer (missing, failed, timed out)."""
+    existing = [p for p in paths if p and os.path.exists(p)]
+    if not existing:
+        return []
+    lsof = shutil.which("lsof")
+    if not lsof:
+        return None
+    try:
+        r = subprocess.run([lsof, "-t"] + existing, capture_output=True, text=True, timeout=10)
+    except Exception:
+        return None
+    pids = sorted({int(t) for t in r.stdout.split() if t.isdigit()})
+    # lsof exits 1 both when nothing holds the files and on errors.
+    if r.returncode not in (0, 1) or (r.returncode == 1 and not pids and r.stderr.strip()):
+        return None
+    return pids
+
+
+def _process_parents() -> Optional[Dict[int, int]]:
+    """pid -> ppid of every running process (ps), None when ps fails."""
+    try:
+        out = subprocess.run(["ps", "-eo", "pid=,ppid="], capture_output=True, text=True, timeout=10)
+    except Exception:
+        return None
+    if out.returncode != 0:
+        return None
+    parents: Dict[int, int] = {}
+    for line in out.stdout.splitlines():
+        parts = line.split()
+        if len(parts) == 2 and parts[0].isdigit() and parts[1].isdigit():
+            parents[int(parts[0])] = int(parts[1])
+    return parents or None
 
 class AgyAgentAdapter(BaseAgentAdapter):
     @property
@@ -58,18 +95,15 @@ class AgyAgentAdapter(BaseAgentAdapter):
         if ctx.epoch and os.path.getmtime(path) < ctx.epoch:
             return False
         if ctx.mode == "discover":
-            lc = f"{ctx.home_dir}/.gemini/antigravity-cli/cache/last_conversations.json"
+            # Issue #40: the cache maps each workspace to the conversation last
-            cache_match = False
+            # opened there, so an id it maps to another workspace is that
-            if os.path.exists(lc):
+            # workspace's; and an id another row records is never this row's,
-                try:
+            # whether or not the cache names it for this cwd.
-                    with open(lc) as f:
+            here = workspace_key(ctx.cwd)
-                        lc_data = json.load(f)
+            if any(v == uuid and workspace_key(k) != here for k, v in self._last_conversations(ctx).items()):
-                    cache_match = (lc_data.get(ctx.cwd) == uuid)
+                return False
-                except Exception:
+            if uuid in (ctx.row.get("_sibling_claimed_uuids") or []):
-                    cache_match = False
+                return False
-            if not cache_match:
-                if uuid in (ctx.row.get("_sibling_claimed_uuids") or []):
-                    return False
         try:
             conn = _ro_connect(path)
             r = conn.execute("SELECT count(*) FROM steps").fetchone()
@@ -83,6 +117,71 @@ class AgyAgentAdapter(BaseAgentAdapter):
     def _cli_root(self, ctx: DiscoveryContext) -> str:
         return f"{ctx.home_dir}/.gemini/antigravity-cli"
 
+    def _last_conversations(self, ctx: DiscoveryContext) -> dict:
+        """cache/last_conversations.json: {cwd: id of the conversation last opened there}."""
+        try:
+            with open(f"{self._cli_root(ctx)}/cache/last_conversations.json") as f:
+                data = json.load(f)
+            return data if isinstance(data, dict) else {}
+        except Exception:
+            return {}
+
+    def capture_active_session_id(self, ctx: DiscoveryContext) -> dict:
+        """Issue #40: the cache only proposes an id - it holds one id per cwd,
+        rewritten whenever any agy opens a conversation there, so it cannot tell
+        two sessions in one cwd apart. The id is this session's only when its
+        presence lock (or DB) is held open by the row's pane process or one of
+        its descendants. Anything unprovable is not pinned (no cache-only fallback)."""
+        here = workspace_key(ctx.cwd)
+        proposed = sorted({v for k, v in self._last_conversations(ctx).items()
+                           if v and workspace_key(k) == here})
+        if not proposed:
+            return capture_result("no-candidate", reason="last_conversations.json names no conversation for this cwd")
+        if len(proposed) > 1:
+            return capture_result("ambiguous", reason="last_conversations.json maps this cwd to several conversations",
+                                  candidates=proposed)
+        uuid = proposed[0]
+        if uuid in (ctx.row.get("_sibling_claimed_uuids") or []):
+            return capture_result("sibling-claimed", reason=f"{uuid} is recorded by another session", candidates=[uuid])
+        if not verify_session_uuid(ctx.cwd, self.name, uuid, row=ctx.row, home_dir=ctx.home_dir, mode="discover"):
+            return capture_result("rejected", reason=f"{uuid} failed verification (missing, older than the session, or empty)",
+                                  candidates=[uuid])
+        status, reason = self._owner_check(uuid, ctx)
+        if status != "ok":
+            return capture_result(status, reason=reason, candidates=[uuid])
+        return capture_result("captured", session_id=uuid, candidates=[uuid])
+
+    def _owner_check(self, uuid: str, ctx: DiscoveryContext):
+        """('ok', '') when a holder of the conversation's presence lock or DB is
+        the row's pane process or its descendant; otherwise
+        ('unverifiable-owner' | 'owner-mismatch', reason)."""
+        try:
+            pane_pid = int((ctx.row.get("pane") or {}).get("pid") or 0)
+        except (TypeError, ValueError):
+            pane_pid = 0
+        if pane_pid <= 1:
+            return "unverifiable-owner", "the row records no pane pid"
+        db = self.artifact_path(uuid, ctx)
+        paths = [f"{self._cli_root(ctx)}/presence/{uuid}.lock", db, f"{db}-wal", f"{db}-shm"]
+        holders = _holder_pids(paths)
+        if holders is None:
+            return "unverifiable-owner", "lsof is unavailable or failed"
+        if not holders:
+            return "unverifiable-owner", f"no process holds {uuid}'s presence lock or DB"
+        if pane_pid in holders:
+            return "ok", ""
+        parents = _process_parents()
+        if parents is None or pane_pid not in parents:
+            return "unverifiable-owner", f"pane process {pane_pid} cannot be found"
+        for pid in holders:
+            seen = set()
+            while pid > 1 and pid not in seen:
+                if pid == pane_pid:
+                    return "ok", ""
+                seen.add(pid)
+                pid = parents.get(pid, 0)
+        return "owner-mismatch", f"{uuid} is held by pid(s) {holders}, none in pane process {pane_pid}'s tree"
+
     def _artifact_paths(self, uuid: str, ctx: DiscoveryContext) -> list:
         """Every on-disk piece of one conversation, DB first: the SQLite
         sidecars, the brain dir, the title annotation and the presence lock."""

.agents/skills/lib_py/agents/adapters/claude.py

@@ -1,6 +1,6 @@
 import os, re, json, glob, math, stat, time, shutil, calendar, subprocess
 from typing import Optional, Any
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, conversation_in_use, scan_names
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, PRE_ASSIGNED, conversation_in_use, scan_names
 from lib_py.verify_session import workspace_key
 
 
@@ -184,6 +184,11 @@ class ClaudeAgentAdapter(BaseAgentAdapter):
     def own_key(self) -> str:
         return 'claude_session_id_own'
 
+    @property
+    def id_lifecycle(self) -> str:
+        # create hands the CLI its id (--session-id); nothing to capture (#40)
+        return PRE_ASSIGNED
+
     @property
     def ready_tokens(self) -> str:
         return 'Anthropic|Assistant|Chat|Welcome|Claude Code|Opus|Sonnet|Haiku'

.agents/skills/lib_py/agents/adapters/grok.py

@@ -1,7 +1,7 @@
 import os, json, glob, shutil
 from typing import Optional, Any
 from urllib.parse import quote
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, scan_names
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, PRE_ASSIGNED, scan_names
 from lib_py.verify_session import workspace_key
 
 
@@ -14,6 +14,11 @@ class GrokAgentAdapter(BaseAgentAdapter):
     def own_key(self) -> str:
         return 'grok_session_id_own'
 
+    @property
+    def id_lifecycle(self) -> str:
+        # create hands the CLI its id (--session-id); nothing to capture (#40)
+        return PRE_ASSIGNED
+
     @property
     def ready_tokens(self) -> str:
         return 'Grok|xAI|Assistant|❯|>>>'

.agents/skills/lib_py/agents/autopin.py

@@ -0,0 +1,261 @@
+"""Auto-pin of a post-discovered session id on a verified local `completed` (Issue #40).
+
+Class A agents (agy, opencode, codex, hermes) write their conversation id to
+disk only after their first turn, so create records the row without one. The
+side that verified a job's `completed` - the delegate-job wrapper, create
+--onboard, and the loop's wait_for_job as a recovery path - calls
+handle_completed(). It captures the id through the adapter
+(capture_active_session_id) and pins it with pin_row() under atomic_dump_yaml.
+reconcile's drift C calls the same capture() and pin_row(), so the two paths
+reach one decision.
+
+One (job_id, dispatch_token, attempt_id) is handled once: a job-scoped flock
+and a marker in the job's directory make a second call (wrapper + loop
+recovery) a no-op. Remote and human jobs have no local disk or pane and are
+skipped; the agent's own publish_event.py never writes the control plane
+(#15/#20/#21). A failed pin never changes the job's result: the reason is
+written on the row and returned.
+
+CLI: python -m lib_py.agents.autopin --registry-dir DIR --job ID
+         [--yaml AGENT_SESSIONS_YAML] [--expect-dispatch-token TOKEN]
+"""
+
+import argparse
+import fcntl
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import time
+from typing import Any, Callable, Dict, List, Optional
+
+from lib_py.agents.base import DiscoveryContext, POST_DISCOVERED, capture_result
+from lib_py.agents.registry import _ADAPTERS, agent_of_row, get_adapter
+
+OWN_KEYS = tuple(a.own_key for a in _ADAPTERS.values())
+MARKER = "autopin.json"
+
+
+def claimed_elsewhere(row: Dict[str, Any], state: Dict[str, Any]) -> List[str]:
+    """Every id another row records: an id already some session's is never this one's."""
+    ids: List[str] = []
+    for other in state.get("herdr_sessions") or []:
+        if other is row or other.get("name") == row.get("name"):
+            continue
+        for key in OWN_KEYS:
+            v = other.get(key)
+            if v and v not in ids:
+                ids.append(v)
+    return ids
+
+
+def capture(row: Dict[str, Any], agent: str, state: Dict[str, Any], home_dir: Optional[str] = None) -> Dict[str, Any]:
+    """The adapter's decision for this row (read-only). Besides the capture
+    statuses: 'pre-assigned' and 'already-set' (nothing to capture), 'skipped'."""
+    adapter = get_adapter(agent)
+    if adapter is None:
+        return capture_result("skipped", reason=f"unknown agent {agent!r}")
+    if adapter.id_lifecycle != POST_DISCOVERED:
+        return capture_result("pre-assigned")
+    if row.get(adapter.own_key):
+        return capture_result("already-set", session_id=row[adapter.own_key])
+    cwd = (row.get("pane") or {}).get("cwd") or ""
+    if not cwd:
+        return capture_result("no-candidate", reason="the row has no pane cwd")
+    row_eval = dict(row)
+    row_eval["_sibling_claimed_uuids"] = claimed_elsewhere(row, state)
+    ctx = DiscoveryContext(workspace=cwd, agent_name=agent, home_dir=home_dir,
+                           epoch=row.get("herdr_session_epoch") or 0, row=row_eval, mode="discover")
+    return adapter.capture_active_session_id(ctx)
+
+
+def pin_row(row: Dict[str, Any], agent: str, uuid: str) -> None:
+    """Record a verified id: own key, source and verified flag, in one change."""
+    row[get_adapter(agent).own_key] = uuid
+    row["session_id_source"] = "discovered"
+    row["session_id_verified"] = True
+    row["last_visible_status"] = "pinned"
+
+
+def _skills_dir() -> str:
+    return os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+def resume_dry_run(skills_dir: str, cwd: str, agent: str, name: str, env: Optional[Dict[str, str]] = None) -> str:
+    """last_visible_status after a pin: 'resume_verified' or why the dry-run failed."""
+    cmd = ["bash", os.path.join(skills_dir, "multi-agent-mux-resume", "scripts", "resume_session.sh"),
+           "--workspace", cwd, "--agent", agent, "--session", name, "--dry-run"]
+    res = subprocess.run(cmd, capture_output=True, text=True, env=env)
+    if res.returncode == 0:
+        return "resume_verified"
+    return f"resume dry-run failed: {res.stderr.strip() or res.stdout.strip()}"
+
+
+def tui_viewport(lib_sh: str, name: str, agent: str, cwd: str, env: Optional[Dict[str, str]] = None) -> int:
+    """lib.sh verify_tui_viewport: 0 match, 1 mismatch, other = no evidence."""
+    script = 'source "$1" && verify_tui_viewport "$2" "$3" "$4"'
+    return subprocess.run(["bash", "-c", script, "_", lib_sh, name, agent, cwd], env=env).returncode
+
+
+def _load_record(registry_dir: str, job_id: str) -> Optional[Dict[str, Any]]:
+    try:
+        with open(os.path.join(registry_dir, f"{job_id}.json"), encoding="utf-8") as f:
+            rec = json.load(f)
+        return rec if isinstance(rec, dict) else None
+    except (OSError, ValueError):
+        return None
+
+
+_MUTATION: Optional[Callable[[Dict[str, Any]], bool]] = None
+
+
+def _atomic_update(yaml_path: str, mutate: Callable[[Dict[str, Any]], bool]) -> None:
+    """Run `mutate(d)` as an atomic_dump_yaml mutation in this process; it
+    returns False to leave the registry untouched."""
+    from lib_py import atomic_yaml
+    global _MUTATION
+    saved = {k: os.environ.get(k) for k in ("YAML_PATH", "AGENT_SESSIONS_MUTATION")}
+    _MUTATION = mutate
+    os.environ["YAML_PATH"] = yaml_path
+    # this very module (it is __main__ under `python -m`), not a second copy
+    os.environ["AGENT_SESSIONS_MUTATION"] = (
+        "import sys as _sys\n"
+        f"if not _sys.modules[{__name__!r}]._MUTATION(d):\n"
+        "    raise SystemExit(0)\n")
+    try:
+        atomic_yaml.atomic_dump_yaml_main()
+    except SystemExit as exc:
+        if exc.code not in (0, None):
+            raise RuntimeError(str(exc.code))
+    finally:
+        _MUTATION = None
+        for k, v in saved.items():
+            if v is None:
+                os.environ.pop(k, None)
+            else:
+                os.environ[k] = v
+
+
+
+def _subprocess_env(yaml_path: str, registry_dir: str) -> Dict[str, str]:
+    """The control plane the lib.sh checks run against: the registry's own."""
+    env = dict(os.environ)
+    env.setdefault("AGENT_SESSIONS_YAML", yaml_path)
+    env.setdefault("MAM_JOBS_DIR", registry_dir)
+    mam = os.path.dirname(yaml_path)
+    if os.path.basename(mam) == ".mam":
+        env.setdefault("WORKSPACE_ROOT", os.path.dirname(mam))
+    return env
+
+
+def _pin_session(name: str, job_id: str, yaml_path: str, home_dir: Optional[str],
+                 viewport: Callable[[str, str, str], int], resume: Callable[[str, str, str], str]) -> Dict[str, Any]:
+    out: Dict[str, Any] = {}
+
+    def mutate(d: Dict[str, Any]) -> bool:
+        row = next((s for s in d.get("herdr_sessions") or [] if s.get("name") == name), None)
+        if row is None:
+            out.update(capture_result("skipped", reason=f"no session row {name!r}"))
+            return False
+        if row.get("status") != "running":
+            out.update(capture_result("skipped", reason=f"session {name!r} is {row.get('status')}"))
+            return False
+        agent = agent_of_row(row)
+        res = capture(row, agent or "", d, home_dir=home_dir)
+        cwd = (row.get("pane") or {}).get("cwd") or ""
+        if res["status"] == "captured":
+            rc = viewport(name, agent, cwd)
+            if rc == 1:
+                res = capture_result("viewport-mismatch", reason="the pane does not show this workspace",
+                                     candidates=res["candidates"])
+            else:
+                pin_row(row, agent, res["session_id"])
+                row["last_visible_status"] = resume(name, agent, cwd)
+                res = dict(res, status="pinned", degraded=(rc != 0))
+                out.update(res)
+                return True
+        out.update(res)
+        if res["status"] in ("pre-assigned", "already-set", "skipped"):
+            return False
+        row["last_visible_status"] = f"autopin {res['status']} (job {job_id}): {res['reason']}"
+        return True
+
+    _atomic_update(yaml_path, mutate)
+    return out
+
+
+def handle_completed(registry_dir: str, job_id: str, yaml_path: Optional[str] = None,
+                     expect_token: Optional[str] = None, home_dir: Optional[str] = None,
+                     viewport: Optional[Callable[[str, str, str], int]] = None,
+                     resume: Optional[Callable[[str, str, str], str]] = None) -> Dict[str, Any]:
+    """Pin the job's session id if the job completed locally and the row still
+    lacks a post-discovered id. Returns the result (also kept in the marker)."""
+    rec = _load_record(registry_dir, job_id)
+    if rec is None:
+        return capture_result("skipped", reason=f"no job record {job_id}")
+    if rec.get("status") != "completed":
+        return capture_result("skipped", reason=f"job {job_id} is {rec.get('status')}")
+    token = rec.get("dispatch_token") or ""
+    if expect_token and token != expect_token:
+        return capture_result("skipped", reason="stale dispatch token")
+    session = str(rec.get("agent_session") or "")
+    if (rec.get("transport") == "remote" or session.startswith("remote:")
+            or rec.get("agent") == "human" or session in ("", "human", "herdr:human")):
+        return capture_result("skipped", reason="not a local agent session")
+    name = session[len("herdr:"):] if session.startswith("herdr:") else session
+    yaml_path = yaml_path or os.environ.get("AGENT_SESSIONS_YAML") or os.path.join(
+        os.path.dirname(os.path.abspath(registry_dir)), "agent-sessions.yaml")
+    if not (os.path.exists(yaml_path) or os.path.exists(os.path.splitext(yaml_path)[0] + ".db")):
+        return capture_result("skipped", reason=f"no session registry at {yaml_path}")
+
+    key = f"{job_id}:{token}:{rec.get('attempt_id')}"
+    job_dir = os.path.join(registry_dir, job_id)
+    os.makedirs(job_dir, exist_ok=True)
+    env = _subprocess_env(yaml_path, registry_dir)
+    if viewport is None:
+        lib_sh = os.environ.get("LIB_SH") or os.path.join(_skills_dir(), "lib.sh")
+        viewport = lambda n, a, c: tui_viewport(lib_sh, n, a, c, env=env)  # noqa: E731
+    if resume is None:
+        resume = lambda n, a, c: resume_dry_run(_skills_dir(), c, a, n, env=env)  # noqa: E731
+
+    with open(os.path.join(job_dir, "autopin.lock"), "w") as lock:
+        fcntl.flock(lock, fcntl.LOCK_EX)
+        marker = os.path.join(job_dir, MARKER)
+        try:
+            with open(marker, encoding="utf-8") as f:
+                done = json.load(f)
+            if done.get("key") == key:
+                return dict(done.get("result") or {}, deduplicated=True)
+        except (OSError, ValueError):
+            pass
+        try:
+            result = _pin_session(name, job_id, yaml_path, home_dir, viewport, resume)
+        except Exception as exc:
+            result = capture_result("error", reason=f"{type(exc).__name__}: {exc}")
+        result["session"] = name
+        fd, tmp = tempfile.mkstemp(dir=job_dir, prefix=".autopin.", suffix=".tmp")
+        with os.fdopen(fd, "w", encoding="utf-8") as f:
+            json.dump({"key": key, "at": int(time.time()), "result": result}, f)
+        os.replace(tmp, marker)
+        return result
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    p = argparse.ArgumentParser(prog="python -m lib_py.agents.autopin")
+    p.add_argument("--registry-dir", required=True)
+    p.add_argument("--job", required=True)
+    p.add_argument("--yaml", default=None, help="agent-sessions.yaml (default: beside the registry)")
+    p.add_argument("--expect-dispatch-token", default=None)
+    a = p.parse_args(argv)
+    res = handle_completed(a.registry_dir, a.job, yaml_path=a.yaml, expect_token=a.expect_dispatch_token)
+    if res.get("status") == "pinned":
+        print(f"autopin: {res['session']} pinned {res['session_id']} (job {a.job})", file=sys.stderr)
+    elif res.get("status") not in ("skipped", "pre-assigned", "already-set") and not res.get("deduplicated"):
+        print(f"autopin: {res.get('session')} not pinned - {res['status']}: {res.get('reason')} (job {a.job})",
+              file=sys.stderr)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.agents/skills/lib_py/agents/base.py

@@ -169,6 +169,22 @@ def db_rows_naming(db: str, uuid: str, columns=(), id_tables=(), connect=None) -
         conn.close()
     return found
 
+# Session-id lifecycles (Issue #40): the id is handed to the CLI before it
+# starts, or the CLI writes it to disk after its first turn.
+PRE_ASSIGNED = 'pre_assigned'
+POST_DISCOVERED = 'post_discovered'
+
+
+def capture_result(status: str, session_id: Optional[str] = None, reason: str = "",
+                   candidates: Optional[List[str]] = None) -> Dict[str, Any]:
+    """What capture_active_session_id found (Issue #40). `status` is
+    'captured' (session_id set) or why nothing may be pinned: 'no-candidate',
+    'ambiguous', 'sibling-claimed', 'rejected', 'unverifiable-owner',
+    'owner-mismatch'."""
+    return {"status": status, "session_id": session_id, "reason": reason,
+            "candidates": list(candidates or [])}
+
+
 class SpawnSpec:
     def __init__(self, agent_name: str, session_name: str, command: str, env: Optional[Dict[str, str]] = None):
         self.agent_name = agent_name
@@ -358,3 +374,28 @@ class BaseAgentAdapter:
 
     def discover(self, ctx: DiscoveryContext) -> list:
         raise NotImplementedError
+
+    @property
+    def id_lifecycle(self) -> str:
+        """PRE_ASSIGNED: the id is given to the CLI at spawn (nothing to capture).
+        POST_DISCOVERED: the CLI writes it after its first turn (Issue #40)."""
+        return POST_DISCOVERED
+
+    def capture_active_session_id(self, ctx: DiscoveryContext) -> Dict[str, Any]:
+        """This session's id, decided only when it is unambiguous (Issue #40):
+        exactly one discover() candidate that verify_session_uuid accepts and
+        no other row records (ctx.row['_sibling_claimed_uuids']). Read-only."""
+        claimed = set(ctx.row.get("_sibling_claimed_uuids") or [])
+        found: List[str] = []
+        for uuid in self.discover(ctx):
+            if not uuid or uuid in claimed or uuid in found:
+                continue
+            if verify_session_uuid(ctx.cwd, self.name, uuid, row=ctx.row, home_dir=ctx.home_dir,
+                                   claude_dir=ctx.claude_dir, mode="discover"):
+                found.append(uuid)
+        if not found:
+            return capture_result("no-candidate", reason="no verified candidate newer than the session")
+        if len(found) > 1:
+            return capture_result("ambiguous", reason=f"{len(found)} candidates newer than the session",
+                                  candidates=found)
+        return capture_result("captured", session_id=found[0], candidates=found)

.agents/skills/lib_py/agents/id_order.py

@@ -0,0 +1,383 @@
+"""Same-cwd creation/resume ordering for post-discovered agents (Issue #63).
+
+While a post-discovered agent (agy, codex, hermes, opencode) in a workspace is
+ still being created (marker held by a live create/resume process) or is running
+without a recorded conversation id (live pane pid), a second create or resume of
+the same agent type in that workspace waits until the first records its id, up
+to MAM_ID_ORDER_WAIT_S (default 600 s; 0 = do not wait). A marker whose owner
+died before the row was registered keeps blocking until herdr answers that its
+session is gone (the pane may still discover the workspace id).
+"""
+from __future__ import annotations
+
+import argparse
+import fcntl
+import hashlib
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import time
+from typing import Any, Callable, Dict, List, Mapping, Optional
+
+from lib_py import ints
+from lib_py.agents.autopin import claimed_elsewhere
+from lib_py.agents.base import POST_DISCOVERED
+from lib_py.agents.registry import agent_of_row, get_adapter
+from lib_py.agents.sanitize import sanitize_herdr_agent_name
+from lib_py.agents.session_ids import canonical_cwd, claiming_rows, own_id
+from lib_py.state import load_state_json
+
+DEFAULT_WAIT_S = 600
+PROBE_TIMEOUT_S = 30.0
+
+
+def wait_s(env: Mapping[str, str] = os.environ) -> int:
+    raw = env.get("MAM_ID_ORDER_WAIT_S")
+    if raw is None:
+        return DEFAULT_WAIT_S
+    n = ints.positive_int(raw, 0)
+    return DEFAULT_WAIT_S if n is None else n
+
+
+def pid_alive(pid: int) -> bool:
+    if not isinstance(pid, int) or pid <= 0:
+        return False
+    try:
+        os.kill(pid, 0)
+        return True
+    except ProcessLookupError:
+        return False
+    except PermissionError:
+        return True
+    except OSError:
+        return False
+
+
+def herdr_session_state(server: str, session: str, timeout: float) -> Optional[bool]:
+    """Is `session` live on herdr server `server`: True, False, or None when
+    herdr gave no authoritative answer. False only from a successful, parsed
+    `agent list` without the name; a failed (server down included), timed-out
+    or unparseable lookup, or no time left, is None. Never starts a server
+    (MAM_NO_AUTOSTART)."""
+    if timeout <= 0:
+        return None
+    skills_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+    env = dict(os.environ, MAM_NO_AUTOSTART="1", HERDR_SESSION_NAME=server or "default")
+    script = 'source "$1" && _herdr agent list'
+    try:
+        res = subprocess.run(
+            ["bash", "-c", script, "_", os.path.join(skills_dir, "lib.sh")],
+            env=env, stdin=subprocess.DEVNULL, capture_output=True, text=True,
+            timeout=min(timeout, PROBE_TIMEOUT_S),
+        )
+    except (OSError, subprocess.SubprocessError):
+        return None
+    if res.returncode != 0:
+        return None
+    try:
+        agents = json.loads(res.stdout)["result"]["agents"]
+    except (ValueError, KeyError, TypeError):
+        return None
+    if not isinstance(agents, list):
+        return None
+    names = {session, sanitize_herdr_agent_name(session)}
+    return any(isinstance(a, dict) and a.get("name") in names for a in agents)
+
+
+def order_dir(cwd: str, agent: str, env: Mapping[str, str] = os.environ,
+              home: Optional[str] = None) -> str:
+    h = home or env.get("HOME") or env.get("HOME_DIR") or os.path.expanduser("~")
+    real_cwd = canonical_cwd(cwd or ".")
+    digest = hashlib.sha256(real_cwd.encode("utf-8")).hexdigest()[:16]
+    return os.path.join(h, ".local", "state", "mam", "id-order", f"{digest}-{agent}")
+
+
+def _parse_pos_int(val: Any) -> Optional[int]:
+    if isinstance(val, bool):
+        return None
+    if isinstance(val, int):
+        return val if val > 0 else None
+    s = str(val or "").strip()
+    return int(s) if s.isdigit() and int(s) > 0 else None
+
+
+def blockers(state: Dict[str, Any], cwd: str, agent: str, me: str,
+             markers: List[Dict[str, Any]],
+             is_alive: Callable[[int], bool] = pid_alive) -> List[str]:
+    target_cwd = canonical_cwd(cwd)
+    found: List[str] = []
+    rows_by_name: Dict[str, Dict[str, Any]] = {}
+
+    for s in state.get("herdr_sessions") or []:
+        if not isinstance(s, dict):
+            continue
+        rname = str(s.get("name") or "")
+        if rname:
+            rows_by_name[rname] = s
+        if not rname or rname == me:
+            continue
+        s_cwd = (s.get("pane") or {}).get("cwd") or ""
+        if not s_cwd or canonical_cwd(s_cwd) != target_cwd:
+            continue
+        if agent_of_row(s) != agent or s.get("status") != "running":
+            continue
+        if own_id(s, agent):
+            continue
+        pane_pid = _parse_pos_int((s.get("pane") or {}).get("pid"))
+        if pane_pid is None or is_alive(pane_pid):
+            if rname not in found:
+                found.append(rname)
+
+    for m in markers or []:
+        if not isinstance(m, dict):
+            continue
+        m_sess = str(m.get("session") or "")
+        if not m_sess or m_sess in found:
+            continue
+        m_cwd = str(m.get("cwd") or "")
+        if m_cwd and canonical_cwd(m_cwd) != target_cwd:
+            continue
+        m_agent = str(m.get("agent") or "")
+        if m_agent and m_agent != agent:
+            continue
+        row = rows_by_name.get(m_sess)
+        if row is None:
+            found.append(m_sess)
+            continue
+        status = str(row.get("status") or "")
+        cur_own = own_id(row, agent)
+        row_epoch = int(row.get("herdr_session_epoch") or 0)
+        end_epoch = int(row.get("stopped_at_epoch") or row.get("terminated_at_epoch") or 0)
+        m_at = int(m.get("at") or 0)
+        prev_own = str(m.get("prev_own_id") or "")
+        prev_epoch = int(m.get("prev_epoch") or 0)
+        prev_end_epoch = int(m.get("prev_end_epoch") or 0)
+
+        pinned_for_attempt = bool(cur_own) and (
+            cur_own != prev_own
+            or (status == "running" and row_epoch > prev_epoch)
+        )
+        if pinned_for_attempt:
+            continue
+        if status == "running":
+            found.append(m_sess)
+        else:
+            ended_after_attempt = (
+                end_epoch > max(m_at, prev_end_epoch)
+                and (prev_epoch == 0 or row_epoch > prev_epoch)
+            )
+            if not ended_after_attempt:
+                found.append(m_sess)
+
+    return found
+
+
+def _registered_for_attempt(m: Dict[str, Any], row: Optional[Dict[str, Any]]) -> bool:
+    if not isinstance(row, dict) or row.get("status") != "running":
+        return False
+    return int(row.get("herdr_session_epoch") or 0) > int(m.get("prev_epoch") or 0)
+
+
+def _read_and_prune_markers(dpath: str, my_pid: int, state: Dict[str, Any],
+                            is_alive: Callable[[int], bool] = pid_alive,
+                            pane_state: Callable[[str, str], Optional[bool]] = (
+                                lambda server, session: None),
+                            ) -> List[Dict[str, Any]]:
+    """Markers that still count. A live owner keeps its marker (another live
+    attempt on the caller's session included). A dead owner's marker goes once
+    its row is registered for the attempt (the row decides from then on) or
+    herdr answers that its session is gone; until then it is kept as an orphan,
+    one an earlier attempt left on the caller's session included."""
+    rows_by_name = {
+        str(s.get("name") or ""): s
+        for s in (state.get("herdr_sessions") or []) if isinstance(s, dict)
+    }
+    out: List[Dict[str, Any]] = []
+    try:
+        names = sorted(os.listdir(dpath))
+    except OSError:
+        return out
+    for fname in names:
+        if not fname.endswith(".json") or fname.startswith("."):
+            continue
+        fpath = os.path.join(dpath, fname)
+        try:
+            with open(fpath, encoding="utf-8") as f:
+                data = json.load(f)
+        except (OSError, ValueError):
+            try:
+                os.remove(fpath)
+            except OSError:
+                pass
+            continue
+        if not isinstance(data, dict):
+            continue
+        owner_pid = _parse_pos_int(data.get("owner_pid"))
+        sess = str(data.get("session") or "")
+        if owner_pid is None or owner_pid == my_pid:
+            drop = True
+        elif is_alive(owner_pid):
+            drop = False
+        elif not sess:
+            drop = True
+        elif _registered_for_attempt(data, rows_by_name.get(sess)):
+            drop = True
+        else:
+            live = pane_state(str(data.get("herdr_server") or ""), sess)
+            drop = live is False
+            data["_orphan"] = "alive" if live else "unknown"
+        if drop:
+            try:
+                os.remove(fpath)
+            except OSError:
+                pass
+            continue
+        out.append(data)
+    return out
+
+
+def write_marker(dpath: str, session: str, owner_pid: int, cwd: str, agent: str,
+                 prev_row: Optional[Dict[str, Any]] = None, herdr_server: str = "") -> str:
+    os.makedirs(dpath, exist_ok=True)
+    marker_path = os.path.join(dpath, f"{session}.json")
+    payload: Dict[str, Any] = {
+        "session": session,
+        "owner_pid": int(owner_pid),
+        "cwd": canonical_cwd(cwd),
+        "agent": agent,
+        "herdr_server": herdr_server,
+        "at": int(time.time()),
+    }
+    if isinstance(prev_row, dict):
+        payload["prev_own_id"] = own_id(prev_row, agent)
+        payload["prev_epoch"] = int(prev_row.get("herdr_session_epoch") or 0)
+        payload["prev_end_epoch"] = int(
+            prev_row.get("stopped_at_epoch") or prev_row.get("terminated_at_epoch") or 0
+        )
+    fd, tmp = tempfile.mkstemp(dir=dpath, prefix=".marker.", suffix=".tmp")
+    with os.fdopen(fd, "w", encoding="utf-8") as f:
+        json.dump(payload, f)
+    os.replace(tmp, marker_path)
+    return marker_path
+
+
+def wait(cwd: str, agent: str, session: str, owner_pid: int,
+         uuid: str = "", yaml_path: Optional[str] = None,
+         home: Optional[str] = None, wait_s_val: Optional[int] = None,
+         poll: float = 0.25,
+         is_alive: Callable[[int], bool] = pid_alive,
+         herdr_server: str = "",
+         pane_state: Optional[Callable[[str, str, float], Optional[bool]]] = None) -> int:
+    adapter = get_adapter(agent)
+    if adapter is None or adapter.id_lifecycle != POST_DISCOVERED:
+        return 0
+
+    cap = wait_s(os.environ) if wait_s_val is None else int(wait_s_val)
+    dpath = order_dir(cwd, agent, os.environ, home=home)
+    os.makedirs(dpath, exist_ok=True)
+    lock_file = os.path.join(dpath, "lock")
+    deadline = time.monotonic() + cap
+    announced = False
+    row_ref = {"name": session}
+    probe = pane_state or herdr_session_state
+
+    answers: Dict[str, bool] = {}  # last definite answer per session, for the message
+
+    def bounded_probe(server: str, sess: str) -> Optional[bool]:
+        live = probe(server, sess, deadline - time.monotonic())
+        if live is not None:
+            answers[sess] = live
+        return live
+
+    while True:
+        with open(lock_file, "a", encoding="utf-8") as lf:
+            fcntl.flock(lf, fcntl.LOCK_EX)
+            state = load_state_json(yaml_path)
+            if uuid:
+                claimed = set(claimed_elsewhere(row_ref, state))
+                if uuid in claimed:
+                    others = ", ".join(claiming_rows(row_ref, uuid, state))
+                    print(
+                        f"ERROR: {session}'s recorded id {uuid} is also recorded by {others}; "
+                        f"refusing to resume on a conversation another session claims (Issue #63).",
+                        file=sys.stderr, flush=True,
+                    )
+                    return 1
+            markers = _read_and_prune_markers(dpath, owner_pid, state,
+                                              is_alive=is_alive, pane_state=bounded_probe)
+            blks = blockers(state, cwd, agent, session, markers, is_alive=is_alive)
+            if not blks:
+                prev_row = next(
+                    (
+                        s for s in (state.get("herdr_sessions") or [])
+                        if isinstance(s, dict) and s.get("name") == session
+                    ),
+                    None,
+                )
+                already_recorded = bool(uuid) and own_id(prev_row, agent) == uuid
+                if not already_recorded and owner_pid and owner_pid > 0:
+                    write_marker(dpath, session, owner_pid, cwd, agent, prev_row=prev_row,
+                                 herdr_server=herdr_server)
+                return 0
+
+        names = ", ".join(blks)
+        if time.monotonic() >= deadline:
+            print(
+                f"ERROR: {names} in {cwd} still has no recorded {agent} id after {cap}s; "
+                f"not starting {session} (Issue #63). Wait for its first turn to finish, "
+                f"or stop it with multi-agent-mux-stop.",
+                file=sys.stderr, flush=True,
+            )
+            for m in markers:
+                if m.get("_orphan") and m.get("session") in blks:
+                    srv = m.get("herdr_server") or "default"
+                    alive = m["_orphan"] == "alive" or answers.get(m["session"]) is True
+                    seen = ("its herdr session is alive" if alive
+                            else "herdr could not tell whether its session is gone")
+                    if not alive and cap == 0:
+                        seen += " (MAM_ID_ORDER_WAIT_S=0 leaves no time to ask herdr)"
+                    print(
+                        f"ERROR: {m['session']}'s create/resume exited before recording it, "
+                        f"and {seen}; close it with: "
+                        f"bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh "
+                        f"--session {m['session']} --herdr-session {srv}",
+                        file=sys.stderr, flush=True,
+                    )
+            return 1
+        if not announced:
+            print(
+                f"id-order: waiting for {names} ({agent}, no recorded id yet) in {cwd} "
+                f"- up to {cap}s (MAM_ID_ORDER_WAIT_S)",
+                file=sys.stderr, flush=True,
+            )
+            announced = True
+        remaining = deadline - time.monotonic()
+        if remaining > 0:
+            time.sleep(min(poll, remaining))
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    p = argparse.ArgumentParser(prog="python -m lib_py.agents.id_order")
+    sub = p.add_subparsers(dest="cmd", required=True)
+    s_wait = sub.add_parser("wait")
+    s_wait.add_argument("--cwd", required=True)
+    s_wait.add_argument("--agent", required=True)
+    s_wait.add_argument("--session", required=True)
+    s_wait.add_argument("--owner-pid", type=int, default=0)
+    s_wait.add_argument("--uuid", default="")
+    s_wait.add_argument("--herdr-server", default="")
+    a = p.parse_args(argv)
+    return wait(
+        cwd=a.cwd,
+        agent=a.agent,
+        session=a.session,
+        owner_pid=a.owner_pid,
+        uuid=a.uuid or "",
+        herdr_server=a.herdr_server or "",
+    )
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.agents/skills/lib_py/agents/sanitize.py

@@ -1,5 +1,6 @@
 import hashlib
 import re
+import shlex
 
 def sanitize_herdr_agent_name(name: str) -> str:
     """
@@ -29,3 +30,14 @@ def sanitize_herdr_agent_name(name: str) -> str:
     
     return s
 
+
+def attach_command(server, name):
+    """The registry row's attach_command (Issue #71).
+
+    A native herdr command, so it works from any shell: the server is always
+    named (`default` too - herdr's env-free default), and the agent by the name
+    herdr registered (sanitize_herdr_agent_name). create, resume and reconcile
+    all write it from here.
+    """
+    return "herdr --session %s agent attach %s" % (
+        shlex.quote(server or "default"), shlex.quote(sanitize_herdr_agent_name(name)))

.agents/skills/lib_py/agents/session_ids.py

@@ -0,0 +1,351 @@
+"""Stop, purge, and resume conversation-id decisions (Issue #63).
+
+Post-discovered agents (agy, codex, hermes, opencode) write their conversation
+id to disk only after their first turn, and agy's workspace cache holds one id
+per cwd. Stop, purge, and resume therefore use the row's own recorded id first
+(never falling through to a workspace guess when a recorded id is present), and
+otherwise use the #40 active-session capture when herdr is alive. Pre-assigned
+agents (claude, grok) keep find_workspace_uuid with other rows' claimed ids
+excluded.
+"""
+from __future__ import annotations
+
+import argparse
+import os
+import shlex
+import sys
+from typing import Any, Dict, List, Optional
+
+from lib_py.agents.autopin import OWN_KEYS, capture, claimed_elsewhere
+from lib_py.agents.base import DiscoveryContext, POST_DISCOVERED
+from lib_py.agents.registry import agent_of_row, get_adapter
+from lib_py.paths import resolve_home
+from lib_py.state import load_state_json
+from lib_py.verify_session import verify_session_uuid
+from lib_py.workspace_uuid import find_workspace_uuid
+
+
+def canonical_cwd(path: str) -> str:
+    if not path:
+        return ""
+    try:
+        return os.path.realpath(path)
+    except Exception:
+        return os.path.abspath(path)
+
+
+def own_id(row: Optional[Dict[str, Any]], agent: str) -> str:
+    adapter = get_adapter(agent)
+    if not adapter or not isinstance(row, dict):
+        return ""
+    val = row.get(adapter.own_key)
+    return str(val).strip() if val else ""
+
+
+def claiming_rows(row: Dict[str, Any], uuid: str, state: Dict[str, Any]) -> List[str]:
+    if not uuid:
+        return []
+    me = row.get("name")
+    holders: List[str] = []
+    for other in state.get("herdr_sessions") or []:
+        if other is row or (me and other.get("name") == me):
+            continue
+        if any(other.get(k) == uuid for k in OWN_KEYS):
+            other_name = str(other.get("name") or "<unnamed>")
+            if other_name not in holders:
+                holders.append(other_name)
+    return holders
+
+
+def same_type_rows(state: Dict[str, Any], cwd: str, agent: str) -> List[Dict[str, Any]]:
+    if not cwd or not agent:
+        return []
+    target_cwd = canonical_cwd(cwd)
+    out: List[Dict[str, Any]] = []
+    for s in state.get("herdr_sessions") or []:
+        if not isinstance(s, dict):
+            continue
+        s_cwd = (s.get("pane") or {}).get("cwd") or ""
+        if s_cwd and canonical_cwd(s_cwd) == target_cwd and agent_of_row(s) == agent:
+            out.append(s)
+    return out
+
+
+def row_for_capture(row: Optional[Dict[str, Any]], pane_pid: Optional[int],
+                    cwd: str = "", name: str = "", agent: str = "") -> Dict[str, Any]:
+    copy = dict(row) if isinstance(row, dict) else {}
+    if name and not copy.get("name"):
+        copy["name"] = name
+    if agent and not copy.get("agent"):
+        copy["agent"] = agent
+    pane = dict(copy.get("pane") or {})
+    if cwd and not pane.get("cwd"):
+        pane["cwd"] = cwd
+    if isinstance(pane_pid, int) and pane_pid > 0:
+        pane["pid"] = pane_pid
+    copy["pane"] = pane
+    return copy
+
+
+def _find_row(state: Dict[str, Any], name: str) -> Optional[Dict[str, Any]]:
+    if not name:
+        return None
+    for s in state.get("herdr_sessions") or []:
+        if isinstance(s, dict) and s.get("name") == name:
+            return s
+    return None
+
+
+def _parse_pid(raw: Any) -> Optional[int]:
+    if isinstance(raw, int):
+        return raw if raw > 0 else None
+    s = str(raw or "").strip()
+    return int(s) if s.isdigit() and int(s) > 0 else None
+
+
+def decide_stop(state: Dict[str, Any], name: str, agent: str, cwd: str,
+                herdr_alive: bool, pane_pid: Optional[int] = None,
+                purge: bool = False, home: Optional[str] = None,
+                claude_dir: Optional[str] = None) -> Dict[str, str]:
+    home_resolved = resolve_home(home)
+    claude_resolved = claude_dir or os.environ.get("CLAUDE_PROJECT_DIR") or f"{home_resolved}/.claude/projects"
+    row = _find_row(state, name)
+    row_ref = row if row is not None else ({"name": name} if name else {})
+    claimed = set(claimed_elsewhere(row_ref, state))
+    adapter = get_adapter(agent)
+    own = own_id(row, agent)
+
+    if own:
+        if own in claimed:
+            others = ", ".join(claiming_rows(row_ref, own, state))
+            return {
+                "captured": "",
+                "status": "sibling-claimed",
+                "purge_uuid": "",
+                "note": f"{own} is also recorded by {others}; registry needs fixing",
+            }
+        if adapter and adapter.id_lifecycle == POST_DISCOVERED:
+            if verify_session_uuid(cwd, agent, own, row, home_dir=home_resolved,
+                                   claude_dir=claude_resolved, mode="revalidate"):
+                return {
+                    "captured": own,
+                    "status": "already-set",
+                    "purge_uuid": own if purge else "",
+                    "note": "",
+                }
+            ctx = DiscoveryContext(workspace=cwd, agent_name=agent, home_dir=home_resolved,
+                                   claude_dir=claude_resolved, row=row, mode="revalidate")
+            can_purge = bool(purge and adapter.has_artifacts(own, ctx))
+            return {
+                "captured": "",
+                "status": "unverified-own",
+                "purge_uuid": own if can_purge else "",
+                "note": f"recorded id {own} no longer verifies; kept as is",
+            }
+
+    if adapter is None or adapter.id_lifecycle != POST_DISCOVERED:
+        found = find_workspace_uuid(cwd, agent, name, state, home_resolved, claude_resolved,
+                                    exclude_ids=claimed) if cwd else ""
+        if found and found in claimed:
+            others = ", ".join(claiming_rows(row_ref, found, state))
+            return {
+                "captured": "",
+                "status": "sibling-claimed",
+                "purge_uuid": "",
+                "note": f"{found} is also recorded by {others}; registry needs fixing",
+            }
+        return {
+            "captured": found,
+            "status": "resolved" if found else "no-candidate",
+            "purge_uuid": found if purge else "",
+            "note": "" if found else "nothing on disk yet",
+        }
+
+    if herdr_alive:
+        cap_row = row_for_capture(row, _parse_pid(pane_pid), cwd=cwd, name=name, agent=agent)
+        res = capture(cap_row, agent, state, home_dir=home_resolved)
+        if res.get("status") == "captured" and res.get("session_id"):
+            u = str(res["session_id"])
+            if u in claimed:
+                others = ", ".join(claiming_rows(row_ref, u, state))
+                return {
+                    "captured": "",
+                    "status": "sibling-claimed",
+                    "purge_uuid": "",
+                    "note": f"{u} is also recorded by {others}; registry needs fixing",
+                }
+            return {
+                "captured": u,
+                "status": "captured",
+                "purge_uuid": u if purge else "",
+                "note": "",
+            }
+        st = str(res.get("status") or "no-candidate")
+        reason = str(res.get("reason") or "")
+        return {
+            "captured": "",
+            "status": st,
+            "purge_uuid": "",
+            "note": f"{st}: {reason}" if reason else st,
+        }
+
+    return {
+        "captured": "",
+        "status": "herdr-dead",
+        "purge_uuid": "",
+        "note": "herdr session was already gone, so the pane that owns the conversation could not be checked; no id recorded",
+    }
+
+
+def decide_resume(state: Dict[str, Any], name: str, agent: str, workspace: str,
+                  herdr_alive: bool = False, pane_pid: Optional[int] = None,
+                  home: Optional[str] = None,
+                  claude_dir: Optional[str] = None) -> Dict[str, Any]:
+    home_resolved = resolve_home(home)
+    claude_resolved = claude_dir or os.environ.get("CLAUDE_PROJECT_DIR") or f"{home_resolved}/.claude/projects"
+    row = _find_row(state, name)
+    adapter = get_adapter(agent)
+    if row is None and not name and workspace:
+        same = same_type_rows(state, workspace, agent)
+        if len(same) == 1:
+            row = same[0]
+            name = str(row.get("name") or "")
+        elif adapter is None or adapter.id_lifecycle != POST_DISCOVERED:
+            creator = next(
+                (s for s in same if str(s.get("name") or "").endswith(f"-creator-{agent}")),
+                None,
+            )
+            if creator is not None:
+                row = creator
+                name = str(row.get("name") or "")
+    row_ref = row if row is not None else ({"name": name} if name else {})
+    claimed = set(claimed_elsewhere(row_ref, state))
+    own = own_id(row, agent)
+
+    if own:
+        if own in claimed:
+            others = ", ".join(claiming_rows(row_ref, own, state))
+            return {
+                "uuid": "",
+                "drop_stale_id": False,
+                "notes": [],
+                "error": (f"ERROR: {name}'s recorded id {own} is also recorded by {others}; "
+                          "refusing to resume on a conversation another session claims (Issue #63). "
+                          "One of these rows holds the wrong id - fix the registry before resuming."),
+            }
+        if adapter and adapter.id_lifecycle == POST_DISCOVERED:
+            if verify_session_uuid(workspace, agent, own, row, home_dir=home_resolved,
+                                   claude_dir=claude_resolved, mode="revalidate"):
+                return {"uuid": own, "drop_stale_id": False, "notes": [], "error": None}
+            if herdr_alive:
+                return {"uuid": own, "drop_stale_id": False, "notes": [], "error": None}
+            note = (f"NOTE: {name}'s recorded {agent} id {own} no longer verifies "
+                    "(its conversation is missing or empty); starting a new conversation (Issue #63)")
+            return {"uuid": "", "drop_stale_id": True, "notes": [note], "error": None}
+
+    if adapter is None or adapter.id_lifecycle != POST_DISCOVERED:
+        u = find_workspace_uuid(workspace, agent, name, state, home_resolved, claude_resolved,
+                                exclude_ids=claimed)
+        if u and u in claimed:
+            others = ", ".join(claiming_rows(row_ref, u, state))
+            return {
+                "uuid": "",
+                "drop_stale_id": False,
+                "notes": [],
+                "error": (f"ERROR: {name or agent}'s resolved id {u} is also recorded by {others}; "
+                          "refusing to resume on a conversation another session claims (Issue #63)."),
+            }
+        return {"uuid": u, "drop_stale_id": False, "notes": [], "error": None}
+
+    if herdr_alive:
+        cap_row = row_for_capture(row, _parse_pid(pane_pid), cwd=workspace, name=name, agent=agent)
+        res = capture(cap_row, agent, state, home_dir=home_resolved)
+        u = str(res["session_id"]) if res.get("status") == "captured" and res.get("session_id") else ""
+    else:
+        same = same_type_rows(state, workspace, agent)
+        n = len(same)
+        if name and all(r.get("name") != name for r in same):
+            n += 1
+        if n >= 2:
+            label = name or agent
+            note = (f"NOTE: {label} has no recorded {agent} id and {n} {agent} sessions share "
+                    f"{workspace}; the cache cannot tell them apart, so it starts a new conversation (Issue #63)")
+            return {"uuid": "", "drop_stale_id": False, "notes": [note], "error": None}
+        u = find_workspace_uuid(workspace, agent, name, state, home_resolved, claude_resolved,
+                                exclude_ids=claimed)
+
+    if u and u in claimed:
+        others = ", ".join(claiming_rows(row_ref, u, state))
+        return {
+            "uuid": "",
+            "drop_stale_id": False,
+            "notes": [],
+            "error": (f"ERROR: {name or agent}'s resolved id {u} is also recorded by {others}; "
+                      "refusing to resume on a conversation another session claims (Issue #63)."),
+        }
+    return {"uuid": u, "drop_stale_id": False, "notes": [], "error": None}
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    p = argparse.ArgumentParser(prog="python -m lib_py.agents.session_ids")
+    sub = p.add_subparsers(dest="cmd", required=True)
+
+    s_stop = sub.add_parser("stop")
+    s_stop.add_argument("--session", required=True)
+    s_stop.add_argument("--agent", required=True)
+    s_stop.add_argument("--cwd", default="")
+    s_stop.add_argument("--herdr-alive", default="0")
+    s_stop.add_argument("--pane-pid", default="")
+    s_stop.add_argument("--purge", default="0")
+
+    s_res = sub.add_parser("resume")
+    s_res.add_argument("--session", default="")
+    s_res.add_argument("--agent", required=True)
+    s_res.add_argument("--workspace", required=True)
+    s_res.add_argument("--herdr-alive", default="0")
+    s_res.add_argument("--pane-pid", default="")
+    s_res.add_argument("--shell", action="store_true")
+
+    a = p.parse_args(argv)
+    state = load_state_json()
+    q = shlex.quote
+
+    if a.cmd == "stop":
+        res = decide_stop(
+            state=state,
+            name=a.session,
+            agent=a.agent,
+            cwd=a.cwd,
+            herdr_alive=(a.herdr_alive == "1"),
+            pane_pid=_parse_pid(a.pane_pid),
+            purge=(a.purge == "1"),
+        )
+        print(f"CAPTURED_UUID={q(res['captured'])}")
+        print(f"CAPTURE_STATUS={q(res['status'])}")
+        print(f"PURGE_UUID={q(res['purge_uuid'])}")
+        print(f"STOP_ID_NOTE={q(res['note'])}")
+        return 0
+
+    res = decide_resume(
+        state=state,
+        name=a.session,
+        agent=a.agent,
+        workspace=a.workspace,
+        herdr_alive=(a.herdr_alive == "1"),
+        pane_pid=_parse_pid(a.pane_pid),
+    )
+    for note in res.get("notes") or []:
+        print(note, file=sys.stderr)
+    if res.get("error"):
+        print(res["error"], file=sys.stderr)
+        return 1
+    if a.shell:
+        print(f"RESUME_UUID={q(res['uuid'])}")
+        print(f"DROP_STALE_ID={'1' if res.get('drop_stale_id') else '0'}")
+    else:
+        print(res["uuid"])
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.agents/skills/lib_py/atomic_yaml.py

@@ -4,6 +4,7 @@
 import os, sys, tempfile, shutil, glob, subprocess, json, sqlite3, fcntl
 from datetime import datetime, timezone
 import yaml
+from lib_py import registry_format
 
 def atomic_dump_yaml_main():
     yaml_path = os.environ['YAML_PATH']
@@ -114,6 +115,27 @@ def atomic_dump_yaml_main():
         elif 'herdr_sessions' not in d:
             d['herdr_sessions'] = []
 
+        # Issue #71: an older registry is migrated here, under the lock and
+        # before the caller's mutation. It changes row fields only, so the
+        # YAML is rewritten whether or not the mutation changes anything.
+        from_version = registry_format.stored_version(d)
+        migrated_rows = 0
+        force_yaml = False
+        if from_version < registry_format.CURRENT:
+            d, migrated_rows = registry_format.migrate(d)
+            force_yaml = True
+        elif row:
+            # The DB is current; its YAML copy may not be (a migration whose
+            # YAML rewrite failed after the DB commit). Then rewrite it.
+            y = None
+            if os.path.exists(yaml_path):
+                try:
+                    with open(yaml_path) as f:
+                        y = yaml.safe_load(f)
+                except Exception:
+                    y = None
+            force_yaml = registry_format.stored_version(y) < registry_format.CURRENT
+
         old_sessions = get_all_sessions_status(d)
         # a mutation that replaces a row the monitor registered for a pane it
         # created itself (create_session.sh) drops that name from old_roles
@@ -167,7 +189,7 @@ def atomic_dump_yaml_main():
 
         conn.commit()
         
-        if new_sessions != old_sessions:
+        if force_yaml or new_sessions != old_sessions:
             if os.path.exists(yaml_path):
                 try:
                     shutil.copy2(yaml_path, yaml_path + '.bak')
@@ -207,6 +229,7 @@ def atomic_dump_yaml_main():
             _flock_f.close()
         except Exception:
             pass
+    return from_version, registry_format.stored_version(d), migrated_rows
 
 if __name__ == '__main__':
     atomic_dump_yaml_main()

.agents/skills/lib_py/delegation/daemon.py

@@ -2,7 +2,8 @@
 
 Behaviour is byte-for-byte compatible with the shell original (issue #5 phase 1,
 D5): same monitor path, same stderr wording and exit status when it is missing,
-same `pgrep -f` pre-check pattern, same log file, same "print the PID" contract.
+the same daemons found by the pre-check (matched exactly since Issue #72, see
+find_running), same log file, same "print the PID" contract.
 Callers capture stdout with $( ), so nothing else may be printed there.
 """
 from __future__ import annotations
@@ -39,20 +40,34 @@ def monitor_script_path(workdir: str) -> str:
 def find_running(monitor_script: str) -> List[str]:
     """PIDs of subscribers already running for this monitor script.
 
-    Uses the exact `pgrep -f` pattern the shell helper used, so a daemon started
+    A subscriber is a process whose command line is `<bash> <monitor_script>
-    by either implementation is found by the other. Multiple matches are returned
+    --subscribe[ ...]`, argv0 a bash, as both this module and the shell helper
-    in full: the legacy helper echoed every line and callers only ever echo it
+    start it. Issue #72: matched exactly (lib.sh _monitor_pids is the shell
-    back, so trimming here would be a silent behaviour change.
+    twin the legacy helper uses), not as a `pgrep -f` regex, because the update skill signals what this returns - a daemon of
+    another workspace the unescaped path also matched, or a process that only
+    names the path in an argument, is not this workspace's monitor. Multiple
+    matches are returned in full: the legacy helper echoed every line and
+    callers only ever echo it back, so trimming here would be a silent
+    behaviour change.
     """
     try:
         res = subprocess.run(
-            ["pgrep", "-f", "bash {} --subscribe".format(monitor_script)],
+            ["ps", "-A", "-ww", "-o", "pid=", "-o", "args="],
             capture_output=True, text=True,
         )
-    except OSError as exc:  # pragma: no cover - pgrep missing
+    except OSError as exc:  # pragma: no cover - ps missing
-        logger.warning("pgrep unavailable: %s", exc)
+        logger.warning("ps unavailable: %s", exc)
         return []
-    return [line for line in res.stdout.split() if line.strip()]
+    want = "{} --subscribe".format(monitor_script)
+    pids = []
+    for line in res.stdout.splitlines():
+        parts = line.strip().split(" ", 1)
+        if len(parts) != 2:
+            continue
+        argv0, _, rest = parts[1].partition(" ")
+        if os.path.basename(argv0) == "bash" and (rest == want or rest.startswith(want + " ")):
+            pids.append(parts[0])
+    return pids
 
 
 def _ignore_sighup():  # pragma: no cover - runs in the forked child

.agents/skills/lib_py/loop/eager.py

@@ -13,7 +13,7 @@ import sys
 from typing import List, Sequence
 
 # Framework version locked with framework constants
-FRAMEWORK_VERSION = "4.9.8"
+FRAMEWORK_VERSION = "4.12.0"
 
 CORE_MODULES: Sequence[str] = (
     # Standard library modules

.agents/skills/lib_py/loop/runner.py

@@ -676,6 +676,7 @@ class LoopRunner:
             if status == "completed":
                 if self.verbose:
                     log_success(f"Job '{job_id}' completed successfully.")
+                self._autopin(job_id)
                 return True
             elif status in ("error", "cancelled"):
                 log_error(f"Job '{job_id}' finished with status '{status}'.")
@@ -686,6 +687,23 @@ class LoopRunner:
         log_error(f"Job '{job_id}' timed out after {max_wait}s.")
         return False
 
+    def _autopin(self, job_id: str) -> None:
+        """Issue #40 recovery path: the handler the wrapper already ran for this
+        job (one job/token/attempt is handled once), run like the wrapper from
+        the control root's skills - lib_py.loop imports no sibling but
+        delegation (G9). Never fails the wait; the handler reports on stderr."""
+        skills = self.workspace_root / ".agents" / "skills"
+        if not (skills / "lib_py" / "agents" / "autopin.py").exists():
+            skills = Path(__file__).resolve().parents[2]
+        yaml_path = os.environ.get("AGENT_SESSIONS_YAML") or str(self.mam_dir / "agent-sessions.yaml")
+        env = dict(os.environ)
+        env["PYTHONPATH"] = str(skills) + (os.pathsep + env["PYTHONPATH"] if env.get("PYTHONPATH") else "")
+        try:
+            subprocess.run([sys.executable, "-m", "lib_py.agents.autopin", "--registry-dir", str(self.jobs_dir),
+                            "--job", job_id, "--yaml", yaml_path], env=env, timeout=300)
+        except Exception as exc:
+            log_warn(f"autopin for job '{job_id}' failed: {exc}")
+
     def _relay_while_submitting(self, label: str, since: str, stop: threading.Event) -> None:
         """Issue #30 (review R2): the wrapper runs until its job ends and its
         output is captured, so a blocked agent would only reach the loop log

.agents/skills/lib_py/pane_lock.py

@@ -18,6 +18,9 @@ one lock per server from the choice to the claim.
   pane_lock.py acquire --fd N     flock(LOCK_EX) on the inherited fd N; prints
                                   `locked`, or `timeout` once MAM_PANE_CLAIM_WAIT_S
                                   (default 120, minimum 1) has passed
+     [--shared] [--wait-env VAR]  Issue #72: LOCK_SH instead, and the wait read
+                                  from VAR (same default and minimum) - the
+                                  update admission lock (lib.sh mam_update_admit)
 
 The lock is a BSD flock, which belongs to the open file on fd 9: it outlives
 this helper and ends when the last process holding that fd ends, however it
@@ -63,11 +66,11 @@ def lock_path(session: Optional[str], env: Mapping[str, str]) -> str:
     return os.path.join(home, ".local", "state", "mam", "pane-lock", session + ".lock")
 
 
-def wait_s(env: Mapping[str, str]) -> int:
+def wait_s(env: Mapping[str, str], var: str = "MAM_PANE_CLAIM_WAIT_S") -> int:
-    return ints.positive_int(env.get("MAM_PANE_CLAIM_WAIT_S"), 1) or DEFAULT_WAIT_S
+    return ints.positive_int(env.get(var), 1) or DEFAULT_WAIT_S
 
 
-def acquire(fd: int, wait: float) -> str:
+def acquire(fd: int, wait: float, shared: bool = False) -> str:
     """`locked`, or `timeout` when the lock was not free within `wait` s. The
     deadline is on the monotonic clock; a step of the wall clock does not
     stretch or cut it. Only contention is waited out: any other error (a bad
@@ -75,7 +78,7 @@ def acquire(fd: int, wait: float) -> str:
     deadline = time.monotonic() + wait
     while True:
         try:
-            fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
+            fcntl.flock(fd, (fcntl.LOCK_SH if shared else fcntl.LOCK_EX) | fcntl.LOCK_NB)
             return "locked"
         except BlockingIOError:
             if time.monotonic() >= deadline:
@@ -90,11 +93,13 @@ def main(argv: Optional[List[str]] = None) -> int:
     s.add_argument("--session", default="")
     s = sub.add_parser("acquire")
     s.add_argument("--fd", type=int, required=True)
+    s.add_argument("--shared", action="store_true")
+    s.add_argument("--wait-env", default="MAM_PANE_CLAIM_WAIT_S")
     a = p.parse_args(argv)
     if a.cmd == "path":
         print(lock_path(a.session, os.environ))
     else:
-        print(acquire(a.fd, wait_s(os.environ)))
+        print(acquire(a.fd, wait_s(os.environ, a.wait_env), a.shared))
     return 0
 
 

.agents/skills/lib_py/registry_format.py

@@ -0,0 +1,92 @@
+"""Registry format version and its migration (Issue #71).
+
+The session registry (agent-sessions.yaml + agent-sessions.db) carries a
+top-level `registry_format` key; it lives in the DB `state` row like every
+other top-level key. A registry without it is format 1.
+
+  1: rows may carry `kill_command` and `start_command`, and `attach_command`
+     reads `HERDR_SESSION_NAME=<server> herdr agent attach <original name>`.
+  2: no `kill_command` / `start_command`; `attach_command` is
+     lib_py.agents.sanitize.attach_command(<row server>, <row name>).
+
+The writer (lib_py.atomic_yaml, the only code that writes the registry)
+migrates an older registry under its lock before the caller's mutation, and
+then rewrites the YAML as well as the DB. Readers (lib_py.state) never
+migrate; they see the old rows until the first write.
+
+Entry point (for #72, the update skill):
+
+    python -m lib_py.registry_format --yaml <agent-sessions.yaml>
+
+runs that migration through the writer (same lock, YAML rewritten), prints one
+line `registry-format: <from> -> <to>, rows changed: <n>` and exits 0 when the
+registry was migrated or already current, nonzero on error. Run it with the
+skills directory on PYTHONPATH (as lib.sh does), e.g.
+`PYTHONPATH=.agents/skills python3 -m lib_py.registry_format --yaml .mam/agent-sessions.yaml`.
+"""
+
+import argparse
+import copy
+import os
+import sys
+
+from lib_py.agents.sanitize import attach_command
+
+FORMAT_KEY = "registry_format"
+CURRENT = 2
+_DROPPED = ("kill_command", "start_command")
+
+
+def stored_version(d):
+    """The format a registry dict says it has (1 when it says nothing)."""
+    v = d.get(FORMAT_KEY) if isinstance(d, dict) else None
+    return v if isinstance(v, int) and not isinstance(v, bool) else 1
+
+
+def _row_server(s):
+    return s.get("herdr_session") or s.get("herdr_server") or "default"
+
+
+def migrate(d):
+    """Return (new registry dict, rows changed). Pure and idempotent: `d` is
+    not modified, and migrating the result again changes nothing. Every row is
+    migrated, `stopped` and `terminated` ones included."""
+    out = copy.deepcopy(d) if isinstance(d, dict) else {}
+    changed = 0
+    for s in out.get("herdr_sessions") or []:
+        if not isinstance(s, dict) or not s.get("name"):
+            continue
+        before = dict(s)
+        for k in _DROPPED:
+            s.pop(k, None)
+        s["attach_command"] = attach_command(_row_server(s), s["name"])
+        if s != before:
+            changed += 1
+    out[FORMAT_KEY] = CURRENT
+    return out, changed
+
+
+def main(argv=None):
+    ap = argparse.ArgumentParser(prog="python -m lib_py.registry_format",
+                                 description="Migrate the session registry to the current format.")
+    ap.add_argument("--yaml", required=True, help="path of agent-sessions.yaml")
+    a = ap.parse_args(argv)
+    yaml_path = os.path.abspath(a.yaml)
+    db_path = os.path.splitext(yaml_path)[0] + ".db"
+    if not (os.path.exists(yaml_path) or os.path.exists(db_path)):
+        print("registry-format: error: no registry at %s" % yaml_path, file=sys.stderr)
+        return 1
+    from lib_py.atomic_yaml import atomic_dump_yaml_main
+    os.environ["YAML_PATH"] = yaml_path
+    os.environ["AGENT_SESSIONS_MUTATION"] = "pass"
+    try:
+        frm, to, n = atomic_dump_yaml_main()
+    except (Exception, SystemExit) as exc:  # the writer refuses with SystemExit
+        print("registry-format: error: %s" % (exc,), file=sys.stderr)
+        return 1
+    print("registry-format: %d -> %d, rows changed: %d" % (frm, to, n), flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.agents/skills/lib_py/stall_watch.py

@@ -38,6 +38,7 @@ from typing import List, Optional
 
 from lib_py.agents.input_region import extract_input_region
 from lib_py.agents.registry import agent_of_row, get_adapter
+from lib_py.agents.sanitize import sanitize_herdr_agent_name
 from lib_py.delegation.engine import TERMINAL_STATUSES
 from lib_py.loop import watcher
 
@@ -154,8 +155,12 @@ class HerdrError(Exception):
 class HerdrSource(object):
     """Every herdr and OS read the judgement needs, in one place."""
 
-    def __init__(self, target, agent, session=None):
+    def __init__(self, target, agent, session=None, *, name):
         self.target, self.session = target, session or None
+        # `name` is the name herdr knows the agent by (#66), worked out once
+        # by StallWatch (#71); the kind is read off the original name, whose
+        # suffix a long name's hash replaces.
+        self.name = name
         self.agent = resolve_agent(agent, target)
         adapter = get_adapter(self.agent) if self.agent else None
         self.resident = tuple(adapter.resident_children) if adapter else ()
@@ -176,7 +181,7 @@ class HerdrSource(object):
         return proc.stdout
 
     def agent_get(self):
-        payload = json.loads(self._herdr("agent", "get", self.target) or "{}")
+        payload = json.loads(self._herdr("agent", "get", self.name) or "{}")
         return (payload.get("result") or {}).get("agent") or {}
 
     def agent_pid(self, pane_id):
@@ -199,12 +204,12 @@ class HerdrSource(object):
         if not self.agent:
             return None
         try:
-            return extract_input_region(self._herdr("agent", "read", self.target), self.agent) == ""
+            return extract_input_region(self._herdr("agent", "read", self.name), self.agent) == ""
         except ValueError:
             return None
 
     def prompt(self, text):
-        self._herdr("agent", "prompt", self.target, text)
+        self._herdr("agent", "prompt", self.name, text)
 
     def collect(self, sig: Signals) -> Signals:
         """Fill the process and input signals of an idle agent."""
@@ -221,7 +226,8 @@ class HerdrSource(object):
 class StallWatch(object):
     def __init__(self, args, source=None):
         self.args = args
-        self.src = source or HerdrSource(args.target, args.agent, args.herdr_session)
+        self.herdr_name = sanitize_herdr_agent_name(args.target)  # for herdr only; logs keep args.target
+        self.src = source or HerdrSource(args.target, args.agent, args.herdr_session, name=self.herdr_name)
         name = resolve_agent(args.agent, args.target)
         adapter = get_adapter(name) if name else None
         reliable = bool(adapter.agent_status_reliable) if adapter else True
@@ -323,7 +329,7 @@ class StallWatch(object):
                 until, tmo = ("idle", "done", "working"), 60000
             else:
                 until, tmo = ("idle", "done", "blocked"), 60000
-            out = watcher.wait_once(self.args.target, until=until, timeout_ms=tmo, session=self.args.herdr_session)
+            out = watcher.wait_once(self.herdr_name, until=until, timeout_ms=tmo, session=self.args.herdr_session)
             if self._wrapper_gone():  # round-2 review D2: before any notice
                 return RC_TERMINAL
             if out.kind in (watcher.TRANSPORT_ERROR, watcher.AGENT_NOT_FOUND):
@@ -425,7 +431,7 @@ def main(argv=None) -> int:
     p = argparse.ArgumentParser(description="notify-only stall watcher for one local herdr job (#30)")
     p.add_argument("--job", required=True)
     p.add_argument("--registry-dir", required=True)
-    p.add_argument("--target", required=True, help="herdr agent name of the job's session")
+    p.add_argument("--target", required=True, help="session name of the job (herdr is called with its sanitized form)")
     p.add_argument("--agent", required=True, help="agent CLI (adapter name)")
     p.add_argument("--herdr-session", default="")
     p.add_argument("--expect-dispatch-token", default=None)

.agents/skills/lib_py/update.py

@@ -0,0 +1,428 @@
+"""Decisions behind the multi-agent-mux-update skill (Issue #72).
+
+update.sh keeps the orchestration in shell (phase 1: this tree's code) and asks
+this module what needs parsing. Standard library only, Python 3.9.
+
+  python -m lib_py.update precheck --workspace W --herdr H
+      What refuses the update (comment 921, decisions 1 and 7): the running
+      rows of the registry (MAM_STATE_JSON, from lib.sh `load_state_json
+      strict`), every live herdr agent whose cwd is inside W on any server
+      `herdr session list --json` reports running (read only: the real herdr H,
+      never the shim, so no server is started), and the open jobs. The agent
+      that called the update - by (server, pane): pane_lock.caller_server and
+      HERDR_PANE_ID - is not counted, nor its row and its one running job.
+      Prints one line per blocker with how to clear it; rc 0 nothing blocks,
+      1 something does (a herdr or registry that cannot be read included).
+  python -m lib_py.update monitor --workspace W
+      JSON {"pids": [...], "lock": "free"|"held"}: the monitor daemons
+      daemon.find_running recognises, and whether .mam/monitor.lock is held.
+  python -m lib_py.update target-workspaces --workspace W --agent-session S --server V --herdr H
+      The workspaces other than W whose update admission a delegate submit
+      to `herdr:<name>` must take (decision 8), one per line: every installed
+      workspace at or above the target's cwd (its row's pane.cwd; with no row
+      the live agent's on server V) and its row's control_plane
+      workspace_root. Nothing for a non-herdr target. rc 1: herdr cannot
+      answer for a rowless target.
+  python -m lib_py.update target-workspaces --workspace W --cwd C
+      The same for an agent create or resume starts in C: every installed
+      workspace at or above C other than W.
+  python -m lib_py.update backup-registry --workspace W --dest D
+      Copies the registry into D under the registry's own write lock
+      (agent-sessions.db.lock, as atomic_yaml takes it): the DB through the
+      SQLite backup API (commits still in -wal included), the YAML and its
+      .bak as files. Prints the names it copied.
+"""
+from __future__ import annotations
+
+import argparse
+import fcntl
+import json
+import os
+import shlex
+import shutil
+import sqlite3
+import subprocess
+import sys
+from typing import Dict, Iterable, List, Mapping, Optional, Tuple
+
+from lib_py.agents.sanitize import sanitize_herdr_agent_name
+from lib_py.delegation import daemon
+from lib_py.delegation.engine import TERMINAL_STATUSES
+from lib_py.pane_lock import caller_server
+
+REGISTRY_FILES = ("agent-sessions.yaml", "agent-sessions.yaml.bak", "agent-sessions.db")
+HERDR_TIMEOUT_S = 20
+
+
+def _real(p: str) -> str:
+    return os.path.realpath(p)
+
+
+def _inside(path: str, root: str) -> bool:
+    if not path:
+        return False
+    p, r = _real(path), _real(root).rstrip(os.sep)
+    return p == r or p.startswith(r + os.sep)
+
+
+def row_server(row: dict) -> str:
+    return row.get("herdr_session") or row.get("herdr_server") or "default"
+
+
+# --------------------------------------------------------------------------- herdr
+
+class HerdrError(Exception):
+    pass
+
+
+def _herdr_json(herdr: str, args: List[str], env: Mapping[str, str]) -> dict:
+    # A pane's own scope ids would narrow the answer to the caller's workspace.
+    cenv = {k: v for k, v in env.items()
+            if k not in ("HERDR_WORKSPACE_ID", "HERDR_PANE_ID", "HERDR_TAB_ID")}
+    try:
+        res = subprocess.run([herdr, *args], env=cenv, stdin=subprocess.DEVNULL,
+                             capture_output=True, text=True, timeout=HERDR_TIMEOUT_S)
+    except (OSError, subprocess.SubprocessError) as exc:
+        raise HerdrError("`herdr %s` failed: %s" % (" ".join(args), exc))
+    if res.returncode != 0:
+        raise HerdrError("`herdr %s` exited %d: %s" % (" ".join(args), res.returncode,
+                                                         (res.stderr or "").strip()[:200]))
+    try:
+        out = res.stdout
+        return json.loads(out[out.index("{"):])
+    except ValueError:
+        raise HerdrError("`herdr %s` printed no JSON" % " ".join(args))
+
+
+def running_servers(herdr: str, env: Mapping[str, str]) -> List[str]:
+    d = _herdr_json(herdr, ["session", "list", "--json"], env)
+    sessions = d.get("sessions")
+    if not isinstance(sessions, list):
+        raise HerdrError("`herdr session list --json` has no sessions list")
+    return [s["name"] for s in sessions
+            if isinstance(s, dict) and s.get("running") and s.get("name")]
+
+
+def server_agents(herdr: str, server: str, env: Mapping[str, str]) -> List[dict]:
+    d = _herdr_json(herdr, ["--session", server, "agent", "list"], env)
+    agents = (d.get("result") or {}).get("agents")
+    if not isinstance(agents, list):
+        raise HerdrError("`herdr --session %s agent list` has no agents list" % server)
+    return [a for a in agents if isinstance(a, dict)]
+
+
+# --------------------------------------------------------------------------- jobs
+
+def _job_records(d: str) -> Iterable[Tuple[str, Optional[dict]]]:
+    """(path, record) per *.json; (path, None) when it cannot be read, and
+    (d, None) when d itself cannot be listed (not an empty registry)."""
+    try:
+        names = sorted(n for n in os.listdir(d) if n.endswith(".json") and not n.startswith("."))
+    except OSError:
+        yield d, None
+        return
+    for p in (os.path.join(d, n) for n in names):
+        try:
+            with open(p, encoding="utf-8") as fh:
+                rec = json.load(fh)
+        except (OSError, ValueError):
+            yield p, None
+            continue
+        yield p, rec if isinstance(rec, dict) else None
+
+
+def _is_jobs_dir(d: str) -> bool:
+    """d is a directory, or cannot be looked at (an unreadable parent): only an
+    absent d (or a file) is skipped."""
+    try:
+        os.stat(d)
+    except (FileNotFoundError, NotADirectoryError):
+        return False
+    except OSError:
+        return True
+    return os.path.isdir(d)
+
+
+def _is_open(rec: dict) -> bool:
+    return rec.get("status") not in TERMINAL_STATUSES and rec.get("dry_run") is not True
+
+
+def open_jobs(workspace: str, state: dict, env: Mapping[str, str]) -> List[dict]:
+    """Every open record (not completed/error/cancelled, not dry_run) in this
+    workspace's .mam/jobs and MAM_JOBS_DIR; in another row's
+    control_plane.mam_jobs_dir only those addressed to a row of this registry.
+    A record, or a directory, that cannot be read is open (path only)."""
+    own, seen = [], set()
+    for c in (os.path.join(workspace, ".mam", "jobs"), env.get("MAM_JOBS_DIR") or ""):
+        if c and _is_jobs_dir(c) and _real(c) not in seen:
+            seen.add(_real(c))
+            own.append(c)
+    rows = state.get("herdr_sessions") or []
+    names = {"herdr:%s" % s.get("name") for s in rows if s.get("name")}
+    other = []
+    for s in rows:
+        c = (s.get("control_plane") or {}).get("mam_jobs_dir") or ""
+        if c and _is_jobs_dir(c) and _real(c) not in seen:
+            seen.add(_real(c))
+            other.append(c)
+    out = []
+    for dirs, addressed_only in ((own, False), (other, True)):
+        for d in dirs:
+            for path, rec in _job_records(d):
+                if rec is None:
+                    out.append({"path": path, "unreadable": True, "dir": path == d})
+                elif _is_open(rec) and (not addressed_only or rec.get("agent_session") in names):
+                    out.append({"path": path, "job_id": rec.get("job_id") or "",
+                                "agent_session": rec.get("agent_session") or "",
+                                "status": rec.get("status"), "registry_dir": d})
+    return out
+
+
+# --------------------------------------------------------------------------- precheck
+
+def precheck(workspace: str, state: dict, herdr: str, env: Mapping[str, str]) -> List[str]:
+    """The lines that refuse the update; [] when nothing does."""
+    blockers: List[str] = []
+    stop = ("bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session %s"
+            " (resume it after the update with multi-agent-mux-resume)")
+    # A rowless agent: stop finds no row to take its server from (#71).
+    stop_rowless = ("bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session %s"
+                    " --herdr-session %s")
+
+    # The caller (decision 7): its server and pane, both or nothing.
+    me_server, me_pane = caller_server(env), env.get("HERDR_PANE_ID") or ""
+    me_name: Optional[str] = None
+    me_found = False
+
+    agents_by_server: Dict[str, List[dict]] = {}
+    try:
+        for server in running_servers(herdr, env):
+            agents_by_server[server] = server_agents(herdr, server, env)
+    except HerdrError as exc:
+        blockers.append("herdr: cannot list the live agents (%s); fix herdr and try again" % exc)
+
+    if me_server and me_pane:
+        for a in agents_by_server.get(me_server, []):
+            if a.get("pane_id") == me_pane:
+                me_found = True
+                me_name = a.get("name") or None   # a nameless pane is excluded by pane only
+                break
+
+    rows = state.get("herdr_sessions") or []
+    me_row = None
+    if me_name:
+        for s in rows:
+            if (s.get("status") == "running" and row_server(s) == me_server
+                    and s.get("name") and sanitize_herdr_agent_name(s["name"]) == me_name):
+                me_row = s
+                break
+
+    for s in rows:
+        if s.get("status") == "running" and s is not me_row:
+            blockers.append("session %s is running (server %s); stop it: %s"
+                            % (s.get("name"), row_server(s), stop % shlex.quote(s.get("name") or "")))
+
+    row_keys = {(row_server(s), sanitize_herdr_agent_name(s["name"]))
+                for s in rows if s.get("status") == "running" and s.get("name")}
+    for server, agents in agents_by_server.items():
+        for a in agents:
+            if me_found and server == me_server and a.get("pane_id") == me_pane:
+                continue
+            if not (_inside(a.get("cwd") or "", workspace)
+                    or _inside(a.get("foreground_cwd") or "", workspace)):
+                continue
+            name = a.get("name") or ""
+            if name and (server, name) in row_keys:
+                continue   # already listed as its running row
+            blockers.append("herdr agent %s (pane %s, server %s) runs in %s; stop it: %s"
+                            % (name or "<unnamed>", a.get("pane_id"), server, a.get("cwd"),
+                               stop_rowless % (shlex.quote(name), shlex.quote(server)) if name else
+                               "herdr --session %s pane close %s"
+                               % (shlex.quote(server), shlex.quote(a.get("pane_id") or ""))))
+
+    jobs = open_jobs(workspace, state, env)
+    if me_row is not None:
+        mine = [j for j in jobs if not j.get("unreadable")
+                and j.get("agent_session") == "herdr:%s" % me_row.get("name")
+                and j.get("status") == "running"]
+        if len(mine) == 1:
+            jobs = [j for j in jobs if j is not mine[0]]
+    for j in jobs:
+        if j.get("dir"):
+            blockers.append("jobs directory %s cannot be listed; fix its permissions, then try again"
+                            % j["path"])
+        elif j.get("unreadable"):
+            blockers.append("job record %s cannot be read; check it, then move or delete it by hand"
+                            % j["path"])
+        else:
+            blockers.append("job %s (%s, %s) is open; wait for it to end or close it: python "
+                            ".agents/skills/multi-agent-mux-delegate-job/scripts/registry.py"
+                            " --registry-dir %s close --job %s --request cancelled"
+                            % (j["job_id"], j["agent_session"] or "-", j["status"],
+                               j["registry_dir"], j["job_id"]))
+
+    if blockers and not me_found:
+        blockers.append("note: no herdr agent was found at the caller's server %r and pane %r, so"
+                        " nothing was excluded as the calling agent" % (me_server, me_pane))
+    return blockers
+
+
+# --------------------------------------------------------------------------- delegate target
+
+def _installed(d: str) -> bool:
+    """update.sh's own test of an installed workspace."""
+    return os.path.isfile(os.path.join(d, ".mam_deploy", "remove.sh")) or os.path.isfile(os.path.join(d, "remove.sh"))
+
+
+def target_workspaces(workspace: str, state: dict, agent_session: str, server: str,
+                      herdr: str, env: Mapping[str, str]) -> List[str]:
+    """Every installed workspace at or above the target's cwd - an update of
+    any of them counts that agent (decision 1) - and its row's
+    control_plane.workspace_root; the caller's own workspace left out. With
+    no row the cwd is the live agent's on <server> (the one delivery uses),
+    read with the real herdr. No herdr, a server that is not running, or no
+    such agent gives nothing (delivery then fails on its own); a herdr that
+    cannot answer raises HerdrError."""
+    if not agent_session.startswith("herdr:"):
+        return []
+    name = agent_session[len("herdr:"):]
+    row = next((s for s in state.get("herdr_sessions") or []
+                if isinstance(s, dict) and s.get("name") == name), None)
+    cwds, out = [], []
+    if row is not None:
+        cwds.append((row.get("pane") or {}).get("cwd") or "")
+        root = (row.get("control_plane") or {}).get("workspace_root") or ""
+        if root:
+            out.append(_real(root))
+    elif herdr and server in running_servers(herdr, env):
+        for a in server_agents(herdr, server, env):
+            if a.get("name") in (name, sanitize_herdr_agent_name(name)):
+                cwds += [a.get("cwd") or "", a.get("foreground_cwd") or ""]
+                break
+    return _others(workspace, out + installed_above(cwds))
+
+
+def installed_above(cwds: Iterable[str]) -> List[str]:
+    """Every installed workspace at or above each cwd."""
+    out = []
+    for cwd in cwds:
+        d = _real(cwd) if cwd else ""
+        while d:
+            if _installed(d):
+                out.append(d)
+            if os.path.dirname(d) == d:
+                break
+            d = os.path.dirname(d)
+    return out
+
+
+def _others(workspace: str, dirs: List[str]) -> List[str]:
+    me = _real(workspace)
+    return [d for i, d in enumerate(dirs) if d != me and d not in dirs[:i]]
+
+
+# --------------------------------------------------------------------------- monitor
+
+def monitor_state(workspace: str) -> dict:
+    pids = daemon.find_running(daemon.monitor_script_path(workspace))
+    lock = os.path.join(workspace, ".mam", "monitor.lock")
+    held = False
+    if os.path.exists(lock):
+        with open(lock, "a") as fh:
+            try:
+                fcntl.flock(fh, fcntl.LOCK_EX | fcntl.LOCK_NB)
+                fcntl.flock(fh, fcntl.LOCK_UN)
+            except BlockingIOError:
+                held = True
+    return {"pids": pids, "lock": "held" if held else "free"}
+
+
+# --------------------------------------------------------------------------- registry backup
+
+def backup_registry(workspace: str, dest: str) -> List[str]:
+    mam = os.path.join(workspace, ".mam")
+    db = os.path.join(mam, "agent-sessions.db")
+    os.makedirs(dest, exist_ok=True)
+    copied = []
+    with open(db + ".lock", "w") as lk:
+        fcntl.flock(lk, fcntl.LOCK_EX)
+        try:
+            if os.path.exists(db):
+                src = sqlite3.connect(db, timeout=60.0)
+                dst = sqlite3.connect(os.path.join(dest, "agent-sessions.db"))
+                try:
+                    src.backup(dst)
+                finally:
+                    dst.close()
+                    src.close()
+                copied.append("agent-sessions.db")
+            for name in REGISTRY_FILES:
+                p = os.path.join(mam, name)
+                if name != "agent-sessions.db" and os.path.exists(p):
+                    shutil.copy2(p, os.path.join(dest, name))
+                    copied.append(name)
+        finally:
+            fcntl.flock(lk, fcntl.LOCK_UN)
+    return copied
+
+
+def _state() -> dict:
+    return json.loads(os.environ.get("MAM_STATE_JSON") or "{}") or {}
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    p = argparse.ArgumentParser(prog="lib_py.update")
+    sub = p.add_subparsers(dest="cmd", required=True)
+    s = sub.add_parser("precheck")
+    s.add_argument("--workspace", required=True)
+    s.add_argument("--herdr", required=True)
+    s = sub.add_parser("monitor")
+    s.add_argument("--workspace", required=True)
+    s = sub.add_parser("target-workspaces")
+    s.add_argument("--workspace", required=True)
+    s.add_argument("--agent-session", default="")
+    s.add_argument("--cwd", default="")
+    s.add_argument("--server", default="default")
+    s.add_argument("--herdr", default="")
+    s = sub.add_parser("backup-registry")
+    s.add_argument("--workspace", required=True)
+    s.add_argument("--dest", required=True)
+    a = p.parse_args(argv)
+    ws = _real(a.workspace)
+    if a.cmd == "precheck":
+        try:
+            state = _state()
+        except ValueError as exc:
+            print("registry: cannot parse MAM_STATE_JSON (%s)" % exc)
+            return 1
+        lines = precheck(ws, state, a.herdr, os.environ)
+        for line in lines:
+            print(line)
+        return 1 if lines else 0
+    if a.cmd == "target-workspaces" and a.cwd:
+        for root in _others(ws, installed_above([a.cwd])):
+            print(root)
+        return 0
+    if a.cmd == "target-workspaces":
+        try:
+            state = _state()
+        except ValueError:
+            state = {}
+        try:
+            roots = target_workspaces(ws, state, a.agent_session, a.server, a.herdr, os.environ)
+        except HerdrError as exc:
+            print("cannot find %s live: %s" % (a.agent_session, exc), file=sys.stderr)
+            return 1
+        for root in roots:
+            print(root)
+        return 0
+    if a.cmd == "monitor":
+        print(json.dumps(monitor_state(ws)))
+        return 0
+    for name in backup_registry(ws, a.dest):
+        print(name)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.agents/skills/lib_py/workspace_uuid.py

@@ -1,7 +1,7 @@
 # workspace_uuid.py — workspace UUID discovery logic
 # Extracted from lib.sh find_workspace_uuid PYEOF block
 
-import os, sys, json
+import os, json
 from lib_py.verify_session import verify_session_uuid, mam_orchestrator_uuids, mam_row_own_uuid
 
 OWN_KEY = {
@@ -15,17 +15,10 @@ OWN_KEY = {
 
 from lib_py.paths import resolve_home
 
-def find_workspace_uuid_main():
+def find_workspace_uuid(ws, agent, target='', state=None, home=None, claude_dir=None, exclude_ids=()):
-    ws = os.environ['WS_ABS']
+    d = state if isinstance(state, dict) else {}
-    agent = os.environ['AGENT']
+    home = resolve_home(home)
-    home = resolve_home()
+    claude_project_dir = claude_dir or os.environ.get('CLAUDE_PROJECT_DIR', f"{home}/.claude/projects")
-    claude_project_dir = os.environ.get('CLAUDE_PROJECT_DIR', f"{home}/.claude/projects")
-    target = os.environ.get('TARGET_SESSION', '')
-
-    try:
-        d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
-    except Exception:
-        d = {}
 
     running_ids = set()
     for s_item in d.get('herdr_sessions', []):
@@ -38,6 +31,10 @@ def find_workspace_uuid_main():
                     running_ids.add(val)
 
     orchestrator_ids = set(mam_orchestrator_uuids())
+    if "MAM_ORCHESTRATOR_UUIDS" not in os.environ:
+        raw_orc = d.get('orchestrator_uuids')
+        if isinstance(raw_orc, list) and all(isinstance(x, str) and x.strip() for x in raw_orc):
+            orchestrator_ids |= set(raw_orc)
     if target:
         for s_item in d.get('herdr_sessions', []):
             if s_item.get('name') == target:
@@ -45,11 +42,7 @@ def find_workspace_uuid_main():
                 if own:
                     orchestrator_ids.discard(own)
 
-    def emit(u):
+    excluded = running_ids | orchestrator_ids | {u for u in (exclude_ids or ()) if u}
-        if u in running_ids or u in orchestrator_ids:
-            return
-        print(u)
-        sys.exit(0)
 
     # Fetch all sessions matching this workspace
     sessions = []
@@ -63,15 +56,17 @@ def find_workspace_uuid_main():
             if s.get('name') != target:
                 continue
             cand = s.get(OWN_KEY.get(agent, ''), None)
-            if cand and verify_session_uuid(ws, agent, cand, s, mode="revalidate"):
+            if cand and verify_session_uuid(ws, agent, cand, s, home_dir=home, claude_dir=claude_project_dir, mode="revalidate"):
-                emit(cand)
+                if cand not in excluded:
+                    return cand
 
     for s in sessions:
         name = s.get('name', '')
         if name.endswith(f"-creator-{agent}"):
             cand = s.get(OWN_KEY.get(agent, ''))
-            if cand and verify_session_uuid(ws, agent, cand, s, mode="revalidate"):
+            if cand and verify_session_uuid(ws, agent, cand, s, home_dir=home, claude_dir=claude_project_dir, mode="revalidate"):
-                emit(cand)
+                if cand not in excluded:
+                    return cand
 
     from lib_py.agents.registry import get_adapter
     from lib_py.agents.base import DiscoveryContext
@@ -80,9 +75,25 @@ def find_workspace_uuid_main():
     if adapter:
         ctx = DiscoveryContext(workspace=ws, agent_name=agent, home_dir=home, claude_dir=claude_project_dir)
         for cand in adapter.discover(ctx):
-            emit(cand)
+            if cand and cand not in excluded:
+                return cand
 
-    print('')
+    return ''
+
+
+def find_workspace_uuid_main():
+    ws = os.environ['WS_ABS']
+    agent = os.environ['AGENT']
+    home = resolve_home()
+    claude_project_dir = os.environ.get('CLAUDE_PROJECT_DIR', f"{home}/.claude/projects")
+    target = os.environ.get('TARGET_SESSION', '')
+
+    try:
+        d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
+    except Exception:
+        d = {}
+
+    print(find_workspace_uuid(ws, agent, target, d, home, claude_project_dir))
 
 if __name__ == '__main__':
     find_workspace_uuid_main()

.agents/skills/multi-agent-mux-create/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-create
 description: "Create a new agent session (claude, antigravity/agy) in a dedicated herdr session for context-preserving long-running work. Always creates a herdr session — never backgrounds with nohup/disown. Writes the new session to .mam/agent-sessions.yaml. Use when you want to start a fresh agent (no prior UUID) for a new project workspace."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]
@@ -146,12 +146,10 @@ herdr_sessions:
     cmd: claude
     cmd_full: claude --dangerously-skip-permissions
     cwd: /path/to/project
-  start_command: "HERDR_SESSION_NAME=<herdr_session> herdr new-session -d -s <SESSION_NAME> -x 140 -y 40 -c <WORKSPACE> <CMD_FULL>"
+  attach_command: "herdr --session <herdr_session> agent attach <herdr name of SESSION_NAME>"
-  attach_command: "HERDR_SESSION_NAME=<herdr_session> herdr agent attach <SESSION_NAME>"
-  kill_command: "HERDR_SESSION_NAME=<herdr_session> herdr kill-session -t <SESSION_NAME>"
 ```
 
-The three commands require `source .agents/skills/lib.sh` first — `new-session`/`kill-session` are tmux-compat pseudo-commands the shim translates, and `HERDR_SESSION_NAME` is what the shim reads to route to the right isolated herdr *session* (real `herdr` has no env-var-based scoping of its own; `herdr_session: default` needs no prefix at all).
+`attach_command` is a native herdr command and runs from any shell: it always names the server (`default` too) and names the agent as herdr registered it (lower case, at most 32 characters: `lib_py/agents/sanitize.py`). Start and stop sessions only through the create, resume and stop skills.
 
 ## Workflow
 
@@ -183,7 +181,7 @@ bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace
 | Exit | Meaning |
 |---|---|
 | 0 | Created; or `--dry-run` |
-| 1 | Pre-flight failure, nothing was spawned: workspace not a directory, herdr not installed, agent CLI not in `PATH`, agent not authenticated. After spawn: the task brief could not be written or the instruction injection failed (the session is rolled back) |
+| 1 | Pre-flight failure, nothing was spawned: workspace not a directory, herdr not installed, agent CLI not in `PATH`, agent not authenticated, or a same-cwd session of the same Class A agent did not record its conversation ID within `MAM_ID_ORDER_WAIT_S` (default 600), or an update of the workspace is in progress (`multi-agent-mux-update`). After spawn: the task brief could not be written or the instruction injection failed (the session is rolled back) |
 | 2 | Bad arguments; control-plane binding refused for a worktree; whitespace in a control-plane path that must be forwarded |
 | 3 | A herdr session of that name already exists (`multi-agent-mux-resume`, or `multi-agent-mux-stop` first) |
 | 4 | The YAML already has a `running` row of that name. The YAML write raises it after spawn, and the herdr session is rolled back. A row the monitor registered for this very pane while it was being created is replaced instead |
@@ -220,6 +218,7 @@ bash .agents/skills/multi-agent-mux-create/scripts/worktree_prepare.sh \
 - **Don't use `nohup`/`disown`/`setsid` for the agent itself** — those background the agent outside herdr. The whole point of this skill is *the herdr session is the supervisor*. `nohup` is OK only for *launching the wrapper* (which itself creates the herdr session via `herdr new-session -d`).
 - **Claude Session ID Auto-Assignment**: Fresh `claude` sessions automatically generate a new UUID (`mam_gen_uuid`) passed via `claude --session-id <uuid>`. `claude_session_id_own` is stored in `.mam/agent-sessions.yaml` with `session_id_source: assigned` and `session_id_verified: false`.
 - **First Message Materialization**: The transcript file `.jsonl` is created on disk when the first user prompt is sent. The monitor loop (`reconcile.sh`) verifies the transcript and promotes `session_id_verified: true` and `last_visible_status: pinned`.
+- **Post-discovered ids (agy, hermes, opencode, codex)**: these rows start with no id (`session_id_source: pending-discovery`). With `--onboard`, create pins the id itself once the onboarding job completes (Issue #40, `lib_py.agents.autopin`), monitor or not; later, every completed delegate job does the same until the id is set.
 - **Wrapper script MUST NOT be created via `hermes profile alias`** — that command writes a `hermes -p <profile>` wrapper that destroys the herdr behavior. Create wrappers manually (see `lab-landing-page-creator-claude` template).
 - **Always use the workspace-relative path** in herdr `cwd` — relative paths break when herdr respawns in a different shell context.
 
@@ -257,5 +256,5 @@ herdr agent read "$SESSION_NAME" --source visible --lines 20   # TUI ready = age
 
 - **Resuming an old conversation** → `multi-agent-mux-resume`
 - **Killing an existing session** → `multi-agent-mux-stop`
-- **Just attaching to an existing session** → `herdr agent attach <name>` (no skill needed)
+- **Just attaching to an existing session** → the row's `attach_command` (no skill needed)
 - **One-shot print mode (claude -p "...")** → no herdr needed; use `claude-code` skill's print mode

.agents/skills/multi-agent-mux-create/scripts/create_session.sh

@@ -260,7 +260,7 @@ spawn() {
         SESSION_UUID=""
         CMD_FULL="$("$(_delegate_py_bin)" -m lib_py.agents spawn-spec "$AGENT" "$RESOLVED_BIN" "" "true" 2>/dev/null || echo "${RESOLVED_BIN} --dangerously-skip-permissions")"
         [ -z "$CP_PREFIX" ] || echo "WARNING: the ~/.local/bin wrapper path bypasses herdr; the control-plane binding is recorded but not forwarded" >&2
-        nohup "$WRAPPER" >/dev/null 2>&1 &
+        ( mam_update_admit_release_all; exec nohup "$WRAPPER" >/dev/null 2>&1 ) &
         disown
       else
         HERDR_SESSION_NAME="$HERDR_SESSION_NAME" _herdr new-session -d -s "$SESSION_NAME" -x 140 -y 40 -c "$WORKSPACE" "$CP_PREFIX$CMD_FULL"
@@ -283,10 +283,14 @@ if [ "$DRY_RUN" = "1" ]; then
   echo "[dry-run] would spawn: herdr session '$SESSION_NAME' in $WORKSPACE (agent=$AGENT, herdr_session=${HERDR_SESSION_NAME:-default}, herdr_workspace=${MAM_WS_LABEL})"
   exit 0
 fi
-
+# Issue #63: a same-cwd session of this post-discovered agent records its id first (lib.sh mam_id_order_wait).
+mam_id_order_wait "$WORKSPACE" "$AGENT" "$SESSION_NAME" || exit 1
+# Issue #72: no new session while an update of the control root or of an
+# installed workspace the pane's cwd is in runs; held until the row is written
+# (lib.sh mam_update_admit_at).
+mam_update_admit_at "$WORKSPACE" || exit 1
 HERDR_EPOCH=$(date +%s)
 NOW_ISO=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
-
 spawn
 
 # _mark_row_rolled_back <status> <note>
@@ -361,7 +365,7 @@ cleanup_herdr_on_error() {
   if [ "$alive" = "1" ]; then
     _mark_row_rolled_back "running" "rollback-failed"
     echo "ERROR: rollback could not kill herdr session '$SESSION_NAME' (kill rc=$kill_rc) - it is still running." >&2
-    echo "       Clean it up with: HERDR_SESSION_NAME=${HERDR_SESSION_NAME:-default} herdr kill-session -t $SESSION_NAME" >&2
+    echo "       Clean it up with: bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session $SESSION_NAME --herdr-session ${HERDR_SESSION_NAME:-default}" >&2
     exit 43
   fi
   _mark_row_rolled_back "terminated" "rolled-back"
@@ -428,11 +432,6 @@ PANE_PID=$(_herdr list-panes -t "$SESSION_NAME" -F '#{pane_pid}' 2>/dev/null ||
 PANE_CWD=$(_herdr list-panes -t "$SESSION_NAME" -F '#{pane_current_path}' 2>/dev/null || echo "$WORKSPACE")
 PANE_CMD=$(_herdr list-panes -t "$SESSION_NAME" -F '#{pane_current_command}' 2>/dev/null || echo "$AGENT")
 
-# 시작 명령
-# NOTE: this must match what `spawn()` actually ran above — env-var-driven
-# herdr server shim (HERDR_SESSION_NAME picked up by the lib.sh shim).
-START_CMD="HERDR_SESSION_NAME=${HERDR_SESSION_NAME:-default} herdr new-session -d -s \"$SESSION_NAME\" -x 140 -y 40 -c \"$WORKSPACE\" \"$CMD_FULL\""
-
 # If --onboard is specified, automatically build the onboarding prompt (if session is ready)
 if [ "$ONBOARD" = "1" ] && [ -z "$SUBMIT_JOB_PROMPT" ] && [ -z "$LAST_VISIBLE_STATUS_OVERRIDE" ]; then
   SUBMIT_JOB_PROMPT="You are a newly spawned $ROLE Team Leader agent in this workspace. Without making any non-standard pre-preparations or modifying files directly, proceed immediately to align yourself with the project context by performing the following tasks:
@@ -508,12 +507,13 @@ fi
 atomic_dump_yaml "$AGENT_SESSIONS_YAML" \
   SESSION_NAME="$SESSION_NAME" AGENT="$AGENT" NOW_ISO="$NOW_ISO" \
   HERDR_EPOCH="$HERDR_EPOCH" PANE_PID="$PANE_PID" PANE_CWD="$PANE_CWD" \
-  CMD_FULL="$CMD_FULL" START_CMD="$START_CMD" CHILD_PID="$CHILD_PID" \
+  CMD_FULL="$CMD_FULL" CHILD_PID="$CHILD_PID" \
   HERDR_SESSION_NAME="${HERDR_SESSION_NAME:-default}" \
   MAM_WS_LABEL="$MAM_WS_LABEL" \
   SESSION_UUID="$SESSION_UUID" \
   LAST_VISIBLE_STATUS_OVERRIDE="${LAST_VISIBLE_STATUS_OVERRIDE:-}" \
   DELEGATE_JOB_ID="$DELEGATE_JOB_ID" ROLE="$ROLE" CONTROL_PLANE_JSON="$CP_JSON" <<'PYEOF'
+from lib_py.agents.sanitize import attach_command
 name = os.environ['SESSION_NAME']
 agent = os.environ['AGENT']
 role = os.environ['ROLE']
@@ -567,9 +567,7 @@ entry = {
         'cmd_full': os.environ['CMD_FULL'],
         'cwd': os.environ['PANE_CWD'],
     },
-    'start_command': os.environ['START_CMD'],
+    'attach_command': attach_command(server_name, name),
-    'attach_command': f'HERDR_SESSION_NAME={server_name} herdr agent attach {name}',
-    'kill_command': f'HERDR_SESSION_NAME={server_name} herdr kill-session -t {name}',
 }
 
 if agent == 'claude':
@@ -644,6 +642,7 @@ snap['cwd'] = os.environ['PANE_CWD']
 print(f"appended: {name}", flush=True)
 PYEOF
 ROW_APPENDED=1
+mam_update_admit_release_all
 
 echo
 echo "=== created ==="
@@ -751,6 +750,9 @@ If you delegate any part of it with multi-agent-mux-delegate-job submit, add --p
   case "$ONBOARD_STATUS" in
     completed)
       echo "onboarding completed: job $DELEGATE_JOB_ID ($(( $(date +%s) - ONBOARD_T0 ))s)"
+      # Issue #40: the first turn is done, so a post-discovered id is on disk -
+      # pin it now instead of waiting for a monitor (worktree creators run none).
+      delegate_autopin_completed "$DELEGATE_JOB_ID" "$DELEGATE_JOB_TOKEN" "$task_reg_dir"
       ;;
     *)
       # The session is kept, as for a missing handshake above: the row says
@@ -770,6 +772,6 @@ fi
 trap - EXIT
 echo "agent-sessions.yaml updated"
 echo
-echo "Attach:  herdr session attach $SESSION_NAME"
+echo "Attach:  $(session_attach_command "$SESSION_NAME" "${HERDR_SESSION_NAME:-default}")"
 echo "Delete:  use multi-agent-mux-stop skill"
 echo "Resume:  use multi-agent-mux-resume skill (after first message creates a session id)"

.agents/skills/multi-agent-mux-delegate-job/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-delegate-job
 description: "Delegate a unit of work to any autonomous agent (claude-code, hermes, agy, grok-build, codex, or a human) and observe it asynchronously over an MQTT event channel. Supported roles include orchestrator, worker, and reviewer."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos, windows]

.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job

@@ -301,6 +301,26 @@ cmd_submit() {
   local reg_dry=()
   if [[ "$DRY_RUN" == "1" ]]; then reg_dry=(--dry-run); fi
 
+  # Issue #72: no job is registered while an update of this registry's
+  # workspace or of one the target is in (lib_py.update target-workspaces:
+  # its row's, or with no row the live agent's on the server delivery uses)
+  # runs; each is held, fd 7 then 20.., until the record is written (lib.sh
+  # mam_update_admit). A dry-run record is never dispatched and is not
+  # counted by the update.
+  local admit_fds=() target_ws tws fd=20
+  if [[ "$DRY_RUN" != "1" ]]; then
+    target_ws="$(MAM_STATE_JSON="$(load_state_json)" PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" "$PY" -m lib_py.update \
+      target-workspaces --workspace "$WORKSPACE_ROOT" --agent-session "$AGENT_SESSION" \
+      --server "$(_is_remote "$AGENT_SESSION" || resolve_herdr_session "${AGENT_SESSION#herdr:}" "$WORKDIR" 2>/dev/null)" \
+      --herdr "$(_resolve_real_herdr_path || true)")" \
+      || { echo "ERROR: cannot resolve the workspace of $AGENT_SESSION; nothing was registered" >&2; exit 1; }
+    mam_update_admit "$WORKSPACE_ROOT" || exit 1
+    while IFS= read -r tws; do
+      [[ -n "$tws" ]] || continue
+      mam_update_admit "$tws" "$fd" || exit 1
+      admit_fds+=("$fd"); fd=$((fd + 1))
+    done <<< "$target_ws"
+  fi
   # 1) register job (prints the new job id)
   JOB_ID="$("$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" register \
       "${reg_prompt[@]}" --agent "$AGENT" --agent-session "$AGENT_SESSION" --role "$DELEGATE_ROLE" \
@@ -310,6 +330,10 @@ cmd_submit() {
       --job-type "$TYPE" --reviewer "$REVIEWER" --reviewer-session "$REVIEWER_SESSION" \
       --max-iterations "$MAX_ITERATIONS" ${reg_parent[@]+"${reg_parent[@]}"} ${reg_dry[@]+"${reg_dry[@]}"})"
   echo "registered job: $JOB_ID"
+  if [[ "$DRY_RUN" != "1" ]]; then
+    mam_update_admit_release
+    for fd in ${admit_fds[@]+"${admit_fds[@]}"}; do mam_update_admit_release "$fd"; done
+  fi
 
   # 1-1) Provision job directory and write direct brief.md (MAM Job Restructuring)
   local job_dir="$REGISTRY_DIR/$JOB_ID"
@@ -451,6 +475,11 @@ EOF
 
     finalize_unfinished "$JOB_ID" "$job_status" "$sub_rc" "direct"
     job_status="${FINAL_JOB_STATUS:-$job_status}"
+    # Issue #40: this subscriber verified the `completed` (or the disk did) -
+    # pin the session's post-discovered id now, daemon or not.
+    if [ "$job_status" = "completed" ]; then
+      delegate_autopin_completed "$JOB_ID" "$_disp_tok" "$REGISTRY_DIR"
+    fi
 
     # Last stdout line: the persistent audit-log dir for this job (see SKILL.md
     # "Audit Logs"). Callers can scrape `tail -n1` to find it.
@@ -890,8 +919,8 @@ finalize_unfinished() {
   FINAL_JOB_STATUS="$final"
   if [ "$step" = "probe" ]; then
     local sess="${target_sess#herdr:}" target_agent diag="no"
-    target_agent=$(_sanitize_herdr_agent_name "$sess")
+    target_agent=$(_sanitize_herdr_agent_name "$sess") || target_agent=""
-    _within_deadline "$deadline" _agent_still_working "$sess" "$target_agent" && diag="yes"
+    [ -n "$target_agent" ] && _within_deadline "$deadline" _agent_still_working "$sess" "$target_agent" && diag="yes"
     echo "liveness: no wire event for ${IDLE_TIMEOUT}s on job $job_id; herdr/pane says busy=$diag (diagnostic only, not evidence)" >&2
   fi
   # The answer comes back on fd 3: stdout carries registry.py's close output.
@@ -1013,7 +1042,7 @@ inject_agent() {
     return 1
   fi
 
-  echo "작업이 세션 '$sess'에 전송되었습니다. (연결하려면: HERDR_SESSION_NAME=$HERDR_SESSION_NAME herdr agent attach $sess — lib.sh를 source한 셸에서 실행)"
+  echo "작업이 세션 '$sess'에 전송되었습니다. (연결하려면: $(session_attach_command "$sess" "${HERDR_SESSION_NAME:-default}"))"
   trap - EXIT
   return 0
 }

.agents/skills/multi-agent-mux-loop/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-loop
 description: "Run an autonomous planning-execution-review loop using multiple agents (Planner, Creator, Reviewers) in the workspace. Automatically orchestrates plan discussion, code changes, and peer reviews until a unanimous PASS is achieved or the maximum iteration limit is reached."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]

.agents/skills/multi-agent-mux-loop/scripts/run_loop.sh

@@ -244,6 +244,9 @@ log_error() {
   echo -e "\033[1;31m[✗]\033[0m $1"
 }
 
+# Issue #72: no loop starts while an update runs; held until the loop marker
+# is published (lib.sh mam_update_admit), released before the loop body runs.
+mam_update_admit "$MAM_REAL_ROOT" || exit 1
 _mam_acquire_rc=0
 mam_acquire_loop_lock "$MAM_LOOP_MARKER" || _mam_acquire_rc=$?
 case "$_mam_acquire_rc" in
@@ -262,6 +265,7 @@ case "$_mam_acquire_rc" in
     ;;
 esac
 trap _mam_release_guard EXIT INT TERM HUP
+mam_update_admit_release
 rm -f "$MAM_REAL_ROOT/.agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job".*.tmp 2>/dev/null || true
 
 # --all-reviewer silently takes precedence over an explicit --reviewer list;

.agents/skills/multi-agent-mux-monitor/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-monitor
 description: "Run a long-lived reconciler that watches .mam/agent-sessions.yaml against the actual herdr/agent runtime state and reconciles them. Use when you want live visibility into which agent sessions are running, which are dead, which have stale YAML entries, and which have new session ids that haven't been recorded yet. Runs as a persistent loop (`reconcile.sh --subscribe`) that keeps going until it times out, idles out, or is interrupted."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]
@@ -161,6 +161,8 @@ YAML:  no such session
          → report: "lab-landing-page-creator-claude: session id materialized b3a7...c2f"
   ```
 - **C-ambiguous. Multiple candidates detected**: If multiple candidate transcripts match an unassigned session, the monitor avoids random pinning, reports `C-ambiguous`, and sets `last_visible_status: "ambiguous: N candidates"`.
+- **Post-discovered ids (agy, hermes, opencode, codex; Issue #40)**: drift C asks the adapter's `capture_active_session_id`, the decision the completed handler (`lib_py.agents.autopin`) also uses. A candidate must be newer than the session, pass verification and be recorded by no other row. For agy, `last_conversations.json[cwd]` only proposes the id: the conversation's presence lock (or DB) must be held by the row's pane process or a descendant, and an id the cache maps to another workspace is rejected. The conversations folder is no longer scanned. A pin records `session_id_source: discovered` and `session_id_verified: true`.
+- **Pinned without a monitor**: the side that verified a job's `completed` (the delegate-job wrapper, `create --onboard`, the loop's job wait) pins the session's post-discovered id at once, so worktree creators (`MAM_NO_SUBSCRIBER_DAEMON=1`) need no reconcile. One job/token/attempt is handled once; a failed or ambiguous capture leaves `last_visible_status: "autopin <status> (job <id>): <reason>"` and the job's result unchanged.
 
 ## Pitfalls
 

.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh

@@ -420,7 +420,7 @@ import yaml
 
 from lib_py.verify_session import verify_session_uuid, workspace_key
 from lib_py.agents.registry import get_adapter
-from lib_py.agents.base import DiscoveryContext, _ro_connect
+from lib_py.agents import autopin
 
 def _slug(path):
     if not path:
@@ -554,17 +554,9 @@ def pane_meta(session, srv):
 from lib_py.agents.registry import get_adapter, own_key as _get_own_key, agent_of_row
 
 def _pin_and_verify_resume(s, agent, cwd, uuid, degraded=False):
-    own_key_field = _get_own_key(agent)
+    # the completed handler's pin (Issue #40): own id, source and verified together
-    if own_key_field:
+    autopin.pin_row(s, agent, uuid)
-        s[own_key_field] = uuid
+    s['last_visible_status'] = autopin.resume_dry_run(skills_dir, cwd, agent, s['name'])
-    s['last_visible_status'] = 'pinned'
-    resume_cmd = ['bash', os.path.join(skills_dir, 'multi-agent-mux-resume', 'scripts', 'resume_session.sh'),
-                  '--workspace', cwd, '--agent', agent, '--session', s['name'], '--dry-run']
-    res = subprocess.run(resume_cmd, capture_output=True, text=True)
-    if res.returncode == 0:
-        s['last_visible_status'] = 'resume_verified'
-    else:
-        s['last_visible_status'] = f"resume dry-run failed: {res.stderr.strip() or res.stdout.strip()}"
     
     id_name = 'session' if agent == 'claude' else 'conversation'
     if not degraded:
@@ -574,7 +566,7 @@ def _pin_and_verify_resume(s, agent, cwd, uuid, degraded=False):
     actions.append(f"updated {id_name} id: {uuid}")
 
 
-from lib_py.agents.sanitize import sanitize_herdr_agent_name as _sanitize
+from lib_py.agents.sanitize import sanitize_herdr_agent_name as _sanitize, attach_command
 
 yaml_sessions = d.get('herdr_sessions', [])
 yaml_session_names = {s['name'] for s in yaml_sessions if s.get('name')}
@@ -664,7 +656,6 @@ if herdr_confirmed:
         _ambient = os.environ.get('HERDR_SESSION_NAME', '')
         if srv == 'default' and _ambient and _ambient != 'default':
             srv = _ambient
-        server_opt = f"-L {srv} " if srv != 'default' else ""
         # The shim resolves this from the pane's root process. Fall back to now
         # only if that failed: 'now' can merely over-estimate creation time,
         # which tightens the stale-transcript guard, whereas 0 disables it and
@@ -682,9 +673,7 @@ if herdr_confirmed:
             'herdr_server': srv,
             'herdr_workspace': _slug(pm['cwd']),
             'pane': {'index': 0, 'pid': pm['pid'], 'cmd': agent, 'cmd_full': cmd_full, 'cwd': pm['cwd']},
-            'start_command': f'HERDR_SESSION_NAME={srv} herdr new-session -d -s "{name}" -x 140 -y 40 -c "{pm["cwd"]}" "{cmd_full}"',
+            'attach_command': attach_command(srv, name),
-            'attach_command': f'HERDR_SESSION_NAME={srv} herdr agent attach {name}',
-            'kill_command': f'herdr {server_opt}kill-session -t {name}',
             'last_visible_status': 'running',
             'last_visible_note': 'auto-registered by monitor',
         }
@@ -783,314 +772,40 @@ for s in d.get('herdr_sessions', []):
         else:
             _pin_and_verify_resume(s, 'claude', cwd, uuid, degraded=True)
 
-# === drift C (agy): agy 새 session id materialize (per-row own id) ===
+# === drift C (agy), drift C (hermes), drift C (opencode), drift C (codex) ===
+# Post-discovered ids (Issue #40): the adapter's capture_active_session_id
+# decides - the same decision the completed handler (lib_py.agents.autopin)
+# makes - so the two paths cannot drift apart. Exactly one verified candidate
+# newer than the session that no other row records; agy additionally needs its
+# presence lock held by this row's pane (its cwd cache alone proves nothing).
 for s in d.get('herdr_sessions', []):
-    if row_agent(s) != 'agy':
+    agent = row_agent(s)
+    if agent not in ('agy', 'hermes', 'opencode', 'codex'):
         continue
     if s.get('status') != 'running':
         continue
-    if s.get('agy_conversation_id_own'):
+    if s.get(OWN_KEY_BY_AGENT[agent]):
         continue
     cwd = (s.get('pane') or {}).get('cwd', '')
     if not cwd:
         continue
-    conv_dir = f"{home}/.gemini/antigravity-cli/conversations"
+    res = autopin.capture(s, agent, d, home_dir=home)
-    if not os.path.isdir(conv_dir):
+    if res['status'] == 'ambiguous':
-        continue
+        n = len(res['candidates'])
-    dbs = sorted(glob.glob(f"{conv_dir}/*.db"), key=os.path.getmtime, reverse=True)
-    
-    sibling_claimed = [
-        other.get('agy_conversation_id_own')
-        for other in d.get('herdr_sessions', [])
-        if other is not s
-        and (other.get('pane') or {}).get('cwd') == cwd
-        and other.get('status') not in ('stopped', 'terminated')
-        and other.get('agy_conversation_id_own')
-    ]
-    s_eval = dict(s)
-    s_eval['_sibling_claimed_uuids'] = sibling_claimed
-
-    valid_candidates = []
-    for db in dbs:
-        uuid = os.path.basename(db)[:-3]
-        if verify_session_uuid(cwd, 'agy', uuid, s_eval, mode="discover"):
-            valid_candidates.append(uuid)
-            
-    if len(valid_candidates) > 1:
         drifts.append({'class': 'C-ambiguous', 'name': s['name'],
-                       'msg': f"{s['name']}: {len(valid_candidates)} candidate transcripts newer than session epoch; not pinning"})
+                       'msg': f"{s['name']}: {n} candidate transcripts newer than session epoch; not pinning"})
-        s['last_visible_status'] = f"ambiguous: {len(valid_candidates)} candidates"
+        s['last_visible_status'] = f"ambiguous: {n} candidates"
         actions.append(f"ambiguous candidates: {s['name']}")
-    if len(valid_candidates) == 1:
+    elif res['status'] == 'captured':
-        uuid = valid_candidates[0]
+        uuid = res['session_id']
-        cmd = ['bash', '-c', f'source "{lib_sh}" && verify_tui_viewport "{s["name"]}" "agy" "{cwd}"']
+        cmd = ['bash', '-c', f'source "{lib_sh}" && verify_tui_viewport "{s["name"]}" "{agent}" "{cwd}"']
         rc = subprocess.run(cmd).returncode
         if rc == 0:
-            _pin_and_verify_resume(s, 'agy', cwd, uuid, degraded=False)
+            _pin_and_verify_resume(s, agent, cwd, uuid, degraded=False)
         elif rc == 1:
             drifts.append({'class': 'C-warn', 'name': s['name'], 'msg': f"{s['name']}: TUI viewport mismatch for candidate {uuid} — not pinned, will retry next cycle"})
         else:
-            _pin_and_verify_resume(s, 'agy', cwd, uuid, degraded=True)
+            _pin_and_verify_resume(s, agent, cwd, uuid, degraded=True)
-
-# === drift C (hermes): hermes 새 session id materialize (per-row own id) ===
-for s in d.get('herdr_sessions', []):
-    if row_agent(s) != 'hermes':
-        continue
-    if s.get('status') != 'running':
-        continue
-    if s.get('hermes_conversation_id_own'):
-        continue
-    cwd = (s.get('pane') or {}).get('cwd', '')
-    if not cwd:
-        continue
-    hdb = f"{home}/.hermes/state.db"
-    if not os.path.exists(hdb):
-        continue
-
-    epoch_threshold = s.get('herdr_session_epoch', 0)
-
-    sibling_claimed = [
-        other.get('hermes_conversation_id_own')
-        for other in d.get('herdr_sessions', [])
-        if other is not s
-        and (other.get('pane') or {}).get('cwd') == cwd
-        and other.get('status') not in ('stopped', 'terminated')
-        and other.get('hermes_conversation_id_own')
-    ]
-    s_eval = dict(s)
-    s_eval['_sibling_claimed_uuids'] = sibling_claimed
-
-    valid_candidates = []
-    try:
-        conn = _ro_connect(hdb)
-        rows = conn.execute(
-            "SELECT id FROM sessions WHERE cwd=? AND started_at >= ? ORDER BY started_at DESC LIMIT 20",
-            (cwd, epoch_threshold)
-        ).fetchall()
-        conn.close()
-        for (uuid,) in rows:
-            if uuid in (sibling_claimed or []):
-                continue
-            if verify_session_uuid(cwd, 'hermes', uuid, s_eval, mode="discover"):
-                valid_candidates.append(uuid)
-    except Exception:
-        pass
-
-    if len(valid_candidates) > 1:
-        drifts.append({'class': 'C-ambiguous', 'name': s['name'],
-                       'msg': f"{s['name']}: {len(valid_candidates)} candidate transcripts newer than session epoch; not pinning"})
-        s['last_visible_status'] = f"ambiguous: {len(valid_candidates)} candidates"
-        actions.append(f"ambiguous candidates: {s['name']}")
-    if len(valid_candidates) == 1:
-        uuid = valid_candidates[0]
-        cmd = ['bash', '-c', f'source "{lib_sh}" && verify_tui_viewport "{s["name"]}" "hermes" "{cwd}"']
-        rc = subprocess.run(cmd).returncode
-        if rc == 0:
-            _pin_and_verify_resume(s, 'hermes', cwd, uuid, degraded=False)
-        elif rc == 1:
-            drifts.append({'class': 'C-warn', 'name': s['name'], 'msg': f"{s['name']}: TUI viewport mismatch for candidate {uuid} — not pinned, will retry next cycle"})
-        else:
-            _pin_and_verify_resume(s, 'hermes', cwd, uuid, degraded=True)
-
-# === drift C (opencode): opencode 새 session id materialize (per-row own id) ===
-for s in d.get('herdr_sessions', []):
-    if row_agent(s) != 'opencode':
-        continue
-    if s.get('status') != 'running':
-        continue
-    if s.get('opencode_session_id_own'):
-        continue
-    cwd = (s.get('pane') or {}).get('cwd', '')
-    if not cwd:
-        continue
-
-    # Resolve DB path via shared OpenCodeAgentAdapter helper with fallbacks
-    odb = None
-    try:
-        op_adapter = get_adapter('opencode')
-        if op_adapter:
-            odb = op_adapter._resolve_db(DiscoveryContext(workspace=cwd, agent_name='opencode', home_dir=home))
-    except Exception:
-        pass
-
-    if not odb:
-        opencode_base = f"{home}/.local/share/opencode"
-        candidates = [
-            f"{opencode_base}/opencode.db",
-            f"{opencode_base}/storage.db",
-        ]
-        for cand in candidates:
-            if os.path.exists(cand):
-                odb = cand
-                break
-        if not odb and os.path.isdir(f"{opencode_base}/project"):
-            for root, _, files in os.walk(f"{opencode_base}/project"):
-                for f in files:
-                    if f.endswith(".db"):
-                        odb = os.path.join(root, f)
-                        break
-                if odb and os.path.exists(odb):
-                    break
-
-    if not odb or not os.path.exists(odb):
-        continue
-
-    epoch_threshold = s.get('herdr_session_epoch', 0)
-
-    sibling_claimed = [
-        other.get('opencode_session_id_own')
-        for other in d.get('herdr_sessions', [])
-        if other is not s
-        and (other.get('pane') or {}).get('cwd') == cwd
-        and other.get('status') not in ('stopped', 'terminated')
-        and other.get('opencode_session_id_own')
-    ]
-    s_eval = dict(s)
-    s_eval['_sibling_claimed_uuids'] = sibling_claimed
-
-    valid_candidates = []
-    try:
-        # read-only: nothing is created or removed beside the agent's db (Issue #60)
-        conn = _ro_connect(odb)
-        cursor = conn.cursor()
-        # opencode 2.x keeps sessions in session_v2 (a migrated 1.x `session`
-        # table is no longer written).
-        cursor.execute("PRAGMA table_info(session_v2)")
-        cols = [col[1] for col in cursor.fetchall()]
-        if cols:
-            cwd_col = "directory" if "directory" in cols else ("cwd" if "cwd" in cols else None)
-            time_col = "time_created" if "time_created" in cols else ("created_at" if "created_at" in cols else ("started_at" if "started_at" in cols else None))
-
-            query = "SELECT id FROM session_v2"
-            params = []
-            where_clauses = []
-            if "parent_id" in cols:
-                # a subagent's session shares the directory and is newer
-                where_clauses.append("parent_id IS NULL")
-            if cwd_col and cwd:
-                where_clauses.append(f"{cwd_col} = ?")
-                params.append(cwd)
-            if time_col and epoch_threshold:
-                if time_col == "time_created":
-                    where_clauses.append(f"{time_col} >= ?")
-                    params.append(int(float(epoch_threshold) * 1000))
-                else:
-                    where_clauses.append(f"{time_col} >= ?")
-                    params.append(epoch_threshold)
-            if where_clauses:
-                query += " WHERE " + " AND ".join(where_clauses)
-            if time_col:
-                query += f" ORDER BY {time_col} DESC"
-            query += " LIMIT 20"
-            rows = cursor.execute(query, params).fetchall()
-            conn.close()
-            for (uuid,) in rows:
-                if uuid in (sibling_claimed or []):
-                    continue
-                if verify_session_uuid(cwd, 'opencode', uuid, s_eval, mode="discover"):
-                    valid_candidates.append(uuid)
-        else:
-            conn.close()
-    except Exception:
-        pass
-
-    if len(valid_candidates) > 1:
-        drifts.append({'class': 'C-ambiguous', 'name': s['name'],
-                       'msg': f"{s['name']}: {len(valid_candidates)} candidate transcripts newer than session epoch; not pinning"})
-        s['last_visible_status'] = f"ambiguous: {len(valid_candidates)} candidates"
-        actions.append(f"ambiguous candidates: {s['name']}")
-    if len(valid_candidates) == 1:
-        uuid = valid_candidates[0]
-        cmd = ['bash', '-c', f'source "{lib_sh}" && verify_tui_viewport "{s["name"]}" "opencode" "{cwd}"']
-        rc = subprocess.run(cmd).returncode
-        if rc == 0:
-            _pin_and_verify_resume(s, 'opencode', cwd, uuid, degraded=False)
-        elif rc == 1:
-            drifts.append({'class': 'C-warn', 'name': s['name'], 'msg': f"{s['name']}: TUI viewport mismatch for candidate {uuid} — not pinned, will retry next cycle"})
-        else:
-            _pin_and_verify_resume(s, 'opencode', cwd, uuid, degraded=True)
-
-# === drift C (codex): codex 새 session id materialize (per-row own id) ===
-for s in d.get('herdr_sessions', []):
-    if row_agent(s) != 'codex':
-        continue
-    if s.get('status') != 'running':
-        continue
-    if s.get('codex_session_id_own'):
-        continue
-    cwd = (s.get('pane') or {}).get('cwd', '')
-    if not cwd:
-        continue
-
-    codex_home = os.environ.get('CODEX_HOME') or f"{home}/.codex"
-    epoch_threshold = s.get('herdr_session_epoch', 0)
-
-    sibling_claimed = [
-        other.get('codex_session_id_own')
-        for other in d.get('herdr_sessions', [])
-        if other is not s
-        and (other.get('pane') or {}).get('cwd') == cwd
-        and other.get('status') not in ('stopped', 'terminated')
-        and other.get('codex_session_id_own')
-    ]
-    s_eval = dict(s)
-    s_eval['_sibling_claimed_uuids'] = sibling_claimed
-
-    valid_candidates = []
-    try:
-        # Rev.2: state DB first (indexed, single query) — dynamic filename,
-        # no hardcoded suffix (see §1.5 / §2 _state_db()).
-        state_matches = glob.glob(f"{codex_home}/state_*.sqlite")
-        state_db = max(state_matches, key=os.path.getmtime) if state_matches else None
-        rows = []
-        if state_db and os.path.exists(state_db):
-            try:
-                conn = _ro_connect(state_db)
-                cols = [c[1] for c in conn.execute("PRAGMA table_info(threads)").fetchall()]
-                order_col = "updated_at" if "updated_at" in cols else ("created_at" if "created_at" in cols else None)
-                if order_col:
-                    rows = conn.execute(
-                        f"SELECT id, {order_col} FROM threads WHERE cwd=? ORDER BY {order_col} DESC LIMIT 20",
-                        (cwd,)
-                    ).fetchall()
-                else:
-                    rows = [(r[0], int(time.time())) for r in conn.execute("SELECT id FROM threads WHERE cwd=? LIMIT 20", (cwd,)).fetchall()]
-                conn.close()
-            except Exception:
-                rows = []
-        if not rows:
-            # Fallback: bounded glob over the date-nested tree
-            paths = sorted(
-                glob.glob(f"{codex_home}/sessions/*/*/*/rollout-*.jsonl"),
-                key=os.path.getmtime, reverse=True
-            )[:50]
-            rows = [(os.path.basename(p)[:-6][-36:], os.path.getmtime(p)) for p in paths]
-
-        for uuid, ts in rows:
-            if epoch_threshold and ts and ts < epoch_threshold:
-                continue
-            if uuid in (sibling_claimed or []):
-                continue
-            if verify_session_uuid(cwd, 'codex', uuid, s_eval, mode="discover"):
-                valid_candidates.append(uuid)
-    except Exception:
-        pass
-
-    if len(valid_candidates) > 1:
-        drifts.append({'class': 'C-ambiguous', 'name': s['name'],
-                       'msg': f"{s['name']}: {len(valid_candidates)} candidate transcripts newer than session epoch; not pinning"})
-        s['last_visible_status'] = f"ambiguous: {len(valid_candidates)} candidates"
-        actions.append(f"ambiguous candidates: {s['name']}")
-    elif len(valid_candidates) == 1:
-        uuid = valid_candidates[0]
-        cmd = ['bash', '-c', f'source "{lib_sh}" && verify_tui_viewport "{s["name"]}" "codex" "{cwd}"']
-        rc = subprocess.run(cmd).returncode
-        if rc == 0:
-            _pin_and_verify_resume(s, 'codex', cwd, uuid, degraded=False)
-        elif rc == 1:
-            drifts.append({'class': 'C-warn', 'name': s['name'], 'msg': f"{s['name']}: TUI viewport mismatch for candidate {uuid} — not pinned, will retry next cycle"})
-        else:
-            _pin_and_verify_resume(s, 'codex', cwd, uuid, degraded=True)
 
 result = {
     'timestamp': now_iso,

.agents/skills/multi-agent-mux-orc-onboard/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-orc-onboard
 description: "Register current or specified orchestrator session UUID into agent-sessions.yaml orchestrator_uuids list to prevent sub-agent discovery capture."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]

.agents/skills/multi-agent-mux-orc-onboard/scripts/orc_onboard.sh

@@ -257,6 +257,11 @@ if [ "$DRY_RUN" = true ]; then
   exit 0
 fi
 
+# Issue #72 (U2): no registry write while an update runs - a rollback would
+# restore the registry without it. Held until the write is done (lib.sh
+# mam_update_admit).
+mam_update_admit || exit 1
+
 # Issue #13: the orchestrator has no herdr_sessions row, so stop_session.sh
 # --purge-conversation can never reach its conversation. Purge FIRST, through
 # the adapter (`lib_py.agents purge`): a refusal because the conversation is
@@ -304,6 +309,7 @@ elif op == "remove":
     uuids = [u for u in uuids if u != target]
 d["orchestrator_uuids"] = uuids
 PYEOF
+mam_update_admit_release
 
 case "$MODE" in
   add) verb="added" ;;

.agents/skills/multi-agent-mux-resume/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-resume
 description: "Resume an existing agent (claude, antigravity/agy) conversation by UUID into a herdr session. Reads .mam/agent-sessions.yaml for the saved session/conversation id, spawns (or reuses) a herdr session of the matching name, and runs `claude -r <id>` or `agy --conversation <id>` inside. Use when you want to reattach to a previous session's context, or revive a session whose herdr died but the agent's conversation is still on disk."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]
@@ -27,7 +27,7 @@ Three cases this skill handles:
 
 1. **herdr is dead, conversation lives** — `agent-sessions.yaml` has the UUID. The JSONL/db is on disk. Re-spawn the herdr session + run `claude -r <id>` / `agy --conversation <id>`.
 2. **herdr is alive but empty** — You started a session with `multi-agent-mux-create` but haven't sent a message yet (so no session id was assigned). The user can either send their first message (and the id is auto-assigned), or you can read the *workspace's* most recent conversation from `$HOME_DIR/.gemini/antigravity-cli/cache/last_conversations.json` (defaults to `~/.gemini/...`) for agy, or the latest `*.jsonl` in `$CLAUDE_PROJECT_DIR/<workspace-key>/` (defaults to `~/.claude/projects/`) for claude.
-3. **herdr is alive AND the agent inside is already running** — `resume_session.sh` only updates the row and exits 0. It does not attach and does not check the agent's permission flags (#45); attach with `herdr --session <server> agent attach <name>`, where `<server>` is the row's `herdr_session` (the server it was resumed on).
+3. **herdr is alive AND the agent inside is already running** — `resume_session.sh` only updates the row and exits 0. It does not attach and does not check the agent's permission flags (#45); attach with the row's `attach_command` (`herdr --session <server> agent attach <name>`, where `<server>` is the row's `herdr_session` and `<name>` the name herdr registered).
 
 ### Resuming a `stopped` session (`stopped → running`)
 
@@ -36,10 +36,10 @@ its row is `status: stopped` with `resumable: true` and the conversation id
 already recorded in `claude_session_id_own` / `agy_conversation_id_own`. This is the
 ideal resume path:
 
-- **tier-1, race-free**: because the stop command wrote the id into the row at stop
+- **tier-1, race-free**: when the row has its own id recorded, `session_ids.py`
-  time, `resolve_session_id.sh` resolves it via `find_workspace_uuid` tier-1 (the
+  resolves it directly from the per-row own id (after checking no other row
-  per-row own id) — no reliance on the mtime-based disk scan, so a concurrent
+  claims it and revalidating on disk) — no reliance on the mtime-based disk scan,
-  session in another workspace can never shadow it.
+  so a concurrent session in the same or another workspace can never shadow it.
 - On resume, `update_yaml_resumed.sh` transitions `stopped → running` and **clears
   the stop metadata** (`stopped_at`, `stopped_at_epoch`, `stop_reason`, `resumable`)
   along with the usual `terminated_at*` / `termination_mode` / `archived_at`, so the
@@ -49,10 +49,10 @@ ideal resume path:
 
 `agent-sessions.yaml` and on-disk discovery are used to resolve the UUID in this order:
 
-1. **`herdr_sessions[]` row's per-row own id** (`claude_session_id_own` / `agy_conversation_id_own` / `hermes_conversation_id_own` / `grok_session_id_own` / `opencode_session_id_own` / `codex_session_id_own`) — explicitly saved by `multi-agent-mux-stop` right before teardown (tier-1, race-free).
+1. **`herdr_sessions[]` row's per-row own id** (`claude_session_id_own` / `agy_conversation_id_own` / `hermes_conversation_id_own` / `grok_session_id_own` / `opencode_session_id_own` / `codex_session_id_own`) — verified against disk and refused (exit 1) if another row also records it (tier-1, race-free).
-2. **Workspace-scoped on-disk scan** (adapter `discover()`)
+2. **Without an own id**: Class A (`agy`, `hermes`, `opencode`, `codex`) uses `#40` pane capture (`autopin.capture`) when herdr is alive, starts a fresh conversation (`FRESH_SPAWN=1` + `NOTE:` on stderr) when herdr is dead and 2+ same-type rows share the cwd, or scans the workspace when it is the only row; Class B (`claude`, `grok`) runs the workspace scan (`find_workspace_uuid`, skipping ids claimed by other rows).
 
-If both are empty → for Class A agents (`agy`, `hermes`, `opencode`, `codex`), `resume_session.sh` automatically falls back to `FRESH_SPAWN=1` (`spawn-spec`). For Class B agents (`claude`, `grok`), fall back to `multi-agent-mux-create`.
+If the resolved id is empty → for Class A agents (`agy`, `hermes`, `opencode`, `codex`), `resume_session.sh` uses `FRESH_SPAWN=1` (`spawn-spec`). For Class B agents (`claude`, `grok`), fall back to `multi-agent-mux-create`.
 
 ## Workflow
 
@@ -60,7 +60,7 @@ If both are empty → for Class A agents (`agy`, `hermes`, `opencode`, `codex`),
 bash .agents/skills/multi-agent-mux-resume/scripts/resume_session.sh --workspace <path> --agent <agent> --session <name>
 ```
 
-`resume_session.sh` does the whole flow: original-cwd check, control-plane binding, session-id resolution (`resolve_session_id.sh`), the herdr-alive check, the agent command (adapter `resume-spec`, or `spawn-spec` for a Class A fresh spawn), spawn (just before it, the session's own empty shell left by a server restart is closed: same session id, no agent, nothing running; `lib_py/herdr_restore.py`), start-up dialogs, and the YAML update (`update_yaml_resumed.sh`, which also publishes a `progress "resumed"` event when the row has a `delegate_job_id`). It never attaches; attaching is a separate step that names the server, because the server the script exports does not reach the calling shell and the native `herdr` binary does not route on environment variables: `herdr --session <server> agent attach <name>` (`<server>` = the `--herdr-session` you passed, or the row's `herdr_session`).
+`resume_session.sh` does the whole flow: original-cwd check, control-plane binding, the session-id decision (`lib_py/agents/session_ids.py`), the herdr-alive check, the agent command (adapter `resume-spec`, or `spawn-spec` for a Class A fresh spawn), spawn (just before it, the session's own empty shell left by a server restart is closed: same session id, no agent, nothing running; `lib_py/herdr_restore.py`), start-up dialogs, and the YAML update (`update_yaml_resumed.sh`, which also publishes a `progress "resumed"` event when the row has a `delegate_job_id`), then the control root's monitor daemon (`start_watchdog`, as create; not with `MAM_NO_SUBSCRIBER_DAEMON=1`). It never attaches; attaching is a separate step that names the server, because the server the script exports does not reach the calling shell and the native `herdr` binary does not route on environment variables: the row's `attach_command`, `herdr --session <server> agent attach <name>` (`<server>` = the `--herdr-session` you passed, or the row's `herdr_session`; `<name>` = the name herdr registered).
 
 | Option | Meaning |
 |---|---|
@@ -75,11 +75,11 @@ bash .agents/skills/multi-agent-mux-resume/scripts/resume_session.sh --workspace
 | Exit | Meaning |
 |---|---|
 | 0 | Resumed; or already running, so only the row was updated (no attach); or `--dry-run` |
-| 1 | From the checks before spawn, nothing was changed: no saved session for claude/grok (use `multi-agent-mux-create` first), agent binary missing or not executable. **The YAML update after spawn (`update_yaml_resumed.sh`) also exits 1** (YAML not found) |
+| 1 | From the checks before spawn, nothing was changed: no saved session for claude/grok (use `multi-agent-mux-create` first), the row's id is also claimed by another row, a same-cwd Class A session did not record its id within `MAM_ID_ORDER_WAIT_S` (default 600), agent binary missing/not executable, or an update of the workspace is in progress (`multi-agent-mux-update`). **The YAML update after spawn (`update_yaml_resumed.sh`) also exits 1** (YAML not found) |
 | 2 | From the checks before spawn, nothing was changed: bad arguments, `--workspace` differs from the original cwd or it no longer exists, control-plane binding refused, whitespace in the control-plane path. **The YAML update after spawn also exits 2** (bad arguments) |
 | other | A later step failed (herdr spawn, start-up dialogs, YAML update) and its code is passed through. resume does not roll back |
 
-A non-zero exit after the spawn can leave the herdr session running while the row is still `stopped`. Before retrying or creating a new session, check with `multi-agent-mux-status`. The `ERROR:` line on stderr tells the two apart: the pre-spawn checks' messages are in `resume_session.sh` (lines 50-223).
+A non-zero exit after the spawn can leave the herdr session running while the row is still `stopped`. Before retrying or creating a new session, check with `multi-agent-mux-status`. The `ERROR:` line on stderr tells the two apart: the pre-spawn checks' messages are in `resume_session.sh` (lines 50-259).
 
 ## Original cwd only (Issue #21 phase 2)
 
@@ -136,4 +136,4 @@ herdr --session "$SERVER" agent read "$SESSION_NAME" --source visible --lines 30
 
 - **No saved session yet** → `multi-agent-mux-create`
 - **Killing an existing session** → `multi-agent-mux-stop`
-- **Just attaching** → `herdr --session <server> agent attach <name>` (no skill needed; `<server>` = the row's `herdr_session`)
+- **Just attaching** → the row's `attach_command` (no skill needed; `herdr --session <server> agent attach <name>`, `<name>` = the name herdr registered)

.agents/skills/multi-agent-mux-resume/scripts/resolve_session_id.sh

@@ -4,9 +4,9 @@
 #   bash resolve_session_id.sh --workspace <path> --agent <claude|agy|hermes|grok|opencode|codex>
 # 출력: stdout 으로 UUID 한 줄 (없으면 빈 줄 + exit 0)
 #
-# P0-C: 전역 agent_identities 를 즉시 반환하지 않는다. lib.sh::find_workspace_uuid
+# P0-C / Issue #63: 전역 agent_identities 를 즉시 반환하지 않는다. lib.sh::mam_session_ids
-# 가 워크스페이스 격리된 해결 경로(per-row own id -> 디스크 스캔 -> cwd 일치하는
+# 가 워크스페이스 격리된 해결 경로(per-row own id -> #40 active capture / 디스크 스캔)만 사용.
-# cache)만 사용. 다른 워크스페이스의 UUID 를 절대 반환하지 않음.
+# 다른 워크스페이스나 다른 행이 기록한 UUID 를 절대 반환하지 않음.
 set -euo pipefail
 
 source "$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/lib.sh"
@@ -22,13 +22,17 @@ EOF
 WORKSPACE=""
 AGENT=""
 SESSION_NAME=""
+HERDR_ALIVE="0"
+PANE_PID=""
 
 while [ $# -gt 0 ]; do
   case "$1" in
-    --workspace) WORKSPACE="$2"; shift 2 ;;
+    --workspace)   WORKSPACE="$2";   shift 2 ;;
-    --agent)     AGENT="$2";     shift 2 ;;
+    --agent)       AGENT="$2";       shift 2 ;;
-    --session)   SESSION_NAME="$2"; shift 2 ;;
+    --session)     SESSION_NAME="$2"; shift 2 ;;
-    -h|--help)   usage; exit 0 ;;
+    --herdr-alive) HERDR_ALIVE="$2"; shift 2 ;;
+    --pane-pid)    PANE_PID="$2";    shift 2 ;;
+    -h|--help)     usage; exit 0 ;;
     *) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
   esac
 done
@@ -40,4 +44,6 @@ case "$AGENT" in
   *) echo "ERROR: --agent must be claude, agy, hermes, grok, opencode, or codex" >&2; exit 2 ;;
 esac
 
-find_workspace_uuid "$WORKSPACE" "$AGENT" "$SESSION_NAME"
+mam_session_ids resume --session "$SESSION_NAME" --agent "$AGENT" \
+  --workspace "$(mam_abs_workspace "$WORKSPACE")" \
+  --herdr-alive "$HERDR_ALIVE" --pane-pid "$PANE_PID"

.agents/skills/multi-agent-mux-resume/scripts/resume_session.sh

@@ -107,9 +107,33 @@ if [ "$cp_rc" -ne 0 ] || [ -z "$CP_JSON" ]; then
   CP_JSON=""
 fi
 
-# 1. Resolve the session id
+if [ -n "$HERDR_SERVER_OPT" ]; then
-UUID=$(bash "$(dirname "${BASH_SOURCE[0]}")/resolve_session_id.sh" \
+  export HERDR_SESSION_NAME="$HERDR_SERVER_OPT"
-  --workspace "$WORKSPACE" --agent "$AGENT" --session "$SESSION_NAME")
+else
+  HERDR_SESSION_NAME="$(resolve_herdr_session "$SESSION_NAME" "$WORKSPACE")"
+  export HERDR_SESSION_NAME
+fi
+
+if [ -n "$HERDR_WORKSPACE_OPT" ]; then
+  export MAM_WS_LABEL="$HERDR_WORKSPACE_OPT"
+else
+  export MAM_WS_LABEL="$(resolve_herdr_workspace "$SESSION_NAME" "$WORKSPACE")"
+fi
+
+HERDR_ALIVE=0
+PANE_PID_NOW=""
+if herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
+  HERDR_ALIVE=1
+  PANE_PID_NOW=$(herdr list-panes -t "$SESSION_NAME" -F '#{pane_pid}' 2>/dev/null | head -1 || true)
+fi
+
+# 1. Resolve the session id (Issue #63: own id first, then #40 capture when
+# herdr is alive, or fresh spawn when 2+ same-type rows share the cwd)
+RESUME_OUT=$(mam_session_ids resume --shell \
+  --workspace "$(mam_abs_workspace "$WORKSPACE")" --agent "$AGENT" --session "$SESSION_NAME" \
+  --herdr-alive "$HERDR_ALIVE" --pane-pid "$PANE_PID_NOW")
+eval "$RESUME_OUT"
+UUID="$RESUME_UUID"
 
 # ISSUE-3: agy/hermes/opencode (Class A) are spawned without a UUID - their
 # own conversation id is only assigned by the agent itself on its first turn.
@@ -130,31 +154,34 @@ if [ -z "$UUID" ]; then
   esac
 fi
 
-if [ -n "$HERDR_SERVER_OPT" ]; then
+# Issue #72: a resumed session gets the monitor daemon create starts - the
-  export HERDR_SESSION_NAME="$HERDR_SERVER_OPT"
+# control root's (Issue #21 A8), also for a worktree --workspace. Called after
-else
+# the row is written; MAM_NO_SUBSCRIBER_DAEMON=1 starts none. Never fails the resume.
-  HERDR_SESSION_NAME="$(resolve_herdr_session "$SESSION_NAME" "$WORKSPACE")"
+_ensure_monitor_daemon() {
-  export HERDR_SESSION_NAME
+  local wd_pid
-fi
+  if wd_pid=$(start_watchdog "resume" "$WORKSPACE_ROOT"); then
-
+    echo "watchdog PID: $wd_pid"
-if [ -n "$HERDR_WORKSPACE_OPT" ]; then
+  else
-  export MAM_WS_LABEL="$HERDR_WORKSPACE_OPT"
+    echo "WARNING: could not start the monitor daemon of '$WORKSPACE_ROOT'; the session itself was resumed" >&2
-else
+  fi
-  export MAM_WS_LABEL="$(resolve_herdr_workspace "$SESSION_NAME" "$WORKSPACE")"
+}
-fi
 
 # 2. If herdr is alive, print warning or attach.
-if herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
+if [ "$HERDR_ALIVE" = "1" ]; then
   if [ "${DRY_RUN:-0}" = "1" ]; then
     echo "[dry-run] herdr '$SESSION_NAME' already running — nothing to validate"
     exit 0
   fi
+  # Issue #72: no registry write while an update runs (lib.sh mam_update_admit).
+  mam_update_admit || exit 1
   echo "herdr '$SESSION_NAME' already running."
   # Just update YAML to make sure it's set to running
   CONTROL_PLANE_JSON="$CP_JSON" bash "$(dirname "${BASH_SOURCE[0]}")/update_yaml_resumed.sh" \
     --session "$SESSION_NAME" --uuid "$UUID" --agent "$AGENT" --workspace "$WORKSPACE" \
-    --herdr-session "$HERDR_SESSION_NAME" \
+    --herdr-session "$HERDR_SESSION_NAME" --already-running \
     ${HERDR_WORKSPACE_OPT:+--herdr-workspace "$HERDR_WORKSPACE_OPT"}
+  mam_update_admit_release
+  _ensure_monitor_daemon
   exit 0
 fi
 
@@ -227,6 +254,15 @@ if [ "${DRY_RUN:-0}" = "1" ]; then
   exit 0
 fi
 
+# Issue #72: no new session while an update of the control root or of an
+# installed workspace the pane's cwd is in runs; held until the row is written
+# (lib.sh mam_update_admit_at).
+mam_update_admit_at "$WORKSPACE" || exit 1
+
+# Issue #63: wait if another same-cwd session of this post-discovered agent
+# is still being created or has not recorded its id yet (lib.sh mam_id_order_wait).
+mam_id_order_wait "$WORKSPACE" "$AGENT" "$SESSION_NAME" "$UUID" || exit 1
+
 if [ "$AGENT" = "opencode" ]; then
   if [ -z "${OPENCODE_PERMISSION:-}" ]; then
     export OPENCODE_PERMISSION='{"*":"allow"}'
@@ -252,9 +288,14 @@ handle_startup_dialogs "$SESSION_NAME" 20 "$AGENT"
 sleep 2
 
 # 5. Update agent-sessions.yaml: status running, last_visible_status
+DROP_FLAG=""
+[ "${DROP_STALE_ID:-0}" = "1" ] && DROP_FLAG="--drop-stale-id"
 CONTROL_PLANE_JSON="$CP_JSON" bash "$(dirname "${BASH_SOURCE[0]}")/update_yaml_resumed.sh" \
   --session "$SESSION_NAME" --uuid "$UUID" --agent "$AGENT" --workspace "$WORKSPACE" \
   --herdr-session "$HERDR_SESSION_NAME" --cmd-full "$CMD_FULL" \
+  ${DROP_FLAG:+$DROP_FLAG} \
   ${HERDR_WORKSPACE_OPT:+--herdr-workspace "$HERDR_WORKSPACE_OPT"}
+mam_update_admit_release_all
+_ensure_monitor_daemon
 
 echo "Successfully resumed $SESSION_NAME ($AGENT)"

.agents/skills/multi-agent-mux-resume/scripts/update_yaml_resumed.sh

@@ -27,6 +27,8 @@ ROLE=""
 HERDR_SERVER_OPT=""
 HERDR_WORKSPACE_OPT=""
 CMD_FULL_OPT=""
+ALREADY_RUNNING=0
+DROP_STALE_ID=0
 
 while [ $# -gt 0 ]; do
   case "$1" in
@@ -38,6 +40,8 @@ while [ $# -gt 0 ]; do
     --herdr-session|--herdr-server) HERDR_SERVER_OPT="$2"; shift 2 ;;
     --herdr-workspace) HERDR_WORKSPACE_OPT="$2"; shift 2 ;;
     --cmd-full)  CMD_FULL_OPT="$2";  shift 2 ;;
+    --already-running) ALREADY_RUNNING=1; shift ;;
+    --drop-stale-id)   DROP_STALE_ID=1;   shift ;;
     -h|--help) usage; exit 0 ;;
     *) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
   esac
@@ -110,7 +114,9 @@ atomic_dump_yaml "$AGENT_SESSIONS_YAML" \
   NOW_EPOCH="$NOW_EPOCH" TARGET_WORKSPACE="${WORKSPACE:-$WORKSPACE_ROOT}" ROLE="$ROLE" \
   PANE_PID="$PANE_PID" CHILD_PID="$CHILD_PID" HERDR_SERVER_OPT_EXPLICIT="${HERDR_SERVER_OPT_EXPLICIT:-0}" \
   MAM_WS_LABEL="$MAM_WS_LABEL" MAM_WS_LABEL_EXPLICIT="${MAM_WS_LABEL_EXPLICIT:-0}" \
+  ALREADY_RUNNING="$ALREADY_RUNNING" DROP_STALE_ID="$DROP_STALE_ID" \
   CMD_FULL_OPT="$CMD_FULL_OPT" <<'PYEOF'
+from lib_py.agents.sanitize import attach_command
 name = os.environ['SESSION_NAME']
 uuid = os.environ['UUID']
 agent = os.environ['AGENT']
@@ -142,9 +148,7 @@ if target is None:
         'herdr_workspace': wsl,
         'delegate_job_id': None,
         'pane': {'index': 0, 'pid': int(pane_pid) if pane_pid.isdigit() else 0, 'cmd': agent, 'cwd': ws_root},
-        'start_command': f'HERDR_SESSION_NAME={server_name} herdr agent attach {name}',
+        'attach_command': attach_command(server_name, name),
-        'attach_command': f'HERDR_SESSION_NAME={server_name} herdr agent attach {name}',
-        'kill_command': f'HERDR_SESSION_NAME={server_name} herdr kill-session -t {name}',
     }
     d.setdefault('herdr_sessions', []).append(target)
 else:
@@ -154,9 +158,7 @@ else:
         if is_explicit or not target.get('herdr_session'):
             target['herdr_session'] = sn
             target['herdr_server'] = sn
-            target['start_command'] = f'HERDR_SESSION_NAME={sn} herdr agent attach {name}'
+            target['attach_command'] = attach_command(sn, name)
-            target['attach_command'] = f'HERDR_SESSION_NAME={sn} herdr agent attach {name}'
-            target['kill_command'] = f'HERDR_SESSION_NAME={sn} herdr kill-session -t {name}'
     wsl = os.environ.get('MAM_WS_LABEL', '')
     ws_explicit = os.environ.get('MAM_WS_LABEL_EXPLICIT') == '1'
     if wsl and (ws_explicit or not target.get('herdr_workspace')):
@@ -173,7 +175,17 @@ if _cp_raw and not isinstance(target.get('control_plane'), dict):
         target['control_plane'] = {k: _cp[k] for k in ('workspace_root', 'agent_sessions_yaml', 'mam_jobs_dir', 'delegate_job_logs_dir')}
     except Exception:
         pass
-if not uuid:
+stale_dropped = ''
+if not uuid and os.environ.get('DROP_STALE_ID') == '1':
+    from lib_py.agents.autopin import claimed_elsewhere
+    from lib_py.agents.registry import get_adapter
+    _adapter = get_adapter(agent)
+    _own_key = _adapter.own_key if _adapter else ''
+    _old = (target.get(_own_key) or '').strip() if _own_key else ''
+    if _old and _old not in set(claimed_elsewhere(target, d)):
+        target[_own_key] = None
+        stale_dropped = _old
+if not uuid and os.environ.get('ALREADY_RUNNING') != '1':
     # ISSUE-3 (challenge c4b0a075): a Class A fresh-spawn resume re-arms
     # discovery from scratch - the resumed agent has not spoken yet, so any
     # on-disk conversation older than THIS resume must not be auto-pinned to
@@ -196,6 +208,10 @@ target.pop('stop_reason', None)
 target.pop('resumable', None)
 if uuid:
     target['last_visible_status'] = f'resumed conversation {uuid} at {now}'
+elif os.environ.get('ALREADY_RUNNING') == '1':
+    target['last_visible_status'] = f'already running; no id recorded at {now}'
+elif stale_dropped:
+    target['last_visible_status'] = f'resumed (fresh spawn, recorded id {stale_dropped} no longer verified) at {now}'
 else:
     # ISSUE-3 Class A fresh-spawn resume: no conversation id existed yet.
     target['last_visible_status'] = f'resumed (fresh spawn, no prior turn) at {now}'

.agents/skills/multi-agent-mux-status/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-status
 description: "Read-only instant snapshot of all agent herdr sessions — name, YAML status, herdr alive, pane cmd/cwd, resume UUID on disk, and any drift. No mutation. Reuses reconcile.sh --dry-run for the diff logic. Use when you want to know 'what's running RIGHT NOW' without spinning up the monitor loop."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]
@@ -94,11 +94,10 @@ lab-paper-pdf2md-creator-claude              default      running    alive  clau
       "job_id": null,
       "job_status": null,
       "pane_cwd": "/home/.../refer_landing_page",
-      "attach_command": "HERDR_SESSION_NAME=default herdr agent attach lab-landing-page-creator-claude",
+      "attach_command": "herdr --session default agent attach lab-landing-page-creator-claude",
       "drift_classes": [],
       "pane_pid": 12345,
       "cmd_full": "claude --dangerously-skip-permissions --session-id <uuid>",
-      "start_command": "...",
       "last_visible_status": "pinned"
     }
   ]

.agents/skills/multi-agent-mux-status/scripts/status.sh

@@ -221,11 +221,10 @@ for s in d.get('herdr_sessions', []):
         'pane_cwd': pane.get('cwd'),
         'attach_command': s.get('attach_command'),
         'drift_classes': drift_by_name.get(name, []),
-        # Additive beyond the D8 example — needed by the M1 Detail Pane
+        # Additive beyond the D8 example (pane pid / full launch command /
-        # (pane pid / full launch command / start command / last banner text).
+        # last banner text).
         'pane_pid': pane.get('pid'),
         'cmd_full': pane.get('cmd_full'),
-        'start_command': s.get('start_command'),
         'last_visible_status': s.get('last_visible_status'),
     })
 

.agents/skills/multi-agent-mux-stop/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multi-agent-mux-stop
 description: "Stop an agent herdr session (claude, antigravity/agy) and update .mam/agent-sessions.yaml. Default stops gracefully and marks status=stopped with conversation preserved for resume. Does NOT delete on-disk conversation artifacts (jsonl/db) — those are preserved unless --purge-conversation is passed. Use when ending a work session, switching to a different one, or cleaning up before a fresh start."
-version: 4.9.8
+version: 4.12.0
 author: godopu
 license: MIT
 platforms: [linux, macos]
@@ -25,17 +25,16 @@ Stop an agent's herdr session gracefully, resolve and store the conversation ID,
 
 - The herdr session's recorded `pane.pid / cmd / cwd / mcp_attachments` for audit
 - The agent's on-disk conversation (claude `*.jsonl`, agy `conversations/*.db`) — so the user can `multi-agent-mux-resume` later
-- The `start_command` so a future `multi-agent-mux-create --session <name>` reproduces the same herdr spec
 
 The stop command is always **graceful by default**:
 1. Sends exit keys to the agent TUI (`/exit` for Claude, `/exit` for Agy) and waits 3 seconds.
 2. If still alive, issues `herdr kill-session` (SIGTERM) and waits 5 seconds.
 3. If still alive, kills the pane PID via SIGKILL (`kill -9`) as a last resort.
-4. Auto-captures the conversation ID into the row (`claude_session_id_own`/`agy_conversation_id_own`) before killing, ensuring the next resume uses a race-free tier-1 lookup.
+4. Auto-captures the conversation ID into the row (`claude_session_id_own`/`agy_conversation_id_own`) before killing (for Class A agents, only an ID verified as this pane's via `#40` capture is recorded, and nothing is recorded if the herdr session was already dead), ensuring the next resume uses a race-free tier-1 lookup.
 
 ## Pre-flight
 
-`stop_session.sh` checks this itself: the YAML exists and the session is registered (otherwise exit 1), and a session already `stopped` is a no-op (exit 0).
+`stop_session.sh` checks this itself: the YAML exists (otherwise exit 1), and a session already `stopped` is a no-op (exit 0). A session with no registry row (its create or resume died before registering it) is still closed, herdr only and with no `--agent`: only when herdr runs it inside this workspace, on the `--herdr-session` server (or `HERDR_SESSION_NAME`). The registry is not changed.
 
 ## Workflow
 
@@ -59,10 +58,12 @@ bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh \
 | Exit | Meaning |
 |---|---|
 | 0 | Stopped; or already `stopped` (no-op, except with `--purge-conversation`, which still purges) |
-| 1 | From the checks before the stop, nothing was changed: YAML not found, or the session is not registered. **The registry update after the stop also exits 1** (the row disappeared from the YAML during the run) |
+| 1 | From the checks before the stop, nothing was changed: YAML not found, its row could not be read, the session is neither registered nor on the herdr server, or an update of the workspace is in progress (`multi-agent-mux-update`). **The registry update after the stop also exits 1** (the row disappeared from the YAML during the run) |
 | 2 | Bad arguments (including the retired `--mode` / `--capture-id` / `--graceful`), or `--agent` omitted and not resolvable |
 | 3 | `--purge-conversation` without `--yes` |
 | 4 | Purge aborted: the herdr session, or an agent process still holding the conversation, survived the kill chain. Records preserved: the registry row and the conversation files are untouched, though the session itself may already be down |
+| 5 | No registry row, and herdr runs the session outside this workspace: refused, nothing changed |
+| 6 | No registry row, and its herdr session survived `kill-session`; the registry is unchanged |
 | other | The registry update after the stop (YAML / DB write) failed and its code is passed through |
 
 Exits 2 and 3, and exit 1 from the pre-stop checks, come before anything is stopped, so nothing was changed. On exit 1 from the registry update, or an `other` exit, the session may already be down while its row still says `running`: check with `multi-agent-mux-status`, then run the stop again (it is idempotent).
@@ -93,7 +94,7 @@ The script:
 2. If `delegate_job_id` is set, automatically publishes a `progress --detail "terminating"` event to the multi-agent-mux-delegate-job registry
 3. Captures the `last_visible_status` from `herdr capture-pane` (so we have a final TUI snapshot for audit)
 4. Attempts graceful exit keys → SIGTERM kill-session → SIGKILL fallback
-5. For `purge-conversation`: deletes, for claude, every path the session owns — `projects/<key>/<uuid>.jsonl` and `<uuid>/`, `file-history/<uuid>/`, `session-env/<uuid>/`, `jobs/<uuid[:8]>/` (when its `state.json` names the session), stale `sessions/<pid>.json` (+ that pid's `.key`) and `<tmp>/claude-<uid>/*/<uuid>/`, then prints anything still carrying the UUID as `WARN residual:`; shared files such as `history.jsonl` are not rewritten (Issue #31). Or, for agy, `~/.gemini/antigravity-cli/conversations/<uuid>.db` with its `-wal`/`-shm`/`-journal` sidecars, `brain/<uuid>/`, `annotations/<uuid>.pbtxt` and `presence/<uuid>.lock` (the lock only once no live process references the conversation — Issue #10)
+5. For `purge-conversation` (purging only the row's own ID or an ID verified for this pane, and never an ID another row records — Issue #63): deletes, for claude, every path the session owns — `projects/<key>/<uuid>.jsonl` and `<uuid>/`, `file-history/<uuid>/`, `session-env/<uuid>/`, `jobs/<uuid[:8]>/` (when its `state.json` names the session), stale `sessions/<pid>.json` (+ that pid's `.key`) and `<tmp>/claude-<uid>/*/<uuid>/`, then prints anything still carrying the UUID as `WARN residual:`; shared files such as `history.jsonl` are not rewritten (Issue #31). Or, for agy, `~/.gemini/antigravity-cli/conversations/<uuid>.db` with its `-wal`/`-shm`/`-journal` sidecars, `brain/<uuid>/`, `annotations/<uuid>.pbtxt` and `presence/<uuid>.lock` (the lock only once no live process references the conversation — Issue #10)
 6. Updates the YAML entry and SQLite database atomically
 7. If `delegate_job_id` is set, publishes a `completed` event to the multi-agent-mux-delegate-job registry
 

.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh

@@ -5,8 +5,8 @@
 #       [--reason <reason>] [--purge-conversation] [--yes]
 #
 # 동작: 항상 graceful stop 입니다. send-keys 로 정상 종료를 유도하고
-#       (미종료 시 SIGTERM → SIGKILL 폴백), kill 직전에 이 워크스페이스의
+#       (미종료 시 SIGTERM → SIGKILL 폴백), kill 직전에 이 세션(pane)의 검증된
-#       conversation id 를 row 에 확정 기록해 다음 resume 이 tier-1(race-free)
+#       conversation id 만 row 에 확정 기록해 다음 resume 이 tier-1(race-free)
 #       으로 복원되게 합니다. status 는 running -> stopped 로 전이합니다.
 #       멱등: 이미 stopped 면 no-op + exit 0.
 #
@@ -28,9 +28,12 @@
 #              구분은 --purge-conversation 유무로 대체되었습니다.
 #
 # Exit codes:
-#   0 = success (or already-stopped no-op) | 1 = YAML not found / not registered
+#   0 = success (or already-stopped no-op; or a session with no row closed)
+#   1 = YAML not found / its row unreadable / not registered and not on the herdr server
 #   2 = invalid args | 3 = interactive confirmation required (--yes 누락)
 #   4 = purge aborted (herdr session or an agent process holding the conversation survived the kill chain)
+#   5 = no row, and herdr runs the session outside this workspace (refused, nothing changed)
+#   6 = no row, and its herdr session survived kill-session (registry unchanged)
 set -euo pipefail
 
 # shellcheck disable=SC1091
@@ -67,7 +70,6 @@ HERDR_SERVER_OPT=""
 HERDR_WORKSPACE_OPT=""
 PURGE=0
 YES=0
-CAPTURE_ID=1
 GRACEFUL=1
 REASON="manual_stop"
 STOP_MODE=1
@@ -98,12 +100,18 @@ fi
 [ -n "$SESSION_NAME" ] || { echo "ERROR: --session required" >&2; usage; exit 2; }
 [ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found" >&2; exit 1; }
 
+# Issue #72 (U2): no registry write while an update runs - a rollback would
+# restore the registry without it. Held until the row is written (lib.sh
+# mam_update_admit).
+mam_update_admit || exit 1
+
 # Implement the purging-<session> file lock mechanism
 if [ "$PURGE" = "1" ]; then
   touch "$WORKSPACE_ROOT/.mam/purging-$SESSION_NAME"
   trap 'rm -f "$WORKSPACE_ROOT/.mam/purging-$SESSION_NAME"' EXIT
 fi
 
+AMBIENT_HERDR_SESSION="${HERDR_SESSION_NAME:-}"
 if [ -n "$HERDR_SERVER_OPT" ]; then
   export HERDR_SESSION_NAME="$HERDR_SERVER_OPT"
 else
@@ -111,20 +119,64 @@ else
   export HERDR_SESSION_NAME
 fi
 
-# --agent 미지정 시 레지스트리 기록으로 해석 (B-21).
+# Issue #71: a session with no registry row (its create/resume died before
-# ① row['agent'] → ② 세션명 접미사 → ③ pane.cmd 순. 셋 다 실패하면
+# registering it) is closed here - herdr only, the registry is left alone. It
-# 종전과 동일하게 exit 2 (헤더 :27-30 의 종료 코드 계약 유지).
+# has no agent kind, so --agent is not needed. Only a session herdr runs
-if [ -z "$AGENT" ]; then
+# inside this workspace is closed; anything else changes nothing. With no row
-  AGENT="$(resolve_agent_type_from_registry "$SESSION_NAME")" || AGENT=""
+# the server is chosen as create_session.sh chose it: --herdr-session, else
-  [ -n "$AGENT" ] || {
+# the environment's HERDR_SESSION_NAME, else the workspace's server.
-    echo "ERROR: cannot infer agent from '$SESSION_NAME'; pass --agent" >&2
+stop_rowless() {
-    exit 2
+  if [ "$PURGE" = "1" ]; then
-  }
+    echo "ERROR: session '$SESSION_NAME' not in $AGENT_SESSIONS_YAML; --purge-conversation needs its row. Nothing changed." >&2
-fi
+    exit 1
+  fi
+  if [ -z "$HERDR_SERVER_OPT" ] && [ -n "$AMBIENT_HERDR_SESSION" ] && [ "$AMBIENT_HERDR_SESSION" != "default" ]; then
+    export HERDR_SESSION_NAME="$AMBIENT_HERDR_SESSION"
+  fi
+  local info cwd
+  info=$(herdr agent get "$SESSION_NAME" 2>/dev/null) || info=""
+  if [ -z "$info" ]; then
+    echo "ERROR: session '$SESSION_NAME' not in $AGENT_SESSIONS_YAML, and herdr server '${HERDR_SESSION_NAME:-default}' has no agent of that name. Nothing changed." >&2
+    exit 1
+  fi
+  cwd=$(printf '%s' "$info" | python3 -c '
+import sys, json
+raw = sys.stdin.read()
+try:
+    print(json.loads(raw[raw.index("{"):]).get("result", {}).get("agent", {}).get("cwd", "") or "")
+except Exception:
+    print("")
+')
+  if ! PANE_CWD="$cwd" python3 -c '
+import os, sys
+cwd, root = os.environ.get("PANE_CWD", ""), os.environ.get("WORKSPACE_ROOT", "")
+if not cwd or not root:
+    sys.exit(1)
+cwd, root = os.path.realpath(cwd), os.path.realpath(root)
+sys.exit(0 if cwd == root or cwd.startswith(root + os.sep) else 1)
+'; then
+    echo "ERROR: refusing to stop '$SESSION_NAME': it is not in $AGENT_SESSIONS_YAML, and herdr runs it in '${cwd:-<unknown>}', outside this workspace ($WORKSPACE_ROOT). Nothing changed." >&2
+    exit 5
+  fi
+  echo "session '$SESSION_NAME' has no registry row: closing its herdr session only (registry unchanged)"
+  herdr kill-session -t "$SESSION_NAME" 2>/dev/null || true
+  _wait_session_gone "$SESSION_NAME" 8 || true
+  if herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
+    echo "ERROR: herdr session '$SESSION_NAME' is still running after kill-session (registry unchanged)" >&2
+    exit 6
+  fi
+  echo "closed herdr session '$SESSION_NAME' on server '${HERDR_SESSION_NAME:-default}' (no registry row)"
+  exit 0
+}
 
 # 세션이 YAML 에 있는지 + 해당 row 의 워크스페이스 cwd 및 delegate_job_id 추출.
 # JSON 으로 emit — cwd 에 '|' 가 들어가도 안전 (review item 7; 기존 cwd|jid 파서 대체).
-MAPPED_DATA=$(MAM_STATE_JSON="$(load_state_json)" SESSION_NAME="$SESSION_NAME" python3 -c "
+# A registry that cannot be read is not "no row" (Issue #71): stop before herdr.
+STATE_JSON=$(load_state_json strict) || {
+  echo "ERROR: cannot read $AGENT_SESSIONS_YAML, so whether '$SESSION_NAME' has a row is unknown. Nothing changed." >&2
+  exit 1
+}
+MAPPED_DATA=$(MAM_STATE_JSON="$STATE_JSON" SESSION_NAME="$SESSION_NAME" python3 -c "
 import sys, os, json
 name = os.environ['SESSION_NAME']
 d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
@@ -137,10 +189,24 @@ for s in d.get('herdr_sessions', []):
                           'delegate_job_logs_dir': cp.get('delegate_job_logs_dir', '') or ''}))
         sys.exit(0)
 sys.exit(7)
-") || {
+") || MAPPED_RC=$?
-  echo "ERROR: session '$SESSION_NAME' not in $AGENT_SESSIONS_YAML" >&2
+# 7 = no row; any other failure (registry unreadable) stops as before.
+[ "${MAPPED_RC:-0}" -ne 7 ] || stop_rowless
+if [ "${MAPPED_RC:-0}" -ne 0 ]; then
+  echo "ERROR: cannot read the row of '$SESSION_NAME' from $AGENT_SESSIONS_YAML" >&2
   exit 1
-}
+fi
+
+# --agent 미지정 시 레지스트리 기록으로 해석 (B-21).
+# ① row['agent'] → ② 세션명 접미사 → ③ pane.cmd 순. 셋 다 실패하면
+# 종전과 동일하게 exit 2 (헤더 :27-30 의 종료 코드 계약 유지).
+if [ -z "$AGENT" ]; then
+  AGENT="$(resolve_agent_type_from_registry "$SESSION_NAME")" || AGENT=""
+  [ -n "$AGENT" ] || {
+    echo "ERROR: cannot infer agent from '$SESSION_NAME'; pass --agent" >&2
+    exit 2
+  }
+fi
 
 TARGET_CWD=$(printf '%s' "$MAPPED_DATA" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("cwd",""))')
 DELEGATE_JOB_ID=$(printf '%s' "$MAPPED_DATA" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("job_id",""))')
@@ -198,12 +264,6 @@ if [ "$PURGE" = "1" ] && [ "$YES" != "1" ]; then
   exit 3
 fi
 
-# purge 대상 UUID 를 워크스페이스 격리해서 해결 (P0-C — 전역 참조 금지)
-PURGE_UUID=""
-if [ "$PURGE" = "1" ] && [ -n "$TARGET_CWD" ]; then
-  PURGE_UUID=$(find_workspace_uuid "$TARGET_CWD" "$AGENT" "$SESSION_NAME" || true)
-fi
-
 NOW_ISO=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
 NOW_EPOCH=$(date +%s)
 
@@ -215,17 +275,19 @@ if herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
   LAST_STATUS=$(herdr capture-pane -t "$SESSION_NAME" -p -S -10 2>/dev/null | tr '\n' ' ' | head -c 500 || true)
 fi
 
-# 캡처: kill 직전에 conversation id 를 해결 (process/jsonl 이 아직 살아있을 때).
+# Issue #63: before the kill, decide the id this stop records and a purge
-# find_workspace_uuid 가 tier-1(row) -> tier-2(workspace-scoped disk scan)
+# deletes (lib_py.agents.session_ids): the row's own id; else, for an agent
-# 를 알아서 시도하므로 herdr 생사와 무관하게 동작.
+# that writes its id after its first turn, only what the #40 capture proves is
-CAPTURED_UUID=""
+# this pane's (nothing once herdr is dead - the reason goes on the row); claude
-if [ "$CAPTURE_ID" = "1" ] && [ -n "$TARGET_CWD" ]; then
+# and grok keep find_workspace_uuid. An id another row records is never used.
-  CAPTURED_UUID=$(capture_conversation_id "$AGENT" "$TARGET_CWD" "$SESSION_NAME" || true)
+CAPTURED_UUID="" CAPTURE_STATUS="" PURGE_UUID="" STOP_ID_NOTE=""
-  if [ -n "$CAPTURED_UUID" ]; then
+if [ -n "$TARGET_CWD" ]; then
-    echo "captured conversation id: $CAPTURED_UUID"
+  PANE_PID_NOW=""
-  else
+  [ "$HERDR_ALIVE" = "1" ] && PANE_PID_NOW=$(herdr list-panes -t "$SESSION_NAME" -F '#{pane_pid}' 2>/dev/null | head -1 || true)
-    echo "WARN: no conversation id resolved before stop (nothing on disk yet)"
+  eval "$(mam_session_ids stop --session "$SESSION_NAME" --agent "$AGENT" --cwd "$TARGET_CWD" \
-  fi
+    --herdr-alive "$HERDR_ALIVE" --pane-pid "$PANE_PID_NOW" --purge "$PURGE")" || true
+  if [ -n "$CAPTURED_UUID" ]; then echo "captured conversation id: $CAPTURED_UUID"
+  else echo "WARN: no conversation id recorded before stop${STOP_ID_NOTE:+ - $STOP_ID_NOTE}"; fi
 fi
 
 delegate_publish_event "$DELEGATE_JOB_ID" progress "terminating" "$DELEGATE_JOB_TOKEN" "$DELEGATE_JOB_ATTEMPT"
@@ -275,7 +337,7 @@ if [ "$PURGE" = "1" ] && [ "$HERDR_ALIVE" = "1" ]; then
   if herdr has-session -t "$SESSION_NAME" 2>/dev/null; then
     echo "ERROR: session '$SESSION_NAME' is still alive after the kill chain." >&2
     echo "  Refusing registry removal — records preserved (no state was modified)." >&2
-    echo "  Diagnose the stuck TUI (herdr session attach '$SESSION_NAME'), then re-run" >&2
+    echo "  Diagnose the stuck TUI ($(session_attach_command "$SESSION_NAME" "${HERDR_SESSION_NAME:-default}")), then re-run" >&2
     echo "  stop_session.sh --purge-conversation --yes (retry is safe/idempotent)." >&2
     delegate_publish_event "$DELEGATE_JOB_ID" cancelled "purge aborted: session still alive; no state was modified" "$DELEGATE_JOB_TOKEN" "$DELEGATE_JOB_ATTEMPT"
     exit 4
@@ -304,7 +366,7 @@ atomic_dump_yaml "$AGENT_SESSIONS_YAML" \
   SESSION_NAME="$SESSION_NAME" AGENT="$AGENT" PURGE="$PURGE" \
   NOW_ISO="$NOW_ISO" NOW_EPOCH="$NOW_EPOCH" LAST_STATUS="$LAST_STATUS" \
   PURGE_UUID="$PURGE_UUID" TARGET_CWD="$TARGET_CWD" \
-  REASON="$REASON" CAPTURED_UUID="$CAPTURED_UUID" <<'PYEOF'
+  REASON="$REASON" CAPTURED_UUID="$CAPTURED_UUID" CAPTURE_STATUS="$CAPTURE_STATUS" STOP_ID_NOTE="$STOP_ID_NOTE" <<'PYEOF'
 import shutil
 name = os.environ['SESSION_NAME']
 agent = os.environ['AGENT']
@@ -326,6 +388,19 @@ if target is None:
     print(f"ERROR: disappeared during script: {name}", flush=True)
     raise SystemExit(1)
 
+from lib_py.agents.autopin import claimed_elsewhere, pin_row
+capture_status = os.environ.get('CAPTURE_STATUS', '').strip()
+note = os.environ.get('STOP_ID_NOTE', '').strip()
+claimed = set(claimed_elsewhere(target, d))
+if captured and captured in claimed:
+    print(f"WARN: refusing to record {captured} on {name}; another row already claims it", flush=True)
+    if not note:
+        note = f"{captured} is already claimed by another row"
+    captured = ''
+if purge_uuid and purge_uuid in claimed:
+    print(f"WARN: refusing to purge {purge_uuid} for {name}; another row claims it", flush=True)
+    purge_uuid = ''
+
 if not purge:
     target['status'] = 'stopped'
     target['stopped_at'] = now
@@ -350,7 +425,11 @@ if captured and not purge:
         target['opencode_session_id_own'] = captured
     elif agent == 'codex':
         target['codex_session_id_own'] = captured
+    if capture_status == 'captured':
+        pin_row(target, agent, captured)
     target['resumable'] = True
+elif not purge and note:
+    target['last_visible_status'] = f"stop: {note}"
 
 if purge and purge_uuid:
     from lib_py.agents.registry import get_adapter
@@ -379,6 +458,7 @@ if purge:
 else:
     print(f"updated: {name} status={target['status']}", flush=True)
 PYEOF
+mam_update_admit_release
 
 delegate_publish_event "$DELEGATE_JOB_ID" cancelled "session stopped by operator before job completion" "$DELEGATE_JOB_TOKEN" "$DELEGATE_JOB_ATTEMPT"
 

.agents/skills/multi-agent-mux-update/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: multi-agent-mux-update
+description: "Update an installed MAM workspace in place to the latest version. Refuses while a session, an open job, a review loop or an unknown monitor is live; stops the monitor daemon and starts it again afterwards; rolls everything back if the install fails; converts the registry with the newly installed code. Use instead of the removed .mam_deploy/update.sh."
+version: 4.12.0
+author: godopu
+license: MIT
+platforms: [linux, macos]
+environments: [terminal, herdr]
+metadata:
+  hermes:
+    tags: [update, install, registry, migration]
+    related_skills: [multi-agent-mux-stop, multi-agent-mux-resume, multi-agent-mux-monitor]
+---
+
+# Multi-Agent Update
+
+```bash
+bash .agents/skills/multi-agent-mux-update/scripts/update.sh --yes
+```
+
+| Item | Behaviour |
+|---|---|
+| Where | An installed workspace only (`.mam_deploy/remove.sh` present). A git checkout updates with `git pull`. |
+| Confirmation | `[y/N]` prompt; without a terminal `-y`/`--yes` is required. There is no force option. |
+| Refused when | a running registry row, a live herdr agent whose cwd is in the workspace (any running server), an open job (an unreadable job JSON or jobs directory included, `dry_run` excluded), a live loop marker, `.mam/monitor.lock` held by a monitor the skills did not start, or another update. The calling agent (its herdr server + pane, row and one running job) is not counted. Each refusal lists the cleanup; nothing is changed. |
+| During the update | create, resume, `run_loop.sh`, delegate submit, stop and orc-onboard refuse (`.mam/update-in-progress`, `.mam/update-admission.lock`). They refuse during the update's checks too, even when the update is then refused; run them again afterwards. create and resume also take the lock of every other installed workspace at or above the session's `--workspace`. |
+| Monitor | stopped first, started again afterwards only if it ran (`MAM_NO_SUBSCRIBER_DAEMON=1`: not started). |
+| Install | the installer at `MAM_INSTALLER_URL` (default: Gitea `main`) runs in place; `.mam` is kept. On failure `.agents/`, `.mam_deploy/`, root files, `.venv`, the installer's `.mam` files and the registry are restored from `.mam/update-backup/`. |
+| Registry | converted by the new code (`lib_py.registry_format`); a failed conversion keeps the install and exits nonzero. |
+| Exit | `0` updated (or cancelled at the prompt), `1` refused or failed, `2` bad arguments; a failed registry conversion after a good install exits with the converter's nonzero code. |

.agents/skills/multi-agent-mux-update/scripts/install_phase.sh

@@ -0,0 +1,129 @@
+#!/usr/bin/env bash
+# install_phase.sh — multi-agent-mux-update, the part that changes the tree (Issue #72, decision 5).
+#
+#   install_phase.sh run <workspace> <monitor_was_running 0|1> <tmpdir>
+#   install_phase.sh restore <workspace> [--skip-registry]
+#
+# update.sh copies this file outside the workspace and execs the copy (same
+# pid and start time, so its .mam/update-in-progress marker stays live). From
+# here on the tree is being replaced, so this calls no lib.sh or lib_py: it runs
+# the installer in place, and on failure restores .mam/update-backup/ and starts
+# the monitor again with the restored (old, whole) tree's start_watchdog. On
+# success phase 2 is the NEW tree's post_update.sh, in a child process. It ends
+# by removing the backup and the marker (only its own: pid + lstart).
+# Must run on macOS bash 3.2.
+set -uo pipefail
+
+MODE="${1:-}"
+WS="${2:-}"
+[ -n "$MODE" ] && [ -d "$WS" ] || { echo "usage: $0 run|restore <workspace> ..." >&2; exit 2; }
+BK="$WS/.mam/update-backup"
+
+set_state() { printf '%s\n' "$1" > "$BK/state.tmp" && mv -f "$BK/state.tmp" "$BK/state"; }
+
+# Puts back every backed-up item, removes the ones that did not exist before,
+# then (unless --skip-registry) the registry: the DB from the backup, its
+# -wal/-shm removed (macOS keeps them after close).
+restore() {
+  local rel n
+  [ -f "$BK/items" ] || { echo "ERROR: $BK/items is missing" >&2; return 1; }
+  while IFS= read -r rel; do
+    [ -n "$rel" ] || continue
+    rm -rf "${WS:?}/$rel" || return 1
+    grep -Fqx -- "$rel" "$BK/absent" 2>/dev/null && continue
+    mkdir -p "$(dirname "$WS/$rel")" && cp -pPR "$BK/files/$rel" "$WS/$rel" || return 1
+  done < "$BK/items"
+  [ "${1:-}" = "--skip-registry" ] && return 0
+  for n in agent-sessions.yaml agent-sessions.yaml.bak agent-sessions.db; do
+    rm -f "$WS/.mam/$n" || return 1
+    if [ -f "$BK/registry/$n" ]; then
+      cp -p "$BK/registry/$n" "$WS/.mam/$n" || return 1
+    fi
+  done
+  rm -f "$WS/.mam/agent-sessions.db-wal" "$WS/.mam/agent-sessions.db-shm"
+}
+
+release_marker() {
+  local m="$WS/.mam/update-in-progress" pid lstart cur
+  [ -f "$m" ] || return 0
+  pid="$(grep '^pid=' "$m" | head -n 1 | cut -d= -f2-)"
+  lstart="$(grep '^lstart=' "$m" | head -n 1 | cut -d= -f2-)"
+  cur="$(ps -p $$ -o lstart= 2>/dev/null | tr -s ' ' | sed 's/^ *//;s/ *$//')"
+  if [ "$pid" = "$$" ] && [ "$lstart" = "$cur" ]; then
+    rm -f "$m"
+  fi
+}
+
+restart_old_monitor() {
+  [ "$1" = "1" ] || return 0
+  if [ "${MAM_NO_SUBSCRIBER_DAEMON:-0}" = "1" ]; then
+    echo "monitor: not restarted (MAM_NO_SUBSCRIBER_DAEMON=1)"
+    return 0
+  fi
+  local pid
+  if pid="$(bash -c 'source "$1/.agents/skills/lib.sh" && start_watchdog update "$1"' _ "$WS")"; then
+    echo "monitor: restarted (PID $pid)"
+  else
+    echo "ERROR: could not restart the monitor daemon" >&2
+  fi
+}
+
+case "$MODE" in
+  restore)
+    restore "${3:-}"
+    exit $?
+    ;;
+  run) ;;
+  *) echo "usage: $0 run|restore <workspace> ..." >&2; exit 2 ;;
+esac
+
+MON="${3:-0}"
+TMPD="${4:-}"
+trap '[ -z "$TMPD" ] || rm -rf "$TMPD"' EXIT
+
+if ! set_state installing; then
+  # Nothing was installed yet: drop the backup and put the monitor back as phase 1 found it.
+  echo "ERROR: cannot write $BK/state; nothing was changed" >&2
+  rm -rf "$BK"
+  restart_old_monitor "$MON"
+  release_marker
+  exit 1
+fi
+URL="${MAM_INSTALLER_URL:-https://git.godopu.com/tmpl/multi-agent-mux/raw/branch/main/deploy/install.sh}"
+echo "install: $URL"
+irc=0
+if command -v curl >/dev/null 2>&1; then
+  curl -fsSL "$URL" | bash -s -- "$WS" || irc=$?
+elif command -v wget >/dev/null 2>&1; then
+  wget -qO- "$URL" | bash -s -- "$WS" || irc=$?
+else
+  echo "ERROR: neither curl nor wget is available to fetch the installer" >&2
+  irc=1
+fi
+
+if [ "$irc" -ne 0 ]; then
+  echo "ERROR: the install failed (rc $irc); rolling back" >&2
+  if restore; then
+    rm -rf "$BK"
+    echo "rolled back: the workspace is at the version it had before the update"
+    restart_old_monitor "$MON"
+  else
+    echo "ERROR: the rollback failed; the backup is kept at $BK (the next update restores it)" >&2
+  fi
+  release_marker
+  exit 1
+fi
+set_state installed
+
+POST="$WS/.agents/skills/multi-agent-mux-update/scripts/post_update.sh"
+prc=0
+if [ -f "$POST" ]; then
+  bash "$POST" --monitor "$MON" || prc=$?
+else
+  echo "ERROR: the installed version has no $POST; the registry converts on its next write and the monitor was not restarted" >&2
+  prc=1
+fi
+rm -rf "$BK"
+release_marker
+[ "$prc" -eq 0 ] && echo "Update complete."
+exit "$prc"

.agents/skills/multi-agent-mux-update/scripts/post_update.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+# post_update.sh — multi-agent-mux-update phase 2 (Issue #72, decision 5).
+#   post_update.sh --monitor <0|1>
+#
+# Run by install_phase.sh from the NEWLY installed tree, in its own process:
+# converts the registry with the new code's entry point (lib_py.registry_format,
+# #71) and starts the monitor again if it ran before the update. Exit 0, or
+# nonzero when the conversion or the monitor restart failed (the install is
+# kept either way: the registry converts again on its next write).
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+WS="$(cd -P "$SCRIPT_DIR/../../../.." && pwd -P)"
+export WORKSPACE_ROOT="$WS"
+export AGENT_SESSIONS_YAML="$WS/.mam/agent-sessions.yaml"
+# shellcheck disable=SC1091
+source "$WS/.agents/skills/lib.sh"
+
+MON=0
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --monitor) MON="$2"; shift 2 ;;
+    *) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
+  esac
+done
+
+rc=0
+if [ ! -f "$AGENT_SESSIONS_YAML" ] && [ ! -f "$WS/.mam/agent-sessions.db" ]; then
+  echo "registry: nothing to convert (no registry)"
+else
+  "$(_delegate_py_bin)" -m lib_py.registry_format --yaml "$AGENT_SESSIONS_YAML" || rc=$?
+  if [ "$rc" -ne 0 ]; then
+    echo "ERROR: the registry was not converted (rc $rc); the install is kept and the next registry write converts it" >&2
+  fi
+fi
+
+if [ "$MON" = "1" ]; then
+  if [ "${MAM_NO_SUBSCRIBER_DAEMON:-0}" = "1" ]; then
+    echo "monitor: not restarted (MAM_NO_SUBSCRIBER_DAEMON=1)"
+  # shellcheck disable=SC2086
+  elif pid="$(start_watchdog update "$WS")" && mam_monitor_started "$WS" $pid; then
+    echo "monitor: restarted (PID $pid)"
+  else
+    echo "ERROR: could not restart the monitor daemon" >&2
+    rc=1
+  fi
+fi
+exit "$rc"

.agents/skills/multi-agent-mux-update/scripts/update.sh

@@ -0,0 +1,267 @@
+#!/usr/bin/env bash
+# update.sh — multi-agent-mux-update (Issue #72): update an installed workspace in place.
+# Usage:
+#   bash .agents/skills/multi-agent-mux-update/scripts/update.sh [-y|--yes]
+#
+# Phase 1 (this script, the installed code): publish .mam/update-in-progress
+# under the admission lock (lib.sh mam_update_admit is the other side), refuse
+# while anything live could see the tree change (lib_py/update.py precheck, a
+# live loop marker, a monitor.lock held by a monitor the skills did not start),
+# stop the monitor daemon, back up what the install can change into
+# .mam/update-backup/, then exec a copy of install_phase.sh outside the tree.
+# That copy runs the installer (MAM_INSTALLER_URL) in place, rolls back on
+# failure, and runs phase 2 (post_update.sh of the NEW tree) on success.
+#
+# Exit codes:
+#   0 = updated (registry converted or nothing to convert)
+#   1 = refused or failed; what was changed and restored is printed
+#   2 = invalid args
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+WS="$(cd -P "$SCRIPT_DIR/../../../.." && pwd -P)"
+export WORKSPACE_ROOT="$WS"
+export AGENT_SESSIONS_YAML="$WS/.mam/agent-sessions.yaml"
+# shellcheck disable=SC1091
+source "$WS/.agents/skills/lib.sh"
+# shellcheck disable=SC1091
+source "$SKILL_DIR/multi-agent-mux-loop/scripts/loop_lock.sh"
+
+YES=0
+while [ $# -gt 0 ]; do
+  case "$1" in
+    -y|--yes) YES=1; shift ;;
+    -h|--help) sed -n '2,4p' "${BASH_SOURCE[0]}"; exit 0 ;;
+    *) echo "ERROR: unknown arg: $1" >&2; exit 2 ;;
+  esac
+done
+
+MAM="$WS/.mam"
+MARKER="$MAM/update-in-progress"
+BK="$MAM/update-backup"
+PY="$(_delegate_py_bin)"
+
+if [ ! -f "$WS/.mam_deploy/remove.sh" ] && [ ! -f "$WS/remove.sh" ]; then
+  echo "ERROR: $WS is not an installed MAM workspace (no .mam_deploy/remove.sh); a git checkout updates with git pull" >&2
+  exit 1
+fi
+
+if [ "$YES" != "1" ]; then
+  if [ ! -t 0 ]; then
+    echo "ERROR: not a terminal; run with -y/--yes" >&2
+    exit 1
+  fi
+  ans=""
+  read -r -p "Update MAM in $WS to the latest version? [y/N]: " ans || ans=""
+  case "$ans" in
+    y|Y|yes|Yes|YES) ;;
+    *) echo "Update cancelled."; exit 0 ;;
+  esac
+fi
+
+# --- the marker, published under the exclusive admission lock (decision 8) ---
+mkdir -p "$MAM"
+exec 7>>"$MAM/update-admission.lock"
+case "$("$PY" -m lib_py.pane_lock acquire --fd 7 --wait-env MAM_UPDATE_ADMISSION_WAIT_S)" in
+  locked) ;;
+  timeout)
+    echo "ERROR: a create, resume, loop, delegate submit, stop or orc-onboard kept the admission lock past MAM_UPDATE_ADMISSION_WAIT_S; nothing was changed, try again" >&2
+    exit 1 ;;
+  *)
+    echo "ERROR: the admission lock $MAM/update-admission.lock could not be decided (lib_py.pane_lock); nothing was changed" >&2
+    exit 1 ;;
+esac
+if [ -f "$MARKER" ] && [ "$(_mam_lock_holder_state "$MARKER")" = "stale" ]; then
+  echo "NOTE: stale update marker (pid $(_mam_lock_field "$MARKER" pid)) taken over; its update is gone"
+fi
+marker_rc=0
+mam_acquire_loop_lock "$MARKER" || marker_rc=$?
+exec 7>&-
+case "$marker_rc" in
+  0) ;;
+  3) echo "ERROR: another update is in progress (pid $(_mam_lock_field "$MARKER" pid)); nothing was changed" >&2; exit 1 ;;
+  *) echo "ERROR: cannot tell whether another update is in progress (ps unavailable?); nothing was changed" >&2; exit 1 ;;
+esac
+
+TMPD=""
+MONITOR_WAS_RUNNING=0
+RESTART_MONITOR=0
+_phase1_exit() {
+  local rc=$?
+  if [ "$RESTART_MONITOR" = "1" ]; then
+    _restart_monitor || true
+  fi
+  mam_release_loop_lock "$MARKER" || true
+  [ -z "$TMPD" ] || rm -rf "$TMPD"
+  exit "$rc"
+}
+trap _phase1_exit EXIT
+
+_restart_monitor() {
+  if [ "${MAM_NO_SUBSCRIBER_DAEMON:-0}" = "1" ]; then
+    echo "monitor: not restarted (MAM_NO_SUBSCRIBER_DAEMON=1)"
+    return 0
+  fi
+  local pid
+  pid=$(start_watchdog update "$WS") || { echo "ERROR: could not restart the monitor daemon" >&2; return 1; }
+  # shellcheck disable=SC2086
+  mam_monitor_started "$WS" $pid || { echo "ERROR: could not restart the monitor daemon (PID ${pid:-none} is not its monitor)" >&2; return 1; }
+  echo "monitor: restarted (PID $pid)"
+}
+
+_monitor_json() {
+  "$PY" -m lib_py.update monitor --workspace "$WS"
+}
+_json_field() {
+  "$PY" -c 'import json,sys; v=json.load(sys.stdin)[sys.argv[1]]; print(" ".join(v) if isinstance(v, list) else v)' "$1"
+}
+
+# --- pre-check: refuse before any change (decisions 1, 7; U3) ---
+BLOCKERS=""
+_block() { BLOCKERS="${BLOCKERS}  - $1
+"; }
+
+if [ -f "$MAM/loop-guard-active" ]; then
+  loop_st="$(_mam_lock_holder_state "$MAM/loop-guard-active")"
+  case "$loop_st" in
+    stale) echo "NOTE: stale loop marker $MAM/loop-guard-active (its loop is gone); not a reason to refuse" ;;
+    *) _block "a review loop is running (pid $(_mam_lock_field "$MAM/loop-guard-active" pid), holder $loop_st); wait for it to end" ;;
+  esac
+fi
+
+STATE_JSON=""
+if ! STATE_JSON="$(load_state_json strict)"; then
+  _block "the registry $AGENT_SESSIONS_YAML cannot be read; fix it first"
+  STATE_JSON='{}'
+fi
+REAL_HERDR="$(_resolve_real_herdr_path || true)"
+if [ -z "$REAL_HERDR" ]; then
+  _block "no herdr binary found on PATH, so the live agents cannot be listed"
+else
+  pre_out=""
+  pre_rc=0
+  pre_out="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.update precheck --workspace "$WS" --herdr "$REAL_HERDR")" || pre_rc=$?
+  if [ "$pre_rc" -ne 0 ]; then
+    while IFS= read -r line; do
+      [ -n "$line" ] && _block "$line"
+    done <<< "${pre_out:-lib_py.update precheck failed (rc $pre_rc)}"
+  fi
+fi
+
+MON_JSON="$(_monitor_json)" || { _block "cannot inspect the monitor daemon (lib_py.update monitor)"; MON_JSON='{"pids": [], "lock": "free"}'; }
+MON_PIDS="$(printf '%s' "$MON_JSON" | _json_field pids)"
+MON_LOCK="$(printf '%s' "$MON_JSON" | _json_field lock)"
+if [ -z "$MON_PIDS" ] && [ "$MON_LOCK" = "held" ]; then
+  _block "$MAM/monitor.lock is held by a monitor the skills did not start (not 'bash $WS/.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh --subscribe'); stop it (find it with: pgrep -af reconcile.sh) and try again"
+fi
+
+if [ -n "$BLOCKERS" ]; then
+  echo "ERROR: update refused; nothing was changed:" >&2
+  printf '%s' "$BLOCKERS" >&2
+  exit 1
+fi
+
+# --- stop the monitor daemon (decision 2) ---
+_monitor_gone() {
+  local p
+  for p in "$@"; do
+    kill -0 "$p" 2>/dev/null && return 1
+  done
+  [ "$(_monitor_json | _json_field lock)" = "free" ]
+}
+_wait_monitor_gone() {
+  local deadline=$(( $(date +%s) + $1 ))
+  shift
+  while :; do
+    _monitor_gone "$@" && return 0
+    [ "$(date +%s)" -lt "$deadline" ] || return 1
+    sleep 0.5
+  done
+}
+if [ -n "$MON_PIDS" ]; then
+  MONITOR_WAS_RUNNING=1
+  # shellcheck disable=SC2086
+  set -- $MON_PIDS
+  kids=""
+  for p in "$@"; do kids="$kids $(pgrep -P "$p" 2>/dev/null | tr '\n' ' ' || true)"; done
+  echo "monitor: stopping the daemon (PID $MON_PIDS)"
+  kill -TERM "$@" 2>/dev/null || true
+  if ! _wait_monitor_gone "$(mam_int_knob MAM_UPDATE_MONITOR_STOP_S 30 1)" "$@"; then
+    # SIGKILL only what is still this workspace's monitor: a PID that ended
+    # during the wait may already be another process's.
+    still=""
+    for p in $(_monitor_json | _json_field pids); do
+      case " $* " in *" $p "*) still="$still $p" ;; esac
+    done
+    # shellcheck disable=SC2086
+    set -- $still
+    for p in "$@"; do kids="$kids $(pgrep -P "$p" 2>/dev/null | tr '\n' ' ' || true)"; done
+    echo "WARNING: the monitor did not stop within MAM_UPDATE_MONITOR_STOP_S; sending SIGKILL to $* $kids" >&2
+    # shellcheck disable=SC2086
+    kill -KILL "$@" $kids 2>/dev/null || true
+    # shellcheck disable=SC2086
+    if _wait_monitor_gone 5 "$@" $kids; then
+      echo "ERROR: the monitor did not stop in time; it was killed and is started again. Nothing else was changed." >&2
+      _restart_monitor || true
+      exit 1
+    fi
+    echo "ERROR: could not restore the monitor state: PIDs still alive or monitor.lock still held ($*$kids; lock $(_monitor_json | _json_field lock)). Nothing else was changed." >&2
+    exit 1
+  fi
+  RESTART_MONITOR=1
+fi
+
+TMPD="$(mktemp -d "${TMPDIR:-/tmp}/mam-update.XXXXXX")"
+cp "$SCRIPT_DIR/install_phase.sh" "$TMPD/install_phase.sh"
+
+# --- a leftover backup of an update that died (U4) ---
+if [ -e "$BK" ]; then
+  left_st="$(cat "$BK/state" 2>/dev/null || true)"
+  case "$left_st" in
+    ""|backing-up|installed)
+      echo "NOTE: removing the backup a previous update left (state ${left_st:-none}); nothing to restore"
+      rm -rf "$BK" ;;
+    installing)
+      echo "NOTE: a previous update died during its install; restoring its backup (the registry is left as it is)"
+      if ! bash "$TMPD/install_phase.sh" restore "$WS" --skip-registry; then
+        RESTART_MONITOR=0
+        echo "ERROR: restoring the previous update's backup failed; it is kept at $BK. Nothing more was changed; the monitor stays stopped." >&2
+        exit 1
+      fi
+      rm -rf "$BK"
+      echo "the previous update was rolled back" ;;
+    *)
+      echo "ERROR: $BK has an unknown state '$left_st'; it is kept and nothing was changed. Check it and remove it by hand." >&2
+      exit 1 ;;
+  esac
+fi
+
+# --- the rollback backup (decisions 3, 10; U4) ---
+_set_state() { printf '%s\n' "$1" > "$BK/state.tmp" && mv -f "$BK/state.tmp" "$BK/state"; }
+ITEMS=".agents .mam_deploy AGENTS.md MESSAGING.md BOOTSTRAP.md BOOTSTRAP.ko.md .mam.env.example .mam.env .gitignore remove.sh update.sh .venv .mam/install_manifest.txt .mam/install_state .mam/asset_hashes.txt .mam/version.txt .mam/base .mam/skill-backups"
+_backup() {
+  mkdir -p "$BK/files" || return 1
+  _set_state backing-up || return 1
+  : > "$BK/items" && : > "$BK/absent" || return 1
+  local rel
+  for rel in $ITEMS; do
+    printf '%s\n' "$rel" >> "$BK/items" || return 1
+    if [ -e "$WS/$rel" ] || [ -L "$WS/$rel" ]; then
+      mkdir -p "$BK/files/$(dirname "$rel")" && cp -pPR "$WS/$rel" "$BK/files/$rel" || return 1
+    else
+      printf '%s\n' "$rel" >> "$BK/absent" || return 1
+    fi
+  done
+  "$PY" -m lib_py.update backup-registry --workspace "$WS" --dest "$BK/registry" >/dev/null
+}
+echo "backup: $BK"
+if ! _backup; then
+  rm -rf "$BK"
+  echo "ERROR: the backup could not be made; nothing was changed" >&2
+  exit 1
+fi
+
+# --- hand over to the copy (decision 5): same pid, so the marker stays live ---
+RESTART_MONITOR=0
+trap - EXIT
+exec bash "$TMPD/install_phase.sh" run "$WS" "$MONITOR_WAS_RUNNING" "$TMPD"

BOOTSTRAP.ko.md

@@ -2,7 +2,7 @@
 
 본 문서는 `herdr_agent_orchestration` 오케스트레이션 및 메시징 백플레인 워크플로우를 새로운 프로젝트에 도입하여 이식하고, 새로운 개발자/에이전트가 초기 가동을 시작할 때 수행해야 하는 환경 설정 및 구축 절차를 안내합니다.
 
-[![Version: v4.9.8](https://img.shields.io/badge/version-v4.9.8-blue.svg)](VERSIONS.md)
+[![Version: v4.12.0](https://img.shields.io/badge/version-v4.12.0-blue.svg)](VERSIONS.md)
 
 새로운 에이전트는 이 안내서에 기술된 절차를 순차적으로 실행하여 초기 환경을 안정적으로 설정할 수 있습니다.
 

BOOTSTRAP.md

@@ -2,7 +2,7 @@
 
 This document guides you through the setup and initialization procedures required to adopt the `herdr_agent_orchestration` orchestration and messaging backplane workflow in a new project, enabling a new developer or agent to get up and running quickly.
 
-[![Version: v4.9.8](https://img.shields.io/badge/version-v4.9.8-blue.svg)](VERSIONS.md)
+[![Version: v4.12.0](https://img.shields.io/badge/version-v4.12.0-blue.svg)](VERSIONS.md)
 
 A new agent can follow the steps in this guide sequentially to establish a stable and reliable initial environment.
 

INSTRUCTION.md

@@ -0,0 +1,13 @@
+# INSTRUCTION.md
+
+MAM 자체(이 저장소)를 개발할 때 따르는 지침입니다. 설치된 프로젝트에는 복사되지 않습니다.
+
+## 1. 스킬 작성: 지침보다 코드를 먼저
+
+- 스킬이 하는 일 가운데 코드로 쓸 수 있는 것(순서, 사전 확인, 거부, 잠금, 정리, 되돌리기)은 SKILL.md 의 지침으로 적지 않고 스크립트에 구현합니다. 그리고 테스트로 고정합니다.
+- SKILL.md 에는 에이전트의 판단이 필요한 것만 남깁니다.
+  - 언제 이 스킬을 쓰는지(쓰지 않을 때 포함)
+  - 옵션을 어떻게 고르는지
+  - 종료 코드와 출력의 해석
+  - 주의할 점
+- SKILL.md 가 설명하는 동작은 코드와 같아야 합니다. 둘이 다르면 코드를 기준으로 문서를 고칩니다. 문서대로 동작해야 한다면 코드를 고치고 테스트를 더합니다.

MESSAGING.md

@@ -1,6 +1,6 @@
 # Messaging System Technical Analysis & Architecture Report
 
-Applies to: MAM v4.9.8
+Applies to: MAM v4.12.0
 
 This report provides a comprehensive, deep-dive analysis of the messaging system implemented in the `multi-agent-mux-delegate-job` skill. It covers the MQTT broker architecture, event protocols, job lifecycles, codebase internals, cross-system integration, and a list of known limitations along with production recommendations.
 

README.ko.md

@@ -2,7 +2,7 @@
 
 [herdr](https://herdr.dev)와 MQTT 위에 만든 **다중 에이전트 오케스트레이션·메시징 백플레인**입니다. 장시간 실행되는 코딩 에이전트(`claude`, `agy`, `hermes`, `grok`, `opencode`, `codex`)를 격리된 herdr pane 에서 돌리고, 작업을 추적되는 잡으로 위임하며, 모든 리뷰어가 통과시킬 때까지 planner / creator / reviewer 루프를 돌립니다.
 
-[![Version: v4.9.8](https://img.shields.io/badge/version-v4.9.8-blue.svg)](VERSIONS.md)
+[![Version: v4.12.0](https://img.shields.io/badge/version-v4.12.0-blue.svg)](VERSIONS.md)
 
 ---
 
@@ -38,7 +38,7 @@ bash deploy/install.sh
 - `MQTT_BROKER=localhost` 로 된 초기 `.mam.env` 를 씁니다. 이미 있는 `.mam.env` 는 그대로 둡니다. 예전 `.env` 만 있으면 그것을 `.mam.env` 로 복사하고 원본은 남깁니다.
 - `.venv`, `.mam/`, `.mam.env` 를 `.gitignore` 에 추가합니다.
 
-`.mam.env` 의 `MQTT_BROKER` 를 직접 운영하는 브로커로 바꾸십시오(사설 브로커는 [MESSAGING.md](MESSAGING.md) 참고). `MQTT_BROKER` 가 아예 설정되지 않으면 코드는 공개 브로커 `broker.hivemq.com` 을 씁니다. 시험용으로는 괜찮지만 실제 작업용은 아닙니다. `deploy/generate-env.sh` 는 `.mam.env` 가 없을 때 `.mam.env.example` 로 만듭니다(`--force` 는 `.mam.env.bak` 을 남기고 덮어씁니다). 업데이트와 제거는 `deploy/update.sh`, `deploy/remove.sh` 입니다. `deploy/install_mam.sh` 는 로컬 클론에서 다른 디렉터리로 복사해 설치하는 별도 설치기입니다.
+`.mam.env` 의 `MQTT_BROKER` 를 직접 운영하는 브로커로 바꾸십시오(사설 브로커는 [MESSAGING.md](MESSAGING.md) 참고). `MQTT_BROKER` 가 아예 설정되지 않으면 코드는 공개 브로커 `broker.hivemq.com` 을 씁니다. 시험용으로는 괜찮지만 실제 작업용은 아닙니다. `deploy/generate-env.sh` 는 `.mam.env` 가 없을 때 `.mam.env.example` 로 만듭니다(`--force` 는 `.mam.env.bak` 을 남기고 덮어씁니다). 업데이트는 `multi-agent-mux-update` 스킬, 제거는 `deploy/remove.sh` 입니다. `deploy/install_mam.sh` 는 로컬 클론에서 다른 디렉터리로 복사해 설치하는 별도 설치기입니다.
 
 ---
 
@@ -56,6 +56,7 @@ bash deploy/install.sh
 | **`multi-agent-mux-delegate-job`** | 세션(`herdr:<name>`)이나 다른 호스트의 러너(`remote:<name>`)에 잡을 위임하고 결과를 기다립니다. [위임 계약](#-위임-계약)을 보십시오. |
 | **`multi-agent-mux-loop`** | 계획·구현·리뷰: 선택적인 planner 와 creator, 그다음 선택한 리뷰어(`--reviewer A,B`, 또는 `--all-reviewer` 로 creator 를 뺀 실행 중인 리뷰어 전원)가 모두 `PASS` 를 낼 때까지(또는 `--max-loop` 까지). 둘 다 없으면 creator 가 스스로 리뷰합니다. 루프 밖에서 끝난 작업은 `--review-only` 로 리뷰합니다. 통과한 리포트는 `.agents/reports/<session>/` 으로 옮겨 보관합니다. |
 | **`multi-agent-mux-orc-onboard`** | 오케스트레이터 자신의 세션 ID 를 등록해, 세션 탐색이 그것을 하위 에이전트로 착각하지 않게 합니다. |
+| **`multi-agent-mux-update`** | 설치된 작업 공간을 제자리에서 업데이트합니다. 실행 중인 세션·열린 잡·루프가 있으면 거부하고, 모니터를 멈췄다가 원래대로 되돌리며, 설치가 실패하면 되돌리고, 새 코드로 레지스트리를 변환합니다. |
 
 ---
 
@@ -195,7 +196,7 @@ sequenceDiagram
 │       │   └── *.py                   # pane_lock, stall_watch, worktree, herdr_config, ...
 │       └── multi-agent-mux-*/         # 스킬마다 디렉터리 하나 (SKILL.md + scripts/)
 ├── .mam/                              # 런타임 상태 (git 제외): 세션, 잡, 감사 로그, shim
-├── deploy/                            # install.sh, install_mam.sh, update.sh, remove.sh, generate-env.sh
+├── deploy/                            # install.sh, install_mam.sh, remove.sh, generate-env.sh
 ├── docs/                              # contracts/, design/, 에이전트 통합·브리지 가이드
 ├── nats-docker/                       # 사설 NATS 브로커 배포 (서브모듈)
 ├── tests/                             # pytest 스위트

README.md

@@ -2,7 +2,7 @@
 
 A **Multi-Agent Orchestration & Messaging Backplane** built on [herdr](https://herdr.dev) and MQTT. It runs long-lived coding agents (`claude`, `agy`, `hermes`, `grok`, `opencode`, `codex`) in isolated herdr panes, delegates work to them as tracked jobs, and drives planner / creator / reviewer loops until every reviewer passes the change.
 
-[![Version: v4.9.8](https://img.shields.io/badge/version-v4.9.8-blue.svg)](VERSIONS.md)
+[![Version: v4.12.0](https://img.shields.io/badge/version-v4.12.0-blue.svg)](VERSIONS.md)
 
 ---
 
@@ -38,7 +38,7 @@ bash deploy/install.sh
 - writes a starter `.mam.env` with `MQTT_BROKER=localhost`. An existing `.mam.env` is kept. If only a legacy `.env` exists, it is copied to `.mam.env` and the original stays;
 - adds `.venv`, `.mam/` and `.mam.env` to `.gitignore`.
 
-Point `MQTT_BROKER` in `.mam.env` at a broker you run (see [MESSAGING.md](MESSAGING.md) for a private broker). If `MQTT_BROKER` is not set at all, the code falls back to the public `broker.hivemq.com`. That is fine for a trial, but not for real work. `deploy/generate-env.sh` creates `.mam.env` from `.mam.env.example` when it is missing (`--force` overwrites it, keeping a `.mam.env.bak`). `deploy/update.sh` and `deploy/remove.sh` update and uninstall. `deploy/install_mam.sh` is a separate installer that copies from a local clone into another directory.
+Point `MQTT_BROKER` in `.mam.env` at a broker you run (see [MESSAGING.md](MESSAGING.md) for a private broker). If `MQTT_BROKER` is not set at all, the code falls back to the public `broker.hivemq.com`. That is fine for a trial, but not for real work. `deploy/generate-env.sh` creates `.mam.env` from `.mam.env.example` when it is missing (`--force` overwrites it, keeping a `.mam.env.bak`). The `multi-agent-mux-update` skill updates an installed workspace, and `deploy/remove.sh` uninstalls. `deploy/install_mam.sh` is a separate installer that copies from a local clone into another directory.
 
 ---
 
@@ -56,6 +56,7 @@ Every skill lives under `.agents/skills/` with a `SKILL.md` that documents its o
 | **`multi-agent-mux-delegate-job`** | Delegates a job to a session (`herdr:<name>`) or to a runner on another host (`remote:<name>`) and waits for its result. See [Delegation contract](#-delegation-contract). |
 | **`multi-agent-mux-loop`** | Plan, implement, review: an optional planner and a creator, then the selected reviewers (`--reviewer A,B`, or `--all-reviewer` for every running reviewer except the creator) until all of them `PASS` or `--max-loop` is reached. With neither option the creator reviews its own work. `--review-only` reviews work finished outside the loop. Passing reports are promoted to `.agents/reports/<session>/`. |
 | **`multi-agent-mux-orc-onboard`** | Registers the orchestrator's own session id, so session discovery never mistakes it for a sub-agent. |
+| **`multi-agent-mux-update`** | Updates an installed workspace in place: refuses while sessions, open jobs or a loop are live; stops and restores the monitor; rolls back on a failed install; converts the registry with the new code. |
 
 ---
 
@@ -195,7 +196,7 @@ sequenceDiagram
 │       │   └── *.py                   # pane_lock, stall_watch, worktree, herdr_config, ...
 │       └── multi-agent-mux-*/         # One directory per skill (SKILL.md + scripts/)
 ├── .mam/                              # Runtime state (git-ignored): sessions, jobs, audit logs, shim
-├── deploy/                            # install.sh, install_mam.sh, update.sh, remove.sh, generate-env.sh
+├── deploy/                            # install.sh, install_mam.sh, remove.sh, generate-env.sh
 ├── docs/                              # contracts/, design/, agent integration and bridge guides
 ├── nats-docker/                       # Private NATS broker deployment (submodule)
 ├── tests/                             # pytest suite

VERSIONS.md

@@ -6,8 +6,8 @@
 
 ## 📌 현재 버전 개요 (Current Release)
 
-- **프레임워크 버전**: `v4.9.8`
+- **프레임워크 버전**: `v4.12.0`
-- **최신 릴리스 일시**: 2026-10-20 (KST)
+- **최신 릴리스 일시**: 2026-10-28 (KST)
 - **기준 브랜치**: `main`
 - **핵심 아키텍처**:
   - **Terminal 상태 단방향 불변성 (`engine.py`, Issue #6 Phase 1)**: `completed`, `error`, `cancelled` 터미널 상태 진입 후 후속 이벤트나 업데이트에 의한 덮어쓰기를 엄격히 차단(Terminal Immutability). `registry.py close` 서브커맨드 및 fail-closed 조기 종료 도입.
@@ -18,29 +18,183 @@
   - **워크트리 운영 모델 2단계 (Issue #21 항목 4·5·7)**: 워크트리 준비·해체 헬퍼(변경 전 판정, untracked 포함, 검증된 단일 `--force`), 리뷰 identity(라운드별 스냅샷·stale 재리뷰·승격 직전 재확인·`identity.json`), 수용 사례 A1–A8.
   - **잡 예산·라벨·멈춤 알림 (Issue #33·#30)**: 위임 잡 예산은 `--job-timeout`/`MAM_JOB_TIMEOUT_S`, 벽시계 초과는 `wall_clock_timeout`(무응답 `deadline_timeout` 과 구분), `lib_py/stall_watch.py` 가 `blocked`/`idle` 을 `progress stalled:*` 로 알리기만 한다(종결 근거는 #18 의 프로토콜 이벤트뿐).
   - **설정 파일 로더 하나 (Issue #26)**: `.mam.env` 는 `lib_py/delegation/envfile.py` 한 곳이 읽는다(셸 해석 없음, 환경변수 우선, 읽을 수 없는 파일은 오류). bash 산술에 들어가는 정수 설정값은 `mam_int` 로 10진수.
-  - **4-Way 버전 락스텝**: `lib.sh`(`MAM_VERSION`) ↔ `lib_py/loop/eager.py`(`FRAMEWORK_VERSION`) ↔ `VERSIONS.md` ↔ 8개 `SKILL.md`.
+  - **4-Way 버전 락스텝**: `lib.sh`(`MAM_VERSION`) ↔ `lib_py/loop/eager.py`(`FRAMEWORK_VERSION`) ↔ `VERSIONS.md` ↔ 9개 `SKILL.md`.
 
 ---
 
 ## 🧭 스킬 패키지 버전 매트릭스 (Skills Version Matrix)
 
-모든 8개 스킬은 YAML frontmatter 메타데이터(`author`, `version`, `platforms`, `environments`) 표준화를 통해 `v4.9.8`로 동기화되어 배포됩니다.
+모든 9개 스킬은 YAML frontmatter 메타데이터(`author`, `version`, `platforms`, `environments`) 표준화를 통해 `v4.12.0`로 동기화되어 배포됩니다.
 
 | 스킬명 | 버전 | 역할 및 주요 책임 | 상태 |
 | :--- | :---: | :--- | :---: |
-| **`multi-agent-mux-create`** | `4.9.8` | 에이전트 세션 신규 생성 및 Herdr 컨테이너 격리 스폰 | ✅ 배포 |
+| **`multi-agent-mux-create`** | `4.12.0` | 에이전트 세션 신규 생성 및 Herdr 컨테이너 격리 스폰 | ✅ 배포 |
-| **`multi-agent-mux-stop`** | `4.9.8` | 대화 UUID 원자적 캡처 및 세션 안전 종료 (Graceful Stop) | ✅ 배포 |
+| **`multi-agent-mux-stop`** | `4.12.0` | 대화 UUID 원자적 캡처 및 세션 안전 종료 (Graceful Stop) | ✅ 배포 |
-| **`multi-agent-mux-resume`** | `4.9.8` | 온디스크 대화 컨텍스트 기반 Tier-1 초고속 세션 복원 | ✅ 배포 |
+| **`multi-agent-mux-resume`** | `4.12.0` | 온디스크 대화 컨텍스트 기반 Tier-1 초고속 세션 복원 | ✅ 배포 |
-| **`multi-agent-mux-status`** | `4.9.8` | 실시간 Herdr 세션 및 레지스트리 드리프트 스냅샷 조회 | ✅ 배포 |
+| **`multi-agent-mux-status`** | `4.12.0` | 실시간 Herdr 세션 및 레지스트리 드리프트 스냅샷 조회 | ✅ 배포 |
-| **`multi-agent-mux-monitor`** | `4.9.8` | YAML ↔ 런타임 상태 간 자율 조정자 (Reconciler Loop) | ✅ 배포 |
+| **`multi-agent-mux-monitor`** | `4.12.0` | YAML ↔ 런타임 상태 간 자율 조정자 (Reconciler Loop) | ✅ 배포 |
-| **`multi-agent-mux-delegate-job`** | `4.9.8` | MQTT 이벤트 채널 기반 비동기 단위 작업 위임 | ✅ 배포 |
+| **`multi-agent-mux-delegate-job`** | `4.12.0` | MQTT 이벤트 채널 기반 비동기 단위 작업 위임 | ✅ 배포 |
-| **`multi-agent-mux-loop`** | `4.9.8` | Planner-Creator-Reviewer 3자 자율 계획·실행·피어리뷰 루프 | ✅ 배포 |
+| **`multi-agent-mux-loop`** | `4.12.0` | Planner-Creator-Reviewer 3자 자율 계획·실행·피어리뷰 루프 | ✅ 배포 |
-| **`multi-agent-mux-orc-onboard`** | `4.9.8` | 오케스트레이터 UUID 격리 등록 및 서브 세션 오염 방지 | ✅ 배포 |
+| **`multi-agent-mux-orc-onboard`** | `4.12.0` | 오케스트레이터 UUID 격리 등록 및 서브 세션 오염 방지 | ✅ 배포 |
+| **`multi-agent-mux-update`** | `4.12.0` | 설치된 작업 공간의 제자리 업데이트·되돌리기와 업데이트 중 입장 차단 | ✅ 배포 |
 
 ---
 
 ## 📋 버전별 상세 변경 내역 (Changelog)
 
+### 🚀 `v4.12.0` — update 스킬로 제자리 업데이트하고, 업데이트 중에는 세션·잡·루프의 시작을 막는다 (Issue #72) (2026-10-28)
+
+> **마이너 (MINOR Release)**: 설치된 작업 공간의 업데이트를 `.mam_deploy/update.sh` 대신 새 `multi-agent-mux-update` 스킬이 한다. 업데이트는 실행 중인 세션·열린 잡·루프가 있으면 거부하고, 모니터를 멈췄다가 다시 띄우며, 설치가 실패하면 되돌린다. 업데이트 중에는 create·resume·run_loop·delegate submit·stop·orc-onboard 가 거부한다. resume 이 모니터 데몬을 띄운다. 공개 진입점(`.mam_deploy/update.sh`)이 없어지고 기존 명령의 동작(업데이트 중 거부)이 늘어 MINOR 로 올린다. PR #75.
+
+#### ⚠️ 호환성
+- `.mam_deploy/update.sh` 와 `deploy/update.sh` 가 없어졌다. 업데이트는 `bash .agents/skills/multi-agent-mux-update/scripts/update.sh --yes` 로 한다. 설치기(`deploy/install.sh`)는 남아 있는 옛 `update.sh` 를 지운다.
+- 업데이트 중(`.mam/update-in-progress` 표식이 live/unknown)에는 create·resume·run_loop·delegate submit·stop·orc-onboard 가 거부한다. 이 명령들은 `.mam/update-admission.lock` 을 공유로 잡고, 기다리는 시간은 `MAM_UPDATE_ADMISSION_WAIT_S`(기본 120 s)다. `.mam` 이 없는 트리(개발 체크아웃)에서는 잠금을 만들지 않는다.
+- resume 이 끝나면 모니터 데몬(`reconcile.sh --subscribe`)을 띄운다. 이미 떠 있으면 새로 띄우지 않고, `MAM_NO_SUBSCRIBER_DAEMON=1` 이면 띄우지 않는다.
+- create·delegate-job·stop 의 attach 안내는 행의 `attach_command`(`herdr --session <server> agent attach <herdr 이름>`)를 보여 준다.
+- **첫 전환 (v4.11.0 이하 설치본, 옛 `update.sh` 로 한 번)**:
+  1. 루프가 끝나기를 기다리고, 열린 잡을 끝내거나 닫는다.
+  2. 세션을 모두 stop 한다.
+  3. 모니터(`reconcile.sh --subscribe`)를 멈춘다.
+  4. 옛 `.mam_deploy/update.sh` 를 실행한다.
+  5. 바로 update 스킬을 한 번 더 실행한다(레지스트리 변환).
+  - 4번의 옛 `update.sh` 는 `.mam` 을 지운 뒤 고정 목록만 되돌리므로 `herdr_workspace_id`, `diagnostics/`, 모니터 로그, `shim/`(lib.sh 가 다시 만듦), 있다면 `briefs/`·`resumelogs/`·`stoplogs/` 를 잃는다.
+  - 첫 전환 뒤에는 모니터가 없다. resume 하면 뜬다.
+
+#### 🌟 주요 개선 사항
+1. **update 스킬 (`multi-agent-mux-update`: `scripts/update.sh`, `install_phase.sh`, `post_update.sh`, `lib_py/update.py`)**:
+   - 1단계(설치된 옛 코드): 배타 입장 잠금 아래에서 표식을 걸고, 아무것도 바꾸기 전에 거부할 것을 확인한다(running 행, cwd 가 이 작업 공간 안인 살아 있는 herdr 에이전트, 읽을 수 없는 것을 포함한 열린 잡, live 루프, 스킬이 띄우지 않은 모니터가 쥔 `.mam/monitor.lock`, 다른 업데이트). 호출한 에이전트(서버+pane)는 세지 않는다.
+   - 이 작업 공간의 모니터만(정확한 명령줄로) 멈추고(TERM, 끝나지 않으면 KILL; `MAM_UPDATE_MONITOR_STOP_S`), `.agents/`·`.mam_deploy/`·루트 파일·`.venv`·설치기가 관리하는 `.mam` 파일·레지스트리를 `.mam/update-backup/` 에 백업한 뒤, 설치 단계의 복사본을 트리 밖에서 exec 한다.
+   - 설치(bash 3.2, lib.sh 를 부르지 않음): `MAM_INSTALLER_URL` 의 설치기를 제자리로 실행한다. 실패하면 백업에서 되돌리고 되돌린 트리로 모니터를 다시 띄운다.
+   - 2단계(새 코드): `lib_py.registry_format` 으로 레지스트리를 변환하고, 원래 떠 있던 모니터만 다시 띄운다. 변환 실패는 변환기의 코드로 끝난다.
+   - 남은 백업은 상태(`backing-up` → `installing` → `installed`)에 따라 지우거나 되돌린 뒤 진행한다. 되돌리기가 실패하면 백업을 두고 멈춘다.
+2. **입장 잠금 (`lib.sh` `mam_update_admit`, `lib_py.pane_lock acquire --shared --wait-env`)**: 위 여섯 명령이 기록을 쓸 때까지 공유 잠금을 쥔다. 오래 사는 자식은 그 fd 를 물려받지 않는다. delegate submit 과 create·resume 은 대상 pane 이 속한 설치 작업 공간의 잠금도 잡는다.
+3. **제자리 설치 (`deploy/install.sh`)**: `install_state` 를 키 단위로 덮어쓴다. 새 버전에 없는 프레임워크 파일은 사용자가 고치지 않았으면 지우고, 고쳤으면 남기고 목록을 출력한다.
+4. **resume 의 모니터 (`resume_session.sh`)**: 행을 쓴 뒤 제어 루트를 workdir 로 `start_watchdog` 를 부른다(worktree 세션 포함). 실패는 경고만 한다. legacy `start_watchdog`(`MAM_DELEGATION_PY=0`)도 모니터를 자기 프로세스 그룹에서 띄운다.
+5. **attach 안내**: create 의 마지막 안내, delegate-job 의 전달 안내, stop 의 TUI 멈춤 안내, `deploy/INSTALL.md`, `install_mam.sh`.
+6. **버전 락스텝**: update 스킬이 매트릭스와 `test_version_consistency.py` 의 스킬 목록에 들어가 9개 `SKILL.md` 를 맞춘다.
+
+#### ✅ 품질 검증
+- **회귀**: `tests/test_issue72_{update,admission,attach_hints,installer,resume_monitor}.py`. base(v4.11.0)에서 78개 중 77개가 실패하고 1개는 건너뛴다(첫 전환 테스트, base 아카이브에 git 기록이 없어서).
+- **리뷰 (`--all-reviewer`, 작성자 PR 의 리뷰 전용 루프)**: 1회차 4명 모두 NOT PASS(모니터를 정확한 명령줄로 고르기, pane 작업 공간의 입장, 레지스트리 스냅샷을 행 단위로 비교, macOS 의 `-shm`). agy 의 지적은 creator 의 반론으로 철회됐다. 2·3회차 3/4 PASS, codex 가 legacy `start_watchdog` 의 프로세스 그룹과 테스트의 패턴 kill 정리를 지적했다. 수정 루프(@ec7f5c4)에서 **4/4 PASS**. 리포트는 `.agents/reports/<session>/` 에 있다.
+- **전체 스위트 (macOS, Python 3.9.6, @ec7f5c4)**: 2268 passed, 56 skipped, 실패 0 (100분). 실제 `~/.claude`·`/private/tmp/claude-<uid>`·herdr 서버 pane 목록·opencode 의 data·state·config·본 체크아웃의 `.mam` 에 이 실행이 남긴 것은 없었고, 본 체크아웃의 모니터는 그대로 떠 있었다.
+- **작성자 확인 (Linux, @253a0aa)**: 2291 passed, 20 skipped, 실패 0.
+- **알려진 비차단**: stale 표식 NOTE 의 출력 순서(다른 업데이트가 끼어들면 메시지가 둘). `MAM_STATE_JSON` 이 깨졌을 때 delegate submit 이 대상 해석을 건너뛴다(등록은 뒤의 레지스트리 접근에서 실패). 행 없는 대상에 submit 할 때마다 herdr 를 한 번 더 조회한다. 입장 경합을 실제 create 로 재현하는 테스트, 기존 `.venv` 내용의 복원 테스트, 되돌리기 뒤 DB 전체 비교 테스트는 없다.
+
+### 🚀 `v4.11.0` — attach 명령은 herdr 에 등록된 이름을 쓰고, 세션 시작·종료는 스킬로만 한다 (Issue #71) (2026-10-27)
+
+> **마이너 (MINOR Release)**: 레지스트리의 `attach_command` 가 원래 세션 이름으로 herdr 를 불러, 이름이 herdr 의 규칙(소문자 `[a-z0-9_-]`, 32자 이하)을 벗어나면 붙지 못했다. 이제 attach 명령은 한 함수가 만들고, 레지스트리 행에서 `kill_command`·`start_command` 를 지웠으며, 레지스트리에 형식 버전(`registry_format: 2`)을 더했다. `status --json` 의 키가 빠지고 stop 의 동작(행 없는 세션 닫기)이 늘어 MINOR 로 올린다. PR #73.
+
+#### ⚠️ 호환성
+- 레지스트리 행에 `kill_command`·`start_command` 가 더 이상 없다. `status --json` 에서도 `start_command` 키가 빠졌다.
+- `attach_command` 는 `herdr --session <server> agent attach <herdr 에 등록된 이름>` 이다. `default` 서버도 적는다.
+- 옛 레지스트리(형식 키 없음 = 1)는 첫 쓰기 때 2 로 바뀐다. 첫 쓰기 전까지 status 에 옛 행이 보일 수 있다.
+- 세션 시작은 create·resume, 종료는 stop 스킬로 한다. attach 만 보기 전용이라 herdr 명령을 직접 쓴다.
+
+#### 🌟 주요 개선 사항
+1. **attach 명령 하나 (`lib_py/agents/sanitize.py` `attach_command`)**: create·resume·reconcile 이 모두 이 함수를 쓴다. 값은 `shlex.quote` 로 감싼다. lib.sh 래퍼의 `herdr agent attach <원래 이름>` 도 이름을 바꿔 부르고, 대상 뒤의 옵션(`--takeover`)은 그대로 넘긴다.
+2. **행이 없는 세션의 stop (`stop_session.sh`)**:
+   - 레지스트리에 행이 없으면 herdr 세션만 닫고 레지스트리는 바꾸지 않는다. herdr 가 기록한 cwd 가 이 작업 공간 안일 때만 닫는다.
+   - 다른 작업 공간의 세션은 exit 5, 서버에 없으면 exit 1, 닫은 뒤에도 살아 있으면 exit 6 이다.
+   - 레지스트리를 읽지 못하면(YAML 깨짐, DB 손상, 테이블 없음) "행 없음" 으로 보지 않고 exit 1 로 멈춘다(`load_state_json strict`).
+   - 사용자에게 보여 주던 날 `kill-session` 안내 두 곳(create exit 43, `id_order.py`)은 stop 스킬 명령으로 바꿨다.
+3. **이름 변환 규칙 하나 (`lib.sh`)**: `_sanitize_herdr_agent_name` 정의를 하나로 합쳤고 shim 은 `declare -f` 로 같은 함수를 받는다. `has-session` 의 `lower()[:32]` 대체 경로를 지웠다. 해시 도구가 없으면 python3 로, python3 도 없으면 오류로 멈춘다(`00000000` 을 붙이지 않는다). ASCII 가 아닌 이름·`-n`·줄바꿈이 든 이름도 Python 함수와 결과가 같다.
+4. **레지스트리 형식 버전 2 (`lib_py/registry_format.py`, `lib_py/atomic_yaml.py`)**: 레지스트리를 쓰는 함수가 잠금(`BEGIN IMMEDIATE`) 안에서, 호출자의 변경 전에 모든 행을 바꾸고 YAML 도 다시 쓴다. 업데이트 뒤 부를 진입점: `PYTHONPATH=.agents/skills python3 -m lib_py.registry_format --yaml <agent-sessions.yaml>` (#72 에서 쓴다).
+5. **stall_watch**: herdr 이름을 `StallWatch` 에서 한 번만 구해 `HerdrSource` 에 넘긴다.
+
+#### ✅ 품질 검증
+- **회귀**: `tests/test_issue71_herdr_names.py`(70개). base(v4.10.1)에서 68개가 실패한다.
+- **리뷰 (`--all-reviewer`, 작성자 PR 의 리뷰 전용 루프)**: 1회차 3/4 PASS. codex 의 지적(행 없는 stop 의 `HERDR_SESSION_NAME=default` 처리)은 create 와 같은 서버 선택 규칙이라는 반론으로 철회됐다. 2회차(@5f60653) **4/4 PASS**. 리뷰어들이 macOS bash 3.2 에서 이름 변환이 Python 함수와 같은 것을 `LC_ALL=C`·UTF-8 양쪽에서 확인했다. 리포트는 `.agents/reports/<session>/` 에 있다.
+- **전체 스위트 (macOS, Python 3.9.6, @5f60653)**: 2173 passed, 56 skipped, 2 failed. 실패는 부하에 민감한 타이밍 테스트 둘(`test_issue14_delivery_ack.py::test_wrapper_idle_timeout_grace_ignores_pane_busy_token`, `test_issue30_stall_watch.py::test_s13_unreliable_agent_status_turns_idle_off_but_keeps_blocked`)이고, 단독으로 3번 모두, 두 파일 전체로도 통과했다(60 passed, 1 skipped). 실제 `~/.claude`·`/private/tmp/claude-<uid>`·herdr 서버 pane 목록·opencode 의 data·state·config 에 이 실행이 남긴 것은 없었다.
+- **작성자 확인 (Linux, Python 3.14)**: 2211 passed, 20 skipped, 실패 0.
+- **알려진 비차단**: `name` 이 없는 행은 형식 변환에서 건너뛰므로 두 필드가 남을 수 있다. delegate-job 래퍼의 위임 안내 문구(`작업이 세션 ...에 전송되었습니다`)는 아직 옛 attach 형태(`HERDR_SESSION_NAME=... herdr agent attach <원래 이름>`)를 보여 준다.
+- **병합**: merge commit 으로 병합한다. `test_issue23_24_startup_path.py` S11 이 이 브랜치의 커밋 `0fc162e` 를 기준으로 쓴다.
+
+### 🚀 `v4.10.1` — stall_watch 가 herdr 에 변환된 에이전트 이름을 쓴다 (Issue #66) (2026-10-25)
+
+> **패치 (PATCH Release)**: 세션 이름이 herdr 의 에이전트 이름 규칙(소문자 `[a-z0-9_-]`, 영문자로 시작, 32자 이하)을 벗어나면, 그 세션에 위임한 잡의 `stall_watch` 가 pane 을 찾지 못하고(`stall_watch:agent_not_found`) 멈춤 알림이 꺼졌다. 이제 herdr 를 부를 때만 `sanitize_herdr_agent_name()` 의 결과를 쓴다. 옵션·동작 계약은 바뀌지 않는다. PR #70.
+
+#### 🌟 주요 개선 사항
+1. **herdr 호출 (`lib_py/stall_watch.py`)**: `HerdrSource` 의 `agent get`·`agent read`·`agent prompt` 와 `StallWatch` 의 `watcher.wait_once` 가 변환된 이름을 쓴다. 32자를 넘는 이름(앞 23자 + `-` + sha1 8자), 대문자·`.` 이 든 이름이 해당한다. 이미 규칙에 맞는 이름은 그대로다.
+2. **원래 이름이 남는 곳**: 로그와 알림은 원래 세션 이름을 쓴다. 에이전트 종류(`resolve_agent`)도 원래 이름의 `-<agent>` 접미사로 정한다. 긴 이름은 변환되면 접미사가 해시로 바뀌기 때문이다.
+3. **mock herdr (`tests/conftest.py`)**: `strict_agent_names` 옵션을 켜면 실제 herdr 처럼 등록된(변환된) 이름에만 답하고, 다른 이름에는 `agent_not_found` 를 낸다. 기본은 꺼져 있어 기존 테스트의 동작은 같다.
+
+#### ✅ 품질 검증
+- **회귀**: `tests/test_issue66_stall_watch_sanitized_name.py`(7개). base(v4.10.0)에서 5개가 실패한다. 긴 이름·대문자 이름의 idle 재촉과 blocked 알림, 원래 이름의 로그, 접미사로 정하는 에이전트 종류, 규칙에 맞는 이름의 무변경을 확인한다.
+- **리뷰 (`--all-reviewer`, 작성자 PR 의 리뷰 전용 루프)**: 1회차(@bb496fd) **4/4 PASS**. lib.sh `_sanitize_herdr_agent_name` 과 Python 함수의 결과가 같은 것도 확인했다. 리포트는 `.agents/reports/<session>/` 에 있다.
+- **전체 스위트 (macOS, Python 3.9.6, @bb496fd)**: 2105 passed, 56 skipped, 실패 0. 실제 `~/.claude`·`/private/tmp/claude-<uid>`·herdr 서버 pane 목록·opencode 의 data·state·config 에 이 실행이 남긴 것은 없었다.
+- **작성자 확인 (Linux)**: 전체 스위트 2140 passed, 20 skipped, 1 failed. 실패는 `tests/test_issue17_item4_decisions.py` 의 정리 경합 하나이고 단독으로 10번 모두 통과했다.
+- **알려진 비차단**: lib.sh 에 `_sanitize_herdr_agent_name` 정의가 두 벌(:36, :293) 있다. 뒤의 것이 적용되고, sha 도구가 없을 때의 대처만 다르다. 이 PR 이전부터 있던 것이다.
+
+### 🚀 `v4.10.0` — 같은 폴더의 같은 종류 에이전트가 서로의 대화 ID 를 쓰지 않는다 (Issue #63) (2026-10-23)
+
+> **마이너 (MINOR Release)**: 같은 폴더에 ID 가 나중에 생기는 같은 종류 에이전트(agy·codex·hermes·opencode)가 둘 있으면, stop·purge·resume 이 `find_workspace_uuid` 의 추측으로 다른 행의 대화 ID 를 기록하거나 지우거나 이어받을 수 있었다. 이제 세 경로가 #40 의 판정을 같이 쓰고, 같은 폴더의 생성 순서를 정하는 새 대기 동작(`MAM_ID_ORDER_WAIT_S`)과 resume 의 새 거부(exit 1)가 추가되어 MINOR 로 올린다. PR #69.
+
+#### 🌟 주요 개선 사항
+1. **ID 판정 (`lib_py/agents/session_ids.py`, 새 파일)**: stop·purge·resume 이 같은 판정을 쓴다. 행의 own id 가 우선이고, 없으면 #40 의 `autopin.capture` 를 쓴다. 다른 행이 기록한 ID 는 쓰지도 지우지도 않는다. claude·grok 은 그대로다.
+2. **stop·purge**:
+   - stop 은 프로세스를 끄기 전에 ID 를 정한다. herdr 가 이미 죽은 행은 확인할 수 없으므로 ID 를 기록하지 않고 이유를 남긴다.
+   - purge 는 own id 이거나 확인을 통과한 ID 만 지우고, 레지스트리를 쓰는 시점에 다른 행이 기록했는지 다시 확인한다.
+3. **resume**:
+   - own id 가 없고 같은 폴더에 같은 종류 행이 둘 이상이면 추측하지 않고 새 대화로 띄운다.
+   - 해결한 ID 를 다른 행이 이미 기록했으면 띄우기 전에 거부한다(exit 1).
+   - 기록된 ID 가 더 이상 유효하지 않으면 새 대화로 띄우고 그 ID 를 지운다(`update_yaml_resumed.sh --drop-stale-id`).
+4. **생성 순서 (`lib_py/agents/id_order.py`, 새 파일)**:
+   - 같은 폴더에서 같은 종류 에이전트가 생성 중이거나 ID 없이 실행 중이면, 새 create·resume 은 그 ID 가 기록될 때까지 기다린다. 폴더·에이전트 단위 잠금(`fcntl`)과 "생성 중" 표시를 쓰고, 폴더는 실제 경로로 비교한다.
+   - 상한은 `MAM_ID_ORDER_WAIT_S`(기본 600 s, 0 이면 기다리지 않음)다. 넘으면 아무것도 띄우지 않고 기다린 세션 이름을 알리며 거부한다(exit 1).
+   - create·resume 이 띄운 뒤 행을 등록하기 전에 죽어 "생성 중" 표시만 남으면, 그 herdr 세션이 살아 있는 동안 계속 막는다. herdr 가 세션이 없다고 확실히 답하거나 그 시도의 행이 등록되면 푼다. 조회 실패는 "모름"으로 보고 막으며, 조회도 대기 상한 안에서만 한다(상한 0 이면 묻지 않음).
+5. **정리**: `find_workspace_uuid()` 가 ID 를 반환하고 다른 행의 ID 를 후보에서 뺀다(`exclude_ids`). 쓰이지 않게 된 `capture_conversation_id`(lib.sh)와 `CAPTURE_ID`(stop)를 지웠다.
+
+#### ✅ 품질 검증
+- **회귀**: `tests/test_issue63_same_cwd_ids.py`(27개). 완료 조건의 회귀 테스트는 base(v4.9.9)에서 실패하고 head 에서 통과한다.
+- **리뷰 (`--all-reviewer`, 작성자 PR 의 리뷰 전용 루프, 수정은 claude creator)**: codex 가 고아 "생성 중" 표시 처리에서 차단 결함을 회차마다 찾았고 ede9c62·8f64174·7cac6f6·1614af5 에서 고쳤다. 마지막 루프 1회차(@1614af5) **4/4 PASS**. 리포트는 `.agents/reports/<session>/` 에 있다.
+- **전체 스위트 (macOS, Python 3.9.6, @1614af5)**: 2097 passed, 56 skipped, 1 failed.
+  - 실패는 `tests/test_issue50_dispatch_herdr.py::test_c11_…` 하나다. 이 브랜치는 위임 코드를 건드리지 않고, 단독으로 세 번 돌리면 매번 통과했다(시간 의존).
+  - 실제 `~/.claude`·`/private/tmp/claude-<uid>`·herdr 서버 pane 목록·opencode 의 data·state·config 에 이 실행이 남긴 것은 없었다.
+- **작성자 확인 (Linux)**: 전체 스위트와 실제 agy 두 개 시험(같은 폴더 동시 create·stop·동시 resume·B purge 뒤 A 의 대화 파일 보존).
+- **알려진 비차단**:
+  - herdr 조회가 계속 실패하면 고아 표시가 남아 이후 create·resume 이 매번 상한까지 기다린다. 거부 메시지가 `herdr kill-session` 명령을 알려 준다.
+  - 등록 중에 herdr 목록이 잠깐 비어 있으면 표시가 풀릴 수 있다.
+  - `--no-onboard` 로 만든 세션은 첫 ID 가 기록될 때까지 다음 create 가 상한까지 기다린다(#68).
+  - presence lock 으로 ID 를 찾는 것과, MAM 밖에서 사람이 같은 폴더에 띄운 에이전트는 범위 밖이다.
+
+### 🚀 `v4.9.9` — completed 를 확인한 쪽이 세션 ID 를 등록하고, agy 는 다른 작업 공간의 대화를 받지 않는다 (Issue #40) (2026-10-21)
+
+> **패치 (PATCH Release)**: 세션 ID 가 생성 뒤에야 생기는 에이전트(agy·opencode·codex·hermes)는 지금까지 모니터 데몬의 reconcile 이 찾아 등록했다. 데몬이 없는 워크트리 creator 는 등록되지 않았고, agy 의 drift C 는 호스트 공용 대화 폴더의 모든 `*.db` 를 후보로 보아 다른 작업 공간의 대화 ID 를 등록할 수 있었다. 이제 잡의 completed 를 확인한 쪽이 같은 판정으로 한 번 등록하고, reconcile 도 그 판정을 쓴다.
+
+#### 🌟 주요 개선 사항
+1. **어댑터 규격**: `BaseAgentAdapter.id_lifecycle`(`pre_assigned`: claude·grok / `post_discovered`: 나머지)과 `capture_active_session_id`. 세션 시작 뒤 갱신되고, 검증을 통과하고, 다른 행이 기록하지 않은 후보가 정확히 하나일 때만 ID 를 돌려준다. 아니면 이유(`no-candidate`, `ambiguous`, `unverifiable-owner` 등)를 돌려준다.
+2. **agy**:
+   - `verify_artifact` 의 discover 모드는 `last_conversations.json` 이 다른 작업 공간에 매핑한 ID 를 거절한다. 다른 행이 기록한 ID 도 항상 제외한다.
+   - capture 는 캐시를 제안으로만 쓴다. 그 대화의 presence lock 이나 DB 를 행의 pane 프로세스(또는 그 자손)가 열고 있음을 `lsof`·`ps` 로 확인해야 등록한다. 확인할 수 없으면 등록하지 않는다.
+3. **`lib_py/agents/autopin.py`**: `handle_completed` 를 completed 를 확인한 쪽이 부른다.
+   - 위임 래퍼(direct), `create --onboard`, 루프 `wait_for_job`(복구 경로).
+   - 로컬 herdr 잡만 처리한다(remote·human 제외).
+   - (잡, dispatch token, attempt) 하나는 한 번만 처리한다(잡 단위 flock 과 잡 폴더의 마커).
+   - 등록은 `atomic_dump_yaml` 로 쓰고 `session_id_source=discovered`, `session_id_verified=true` 를 남긴다. 실패하면 이유를 행에 남기고, 잡의 결과는 바꾸지 않는다.
+   - 에이전트가 실행하는 `publish_event.py` 에는 쓰기를 넣지 않았다.
+4. **reconcile**: drift C 의 agy·hermes·opencode·codex 가 같은 capture 를 부른다. agy 의 `*.db` glob 은 없어졌다. `_pin_and_verify_resume` 은 `pin_row` 를 쓴다.
+
+#### ✅ 품질 검증
+- **회귀**: `tests/test_issue40_auto_pin.py`(27개). 이슈의 완료 조건 네 가지를 고정한다.
+  1. 다른 작업 공간의 ID 를 등록하지 않는다.
+  2. 데몬 없이(`MAM_NO_SUBSCRIBER_DAEMON=1`) 첫 completed 뒤 agy·opencode·codex·hermes 가 등록된다.
+  3. 래퍼와 루프 복구가 같은 잡을 처리해도 등록은 한 번이고, 후보가 모호하면 등록하지 않고 이유를 남긴다.
+  4. claude·grok 행과 이미 ID 가 있는 행은 바뀌지 않는다.
+
+  base(v4.9.8)에서 실패한다. `tests/test_issue64_ro_connect.py` 의 다른 작업 공간 agy 단언은 이제 거절(False)을 기대한다.
+- **리뷰 (`--all-reviewer`, `--plan`, 구현은 claude creator)**: 1회차(@feccfd5) **4/4 PASS**. 리포트는 `.agents/reports/<session>/` 에 있다.
+- **전체 스위트 (macOS, Python 3.9.6, @feccfd5)**: 2068 passed, 56 skipped, 3 failed.
+  - 실패 3개는 모두 `tests/test_issue42_skill_blocks.py` 였다. 이 변경이 옮긴 SKILL.md 블록과 `reconcile.sh` 근거 줄 번호가 목록에 남아 있었다.
+  - `tests/data/skill_code_blocks.json` 을 갱신한 뒤(@84af709) 이 파일은 37 passed, 1 skipped.
+  - 실제 `~/.claude`·`/private/tmp/claude-<uid>`·herdr 서버 pane 목록·opencode 의 data·state·config 에 이 실행이 남긴 것은 없었다.
+- **알려진 비차단**:
+  - agy 등록은 `lsof`·`ps`, 행의 pane pid, agy 가 presence lock 이나 DB 를 열고 있음에 기댄다. `lsof` 가 없는 환경에서는 agy 가 자동 등록되지 않는다(오등록보다 미등록을 택함). completed 경로는 이유를 행에 남긴다.
+  - reconcile 은 `ambiguous` 만 이유를 남기고 `unverifiable-owner`·`owner-mismatch`·`rejected` 는 조용히 건너뛴다.
+  - id 가 빈 claude 행에서 `pre-assigned` 보호가 걸리는지 확인하는 테스트는 없다.
+  - 중복 마커는 실패 결과도 기록하므로, 래퍼 시점에 `no-candidate` 였던 잡은 루프 복구에서 다시 시도하지 않는다. 다음 잡의 completed 나 reconcile 이 다시 시도한다.
+  - 다른 행이 가진 ID 는 멈춘(stopped) 행의 것이어도 제외한다.
+  - stop 의 캡처 경로 정리는 범위 밖이다.
+
 ### 🚀 `v4.9.8` — agy·codex·hermes DB 조회도 읽기 전용 (Issue #64) (2026-10-20)
 
 > **패치 (PATCH Release)**: v4.9.7 이 opencode 에 적용한 읽기 전용 열기(`_ro_connect`)를 agy·codex·hermes 의 조회에도 적용한다. macOS 의 시스템 SQLite 는 쓰기 가능으로 열었다 닫기만 해도 `-wal`·`-shm` 을 남긴다(persistent WAL). 그래서 MAM 의 조회가 다른 작업 공간의 agy 대화 DB 옆에 사이드카를 만들 수 있었다. Linux 는 닫을 때 지우므로 Linux 확인은 이슈에서 따로 한다.

deploy/INSTALL.md

@@ -60,7 +60,7 @@ $ bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh \
 ### 2) 세션 접속 (Attach)
 백그라운드에서 구동된 에이전트 TUI 화면에 들어갑니다.
 ```bash
-$ herdr session attach my-project-dev-claude
+$ herdr --session multi-agent-mux agent attach my-project-dev-claude
 ```
 *   **화면 탈출**: 대화 중 세션을 유지한 채 터미널로 돌아오려면 `Ctrl + B`를 누른 뒤 `D` 키를 차례로 입력합니다.
 

deploy/README.md

@@ -9,7 +9,7 @@ This directory contains packaging templates and installation scripts to deploy t
 *   **`install.sh`**: A self-contained, idempotent remote shell installer (via curl) that checks system requirements (`herdr`, `python3`), sets up a local python virtual environment (`.venv`), and performs 3-way refresh with key-level registry merge (Rev.2).
 *   **`install_mam.sh`**: A local-clone installer that copies rules/skills (`.agents/`), `AGENTS.md`, manifests, and asset hashes into target projects.
 *   **`lib_ownership.sh`**: Single source of truth for framework-owned files and key-level registry files.
-*   **`update.sh`**: In-place updater script installed into target `.mam_deploy/update.sh`.
+*   **Updates**: installed workspaces update with the `multi-agent-mux-update` skill (`bash .agents/skills/multi-agent-mux-update/scripts/update.sh`).
 *   **`remove.sh`**: Clean uninstaller script installed into target `.mam_deploy/remove.sh`.
 *   **`generate-env.sh`**: Environment configuration bootstrap helper.
 *   **`INSTALL.md`**: Detailed installation and quick-start user manual.
@@ -40,7 +40,7 @@ bash deploy/install_mam.sh --target /path/to/your/project
 Refer to **`INSTALL.md`** inside this directory for the full instructions and workflows.
 
 > [!NOTE]
-> `install_mam.sh` automatically deploys `.mam_deploy/update.sh` and `.mam_deploy/remove.sh` into target workspaces, recording install manifests and asset hashes to enable clean updates and uninstalls.
+> `install_mam.sh` automatically deploys `.mam_deploy/remove.sh` into target workspaces, recording install manifests and asset hashes to enable clean updates and uninstalls.
 
 ### 3. Custom Fork / Private Mirror Installations
 If you run a private mirror or fork, you can override the source URLs during installation using environment variables:
@@ -53,7 +53,7 @@ curl -fsSL https://my-mirror.example.com/.../install.sh \
     bash
 
 # Updating an existing workspace against a mirror
-MAM_INSTALLER_URL=https://my-mirror.example.com/.../install.sh bash deploy/update.sh
+MAM_INSTALLER_URL=https://my-mirror.example.com/.../install.sh bash .agents/skills/multi-agent-mux-update/scripts/update.sh
 ```
 
 ### 4. Registering as a Workspace Plugin

deploy/gitea-ci.yml

@@ -41,7 +41,7 @@ jobs:
           shellcheck deploy/install.sh
           shellcheck deploy/install_mam.sh
           shellcheck deploy/generate-env.sh
-          shellcheck deploy/update.sh
+          shellcheck .agents/skills/multi-agent-mux-update/scripts/*.sh
           shellcheck deploy/remove.sh
           echo "✅ ShellCheck completed successfully."
 

deploy/install.sh

@@ -125,7 +125,9 @@ if [ "$REFRESH" -eq 1 ] || [ "${MAM_SKIP_VENV:-0}" -eq 1 ] || ! check_assets_pre
   FETCH_METHOD="archive"
   if [ -d "$REPO_URL" ]; then
     echo "🌐 Copying local working tree into a staging area..."
-    cp -R "$REPO_URL/." "$STAGE_DIR/"
+    # Everything but .mam/: runtime state is never staged, and it may hold the
+    # update skill's rollback copy (.mam/update-backup/, Issue #72).
+    find "$REPO_URL/." -mindepth 1 -maxdepth 1 ! -name .mam -exec cp -R {} "$STAGE_DIR/" \;
     FETCH_METHOD="local"
   elif command -v git &>/dev/null; then
     echo "🌐 Cloning repository (shallow) into a staging area..."
@@ -157,9 +159,16 @@ if [ "$REFRESH" -eq 1 ] || [ "${MAM_SKIP_VENV:-0}" -eq 1 ] || ! check_assets_pre
   MANIFEST_FILE=".mam/install_manifest.txt"
   touch "$MANIFEST_FILE"
 
-  # Migrate legacy root layout for remove.sh and update.sh into .mam_deploy/ if owned
+  # Drop every line naming this path from the manifest
+  manifest_drop() {
+    grep -Fvx -- "$1" "$MANIFEST_FILE" > "$MANIFEST_FILE.tmp" || true
+    mv -f "$MANIFEST_FILE.tmp" "$MANIFEST_FILE"
+  }
+
+  # Migrate legacy root layout for remove.sh into .mam_deploy/ if owned
   mkdir -p .mam_deploy
-  for legacy_script in remove.sh update.sh; do
+  # shellcheck disable=SC2043  # one legacy script left (update.sh went with Issue #72)
+  for legacy_script in remove.sh; do
     if [ -f "$legacy_script" ] && grep -Fqx "$legacy_script" "$MANIFEST_FILE" 2>/dev/null; then
       mv -f "$legacy_script" ".mam_deploy/$legacy_script"
       python3 -c '
@@ -179,6 +188,13 @@ with open(path, "w") as f:
     fi
   done
 
+  # update.sh is no longer shipped (Issue #72; the multi-agent-mux-update skill
+  # updates). A legacy root update.sh goes only if the manifest says we put it there.
+  if [ -f update.sh ] && grep -Fqx update.sh "$MANIFEST_FILE" 2>/dev/null; then
+    rm -f update.sh
+    manifest_drop update.sh
+  fi
+
   # Safe refresh & fingerprint checking logic
   TS=$(date -u +%Y%m%dT%H%M%SZ)
   FRAMEWORK_LEDGER=".mam/.framework_ledger.tmp"
@@ -374,7 +390,7 @@ MERGEREG
     fi
   done
 
-  # Install remove.sh and update.sh into .mam_deploy/
+  # Install remove.sh into .mam_deploy/
   mkdir -p .mam_deploy
   if [ -f "$STAGE_DIR/deploy/remove.sh" ]; then
     cp "$STAGE_DIR/deploy/remove.sh" .mam_deploy/remove.sh
@@ -384,13 +400,9 @@ MERGEREG
     fi
   fi
 
-  if [ -f "$STAGE_DIR/deploy/update.sh" ]; then
+  # An older install's updater is not shipped any more (Issue #72)
-    cp "$STAGE_DIR/deploy/update.sh" .mam_deploy/update.sh
+  rm -f .mam_deploy/update.sh
-    chmod 0755 .mam_deploy/update.sh
+  manifest_drop .mam_deploy/update.sh
-    if ! grep -Fqx ".mam_deploy/update.sh" "$MANIFEST_FILE" 2>/dev/null; then
-      echo ".mam_deploy/update.sh" >> "$MANIFEST_FILE"
-    fi
-  fi
 
   if [ -f "$STAGE_DIR/.mam.env.example" ] && [ ! -e ".mam.env.example" ]; then
     cp "$STAGE_DIR/.mam.env.example" .
@@ -407,6 +419,34 @@ MERGEREG
     fi
   fi
 
+  # Framework-owned files the previous install recorded (manifest and
+  # asset_hashes.txt) that this version no longer ships (Issue #72). Unmodified
+  # ones are deleted. Modified ones are kept and become the user's file: they
+  # leave the manifest, so remove.sh leaves them alone, and asset_hashes.txt
+  # (rebuilt below from the shipped files only).
+  if [ -f .mam/asset_hashes.txt ]; then
+    SHIPPED_LIST=".mam/.shipped_paths.tmp"
+    cut -f2 "$FRAMEWORK_LEDGER" > "$SHIPPED_LIST"
+    while read -r _old_sha _old_path; do
+      [ -n "${_old_path:-}" ] || continue
+      is_framework_owned "$_old_path" || continue
+      grep -Fqx -- "$_old_path" "$MANIFEST_FILE" || continue
+      if grep -Fqx -- "$_old_path" "$SHIPPED_LIST"; then continue; fi
+      if [ -f "$_old_path" ] && [ "$(python3 -c 'import hashlib, sys; print(hashlib.sha256(open(sys.argv[1], "rb").read()).hexdigest())' "$_old_path")" != "$_old_sha" ]; then
+        echo "ℹ️  Local modification detected (no longer shipped, kept as yours): $_old_path" >&2
+      else
+        rm -f "$_old_path"
+        _old_dir="$(dirname "$_old_path")"
+        while [ "$_old_dir" != ".agents" ] && rmdir "$_old_dir" 2>/dev/null; do
+          _old_dir="$(dirname "$_old_dir")"
+        done
+      fi
+      rm -f ".mam/base/$_old_path"
+      manifest_drop "$_old_path"
+    done < .mam/asset_hashes.txt
+    rm -f "$SHIPPED_LIST"
+  fi
+
   # Re-build asset_hashes.txt from the UPSTREAM copy of every framework-owned file
   python3 - .mam/asset_hashes.txt "$FRAMEWORK_LEDGER" <<'HASHDB'
 import os, hashlib, sys
@@ -590,15 +630,25 @@ with open(gi_path, "w") as f:
 PY
 
 if [ "${MAM_SKIP_GITIGNORE:-0}" -eq 0 ]; then
+  # Set the key: overwrite it in place, one line per key, other keys kept
   python3 -c '
 import os
+os.makedirs(".mam", exist_ok=True)
+lines = []
 if os.path.exists(".mam/install_state"):
-    with open(".mam/install_state", "a") as f:
+    with open(".mam/install_state") as f:
-        f.write("gitignore_created=1\n")
+        lines = f.read().splitlines()
-else:
+out, done = [], False
-    os.makedirs(".mam", exist_ok=True)
+for line in lines:
-    with open(".mam/install_state", "w") as f:
+    if line.startswith("gitignore_created="):
-        f.write("gitignore_created=1\n")
+        if done:
+            continue
+        line, done = "gitignore_created=1", True
+    out.append(line)
+if not done:
+    out.append("gitignore_created=1")
+with open(".mam/install_state", "w") as f:
+    f.write("\n".join(out) + "\n")
 '
 fi
 
@@ -617,6 +667,6 @@ cat <<EOF
      $ bash .agents/skills/multi-agent-mux-status/scripts/status.sh
 
   3. Update installed skills in the future:
-     $ bash .mam_deploy/update.sh
+     $ bash .agents/skills/multi-agent-mux-update/scripts/update.sh
 --------------------------------------------------------------------------------
 EOF

deploy/install_mam.sh

@@ -132,16 +132,12 @@ if [ -f "$SRC_DIR/.mam.env.example" ]; then
   log_ok "Copied .mam.env.example configuration template"
 fi
 
-# Deploy remove.sh and update.sh into .mam_deploy/ (R-3)
+# Deploy remove.sh into .mam_deploy/ (R-3)
 mkdir -p "$TARGET_DIR/.mam_deploy"
 if [ -f "$SRC_DIR/deploy/remove.sh" ]; then
   cp "$SRC_DIR/deploy/remove.sh" "$TARGET_DIR/.mam_deploy/remove.sh"
   chmod 0755 "$TARGET_DIR/.mam_deploy/remove.sh"
 fi
-if [ -f "$SRC_DIR/deploy/update.sh" ]; then
-  cp "$SRC_DIR/deploy/update.sh" "$TARGET_DIR/.mam_deploy/update.sh"
-  chmod 0755 "$TARGET_DIR/.mam_deploy/update.sh"
-fi
 
 if [ -f "$SRC_DIR/deploy/generate-env.sh" ]; then
   mkdir -p "$TARGET_DIR/scripts"
@@ -161,7 +157,7 @@ mkdir -p "$TARGET_DIR/.mam"
 MANIFEST_FILE="$TARGET_DIR/.mam/install_manifest.txt"
 : > "$MANIFEST_FILE"
 ( cd "$TARGET_DIR" && find .agents -type f -print ) >> "$MANIFEST_FILE"
-for extra in ".mam.env.example" ".mam_deploy/remove.sh" ".mam_deploy/update.sh" \
+for extra in ".mam.env.example" ".mam_deploy/remove.sh" \
              "scripts/generate-env.sh"; do
   if [ -e "$TARGET_DIR/$extra" ]; then
     echo "$extra" >> "$MANIFEST_FILE"
@@ -327,7 +323,7 @@ cat <<EOF
          --herdr-server multi-agent-mux
 
   2. Attach to the running session:
-     $ HERDR_SERVER_NAME=multi-agent-mux herdr agent attach <session_name>
+     $ herdr --session multi-agent-mux agent attach <herdr name>
 
   3. Gracefully stop the session:
      $ bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh \\

deploy/remove.sh

@@ -92,6 +92,7 @@ else
     ".agents/skills/multi-agent-mux-resume"
     ".agents/skills/multi-agent-mux-status"
     ".agents/skills/multi-agent-mux-stop"
+    ".agents/skills/multi-agent-mux-update"
     ".agents/hooks"
     ".agents/hooks.json"
     ".agents/MULTI_AGENT_RULES.md"

deploy/update.sh

@@ -1,269 +0,0 @@
-#!/usr/bin/env bash
-# ==============================================================================
-# update.sh — Multi-Agent Mux (MAM) Orchestration Updater
-# ==============================================================================
-# Safely updates MAM skills, virtual environment, and docs to the latest version.
-# Preserves user configuration (.env) and local metadata/jobs database (.mam).
-# ==============================================================================
-set -euo pipefail
-
-TARGET_DIR=""
-FORCE=0
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-
-# Parse arguments
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    -y|--yes|--force)
-      FORCE=1
-      shift
-      ;;
-    *)
-      TARGET_DIR="$1"
-      shift
-      ;;
-  esac
-done
-
-if [ -z "$TARGET_DIR" ]; then
-  if [ "$(basename "$SCRIPT_DIR")" = ".mam_deploy" ]; then
-    TARGET_DIR="$(dirname "$SCRIPT_DIR")"
-  else
-    TARGET_DIR="$(pwd)"
-  fi
-else
-  if [ "$(basename "$TARGET_DIR")" = ".mam_deploy" ]; then
-    TARGET_DIR="$(dirname "$TARGET_DIR")"
-  fi
-  if [ ! -d "$TARGET_DIR" ]; then
-    echo "❌ Error: Target directory '$TARGET_DIR' does not exist." >&2
-    exit 1
-  fi
-  TARGET_DIR="$(cd "$TARGET_DIR" && pwd)"
-fi
-
-echo "===================================================================="
-echo "⚡ Starting Multi-Agent Mux (MAM) Update"
-echo "📂 Target Workspace: $TARGET_DIR"
-echo "===================================================================="
-
-cd "$TARGET_DIR"
-
-# 1. Verification of existing install (B-2: dual resolution)
-REMOVER=""
-for cand in ".mam_deploy/remove.sh" "remove.sh"; do
-  if [ -f "$cand" ]; then
-    REMOVER="$cand"
-    break
-  fi
-done
-
-if [ -z "$REMOVER" ]; then
-  echo "❌ Error: No MAM installation (remove.sh) found in '$TARGET_DIR'." >&2
-  echo "   Please run install.sh first to set up the workspace." >&2
-  exit 1
-fi
-
-# Request confirmation if not forced
-if [ $FORCE -eq 0 ]; then
-  echo "⚠️  WARNING: This will update MAM orchestration skills, virtual environment, "
-  echo "   and docs to the latest version."
-  echo "   (Your configuration, job history, and custom skills will be preserved)."
-  if [ ! -t 0 ]; then
-    echo "❌ Error: Non-interactive terminal detected. Please run with -y/--yes/--force." >&2
-    exit 1
-  fi
-  if ! read -p "❓ Proceed with update? [y/N]: " -r response; then
-    response="n"
-  fi
-  if [[ ! "$response" =~ ^[yY](es)?$ ]]; then
-    echo "❌ Update cancelled by user."
-    exit 0
-  fi
-fi
-
-# 1.5 Pre-capture legacy ownership before remove.sh deletes the manifest (M-4)
-MAM_LEGACY_ENV_OWNED=0
-if [ -f ".mam/install_manifest.txt" ] && grep -Fqx ".env" ".mam/install_manifest.txt" 2>/dev/null; then
-  MAM_LEGACY_ENV_OWNED=1
-fi
-export MAM_LEGACY_ENV_OWNED
-
-# 2. Stage backups of user configurations and metadata to prevent deletion
-echo "💾 Backing up configuration and database..."
-HAS_ENV=0
-ENV_BACKUP_SRC=""
-ENV_BACKUP_TMP=""
-
-if [ -f ".mam.env" ]; then
-  HAS_ENV=1
-  ENV_BACKUP_SRC=".mam.env"
-  ENV_BACKUP_TMP=".mam.env.update-tmp"
-  mv ".mam.env" "$ENV_BACKUP_TMP"
-elif [ -f ".env" ]; then
-  HAS_ENV=1
-  ENV_BACKUP_SRC=".env"
-  ENV_BACKUP_TMP=".env.update-tmp"
-  mv ".env" "$ENV_BACKUP_TMP"
-fi
-
-HAS_MAM=0
-if [ -d ".mam" ]; then
-  HAS_MAM=1
-  # Copy database and jobs to temporary backup outside of .mam.
-  # We do NOT move the .mam folder away so that remove.sh can still read .mam/install_manifest.txt!
-  mkdir -p .mam.update-tmp
-  # Copy SQLite databases and session files
-  for db in .mam/agent-sessions.*; do
-    if [ -f "$db" ]; then
-      cp -f "$db" .mam.update-tmp/
-    fi
-  done
-  # Copy jobs history
-  if [ -d ".mam/jobs" ] && [ "$(ls -A .mam/jobs 2>/dev/null)" ]; then
-    mkdir -p .mam.update-tmp/jobs
-    cp -rf .mam/jobs/* .mam.update-tmp/jobs/
-  fi
-  # Copy delegate logs
-  if [ -d ".mam/delegate_job_logs" ] && [ "$(ls -A .mam/delegate_job_logs 2>/dev/null)" ]; then
-    mkdir -p .mam.update-tmp/delegate_job_logs
-    cp -rf .mam/delegate_job_logs/* .mam.update-tmp/delegate_job_logs/
-  fi
-  # Copy manifest so we have a backup
-  if [ -f ".mam/install_manifest.txt" ]; then
-    cp -f .mam/install_manifest.txt .mam.update-tmp/
-  fi
-  # C12: Copy MAM state files across update cycle
-  for st in install_state asset_hashes.txt version.txt; do
-    if [ -f ".mam/$st" ]; then
-      cp -f ".mam/$st" .mam.update-tmp/
-    fi
-  done
-  if [ -d ".mam/skill-backups" ]; then
-    mkdir -p .mam.update-tmp/skill-backups
-    cp -rf .mam/skill-backups/* .mam.update-tmp/skill-backups/ 2>/dev/null || true
-  fi
-fi
-
-# Define trap to restore backup files on failure
-restore_on_failure() {
-  echo "❌ Update failed. Reverting configuration and database to previous state..."
-  if [ $HAS_ENV -eq 1 ] && [ -n "$ENV_BACKUP_TMP" ] && [ -f "$ENV_BACKUP_TMP" ]; then
-    mv -f "$ENV_BACKUP_TMP" "$ENV_BACKUP_SRC" 2>/dev/null || true
-  fi
-  if [ $HAS_MAM -eq 1 ] && [ -d ".mam.update-tmp" ]; then
-    # Revert to old database/jobs backup by restoring .mam directory
-    rm -rf .mam 2>/dev/null || true
-    mkdir -p .mam
-    cp -f .mam.update-tmp/agent-sessions.* .mam/ 2>/dev/null || true
-    if [ -d ".mam.update-tmp/jobs" ]; then
-      cp -rf .mam.update-tmp/jobs .mam/ 2>/dev/null || true
-    fi
-    if [ -d ".mam.update-tmp/delegate_job_logs" ]; then
-      cp -rf .mam.update-tmp/delegate_job_logs .mam/ 2>/dev/null || true
-    fi
-    if [ -f ".mam.update-tmp/install_manifest.txt" ]; then
-      cp -f .mam.update-tmp/install_manifest.txt .mam/ 2>/dev/null || true
-    fi
-    for st in install_state asset_hashes.txt version.txt; do
-      if [ -f ".mam.update-tmp/$st" ]; then
-        cp -f ".mam.update-tmp/$st" .mam/ 2>/dev/null || true
-      fi
-    done
-    if [ -d ".mam.update-tmp/skill-backups" ]; then
-      mkdir -p .mam/skill-backups
-      cp -rf .mam.update-tmp/skill-backups/* .mam/skill-backups/ 2>/dev/null || true
-    fi
-    rm -rf .mam.update-tmp 2>/dev/null || true
-  fi
-}
-trap restore_on_failure EXIT
-
-# 3. Perform uninstallation of existing files
-echo "🗑️  Removing existing installation..."
-# remove.sh will run in manifest mode because .mam/install_manifest.txt is still present.
-# It will delete .agents/, documents, scripts, .venv, and .mam folder.
-bash "$REMOVER" --force "$TARGET_DIR"
-
-# 4. Fetch and run the latest installer from Gitea
-echo "📥 Fetching and running the latest installer..."
-# Note: MAM_*_URL environment variables are automatically inherited by the child installer bash process.
-INSTALLER_URL="${MAM_INSTALLER_URL:-https://git.godopu.com/tmpl/multi-agent-mux/raw/branch/main/deploy/install.sh}"
-if command -v curl &>/dev/null; then
-  curl -fsSL "$INSTALLER_URL" | bash -s -- "$TARGET_DIR"
-elif command -v wget &>/dev/null; then
-  wget -qO- "$INSTALLER_URL" | bash -s -- "$TARGET_DIR"
-else
-  echo "❌ Error: Neither 'curl' nor 'wget' is available to fetch the installer." >&2
-  exit 1
-fi
-
-# Disable failure trap since installation succeeded
-trap - EXIT
-
-# 5. Restore backups of configuration and database
-echo "🔄 Restoring configuration and database..."
-if [ $HAS_ENV -eq 1 ] && [ -n "$ENV_BACKUP_TMP" ] && [ -f "$ENV_BACKUP_TMP" ]; then
-  if [ "$MAM_LEGACY_ENV_OWNED" = "1" ] && [ "$ENV_BACKUP_SRC" = ".env" ] && [ ! -f ".mam.env" ]; then
-    mv -f "$ENV_BACKUP_TMP" ".mam.env"
-    chmod 0600 ".mam.env" 2>/dev/null || true
-  else
-    mv -f "$ENV_BACKUP_TMP" "$ENV_BACKUP_SRC"
-  fi
-fi
-
-if [ $HAS_MAM -eq 1 ]; then
-  if [ -d ".mam.update-tmp" ]; then
-    # The installer created a new .mam directory with a new manifest.
-    # We want to merge the old .mam database/jobs back while keeping the new manifest.
-    for db in .mam.update-tmp/agent-sessions.*; do
-      if [ -f "$db" ]; then
-        cp -f "$db" .mam/
-      fi
-    done
-    if [ -d ".mam.update-tmp/jobs" ] && [ "$(ls -A .mam.update-tmp/jobs 2>/dev/null)" ]; then
-      mkdir -p .mam/jobs
-      cp -rf .mam.update-tmp/jobs/* .mam/jobs/
-    fi
-    if [ -d ".mam.update-tmp/delegate_job_logs" ] && [ "$(ls -A .mam.update-tmp/delegate_job_logs 2>/dev/null)" ]; then
-      mkdir -p .mam/delegate_job_logs
-      cp -rf .mam.update-tmp/delegate_job_logs/* .mam/delegate_job_logs/
-    fi
-    # Issue #8: asset_hashes.txt and version.txt describe the tree the
-    # installer just wrote, so the pre-update copies must NOT come back here -
-    # restoring them made version.txt name the previous commit and remove.sh
-    # treat every updated file as locally modified (spurious backups). Only
-    # install_state carries history worth keeping: merge in any key the fresh
-    # install did not write (e.g. gitignore_created from the original install).
-    # The failure path (restore_on_failure) still puts all three back verbatim.
-    if [ -f ".mam.update-tmp/install_state" ]; then
-      touch .mam/install_state
-      # A fresh install_state without a final newline would glue the first
-      # merged key onto its last line.
-      if [ -s .mam/install_state ] && [ -n "$(tail -c1 .mam/install_state)" ]; then
-        printf '\n' >> .mam/install_state
-      fi
-      while IFS= read -r line || [ -n "$line" ]; do
-        case "$line" in
-          *=*) ;;
-          *) continue ;;   # not a key=value line
-        esac
-        key="${line%%=*}"
-        [ -n "$key" ] || continue
-        # exact key match, no regex interpretation of the key
-        if ! awk -F= -v k="$key" '$1 == k { found = 1 } END { exit !found }' .mam/install_state; then
-          printf '%s\n' "$line" >> .mam/install_state
-        fi
-      done < .mam.update-tmp/install_state
-    fi
-    if [ -d ".mam.update-tmp/skill-backups" ]; then
-      mkdir -p .mam/skill-backups
-      cp -rf .mam.update-tmp/skill-backups/* .mam/skill-backups/ 2>/dev/null || true
-    fi
-    rm -rf ".mam.update-tmp"
-  fi
-fi
-
-echo "===================================================================="
-echo "🎉 Update complete!"
-echo "===================================================================="

docs/NEW_AGENT_INTEGRATION_GUIDE.md

@@ -34,6 +34,7 @@ MAM은 에이전트별 동작 특성(TUI 프롬프트 패턴, 세션 복원 인
 │   │   • input_prompt, input_placeholder, input_rule_pattern                                                                          │   │
 │   │   • artifact_path(), verify_artifact(), purge_artifacts()                                                                        │   │
 │   │   • spawn_spec(), resume_spec(), auth_ok(), discover()                                                                           │   │
+│   │   • id_lifecycle, capture_active_session_id()  (Issue #40)                                                                       │   │
 │   └────────────────────────────────────────────────────────────────┬─────────────────────────────────────────────────────────────────┘   │
 │                                                                    │                                                                     │
 │               ┌────────────────────┬───────────────────────────────┬───────────────────────────────┬─────────────────────┐               │
@@ -70,7 +71,7 @@ MAM은 에이전트별 동작 특성(TUI 프롬프트 패턴, 세션 복원 인
 
 import os
 from typing import Any, List, Optional
-from ..base import BaseAgentAdapter, DiscoveryContext
+from ..base import BaseAgentAdapter, DiscoveryContext, PRE_ASSIGNED
 
 
 class GrokAgentAdapter(BaseAgentAdapter):
@@ -169,8 +170,19 @@ class GrokAgentAdapter(BaseAgentAdapter):
     def discover(self, ctx: DiscoveryContext) -> List[str]:
         """디스크의 세션 저장소에서 워크스페이스와 일치하는 세션 UUID 목록 탐색"""
         return []
+
+    # =========================================================================
+    # 세션 ID 라이프사이클 (Issue #40)
+    # =========================================================================
+    @property
+    def id_lifecycle(self) -> str:
+        """PRE_ASSIGNED: 기동 시 --session-id 로 ID 를 넘긴다 (claude, grok).
+        POST_DISCOVERED(기본값): 첫 턴 뒤 디스크에 생긴 ID 를 찾는다 (agy, opencode, codex, hermes)."""
+        return PRE_ASSIGNED
 ```
 
+**세션 ID 자동 확정 (Issue #40)**: `POST_DISCOVERED` 어댑터는 `capture_active_session_id(ctx)` 를 제공합니다. 기본 구현은 `discover()` 후보 중 `verify_session_uuid` 를 통과하고 다른 행이 기록하지 않은 것이 **정확히 하나**일 때만 `capture_result('captured', session_id=...)` 를 돌려주고, 아니면 `no-candidate` / `ambiguous` 등 이유를 돌려줍니다(읽기 전용). 후보 출처가 하나의 값만 주는 경우(agy 의 cwd 캐시처럼)에는 이 유일성이 아무것도 증명하지 못하므로, 그 어댑터는 이 메서드를 재정의해 소유를 따로 증명해야 합니다(agy: presence lock 을 쥔 프로세스가 그 행의 pane 프로세스 또는 자손). 실제 기록은 `completed` 를 검증한 수신 측(`lib_py.agents.autopin`: 위임 래퍼, `create --onboard`, 루프의 잡 대기)과 reconcile drift C 가 같은 판정으로 하며, 어댑터는 YAML/SQLite 에 쓰지 않습니다.
+
 ---
 
 ### Step 2: 어댑터 레지스트리 등록 (`.agents/skills/lib_py/agents/registry.py`)

tests/conftest.py

@@ -470,6 +470,9 @@ def _sanitize_agent_name(name):
 def _match_agent(k, target):
     if not k or not target:
         return False
+    # Issue #66: like the real herdr, answer only the registered (sanitized) name.
+    if state.get("strict_agent_names"):
+        return k == target
     return k == target or _sanitize_agent_name(k) == target or _sanitize_agent_name(target) == k or _sanitize_agent_name(k) == _sanitize_agent_name(target)
 
 args = sys.argv[1:]
@@ -1052,6 +1055,10 @@ elif cmd1 == "agent":
             }))
             sys.exit(0)
         else:
+            if state.get("strict_agent_names"):
+                sys.stderr.write(json.dumps({"error": {"code": "agent_not_found",
+                                                       "message": "agent " + name + " not found"}}) + "\\n")
+                sys.exit(1)
             sys.stderr.write("Agent " + name + " not found\\n")
             sys.exit(1)
     elif cmd2 == "wait":
@@ -1143,6 +1150,10 @@ elif cmd1 == "agent":
             print(buffer_content)
             sys.exit(0)
         else:
+            if state.get("strict_agent_names"):
+                sys.stderr.write(json.dumps({"error": {"code": "agent_not_found",
+                                                       "message": "agent " + name + " not found"}}) + "\\n")
+                sys.exit(1)
             sys.stderr.write("Agent " + name + " not found\\n")
             sys.exit(1)
     elif cmd2 == "prompt":

tests/data/skill_code_blocks.json

@@ -11,7 +11,7 @@
    "kind": "example",
    "evidence": [
     "multi-agent-mux-create/scripts/create_session.sh:99",
-    "multi-agent-mux-create/scripts/create_session.sh:356"
+    "multi-agent-mux-create/scripts/create_session.sh:360"
    ],
    "mismatch": null,
    "note": "HERDR_SESSION_NAME environment example"
@@ -61,9 +61,9 @@
   {
    "skill": "multi-agent-mux-create",
    "start": 134,
-   "end": 152,
+   "end": 150,
    "lang": "yaml",
-   "sha": "2dd608d04ae0",
+   "sha": "efba73c1d7f7",
    "class": "c",
    "kind": "example",
    "evidence": [
@@ -74,8 +74,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 158,
+   "start": 156,
-   "end": 160,
+   "end": 158,
    "lang": "bash",
    "sha": "613003708f19",
    "class": "c",
@@ -88,8 +88,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 204,
+   "start": 202,
-   "end": 208,
+   "end": 206,
    "lang": "bash",
    "sha": "38836d31bf38",
    "class": "c",
@@ -103,8 +103,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 230,
+   "start": 229,
-   "end": 252,
+   "end": 251,
    "lang": "bash",
    "sha": "d90cfd2555fd",
    "class": "b",
@@ -122,7 +122,7 @@
    "class": "c",
    "kind": "invocation",
    "evidence": [
-    "multi-agent-mux-delegate-job/multi-agent-mux-delegate-job:1046-1057"
+    "multi-agent-mux-delegate-job/multi-agent-mux-delegate-job:1051-1062"
    ],
    "mismatch": null,
    "note": "CLI reference; subcommands submit/status/list/verify/wait/logs match main()"
@@ -231,7 +231,7 @@
    "class": "c",
    "kind": "example",
    "evidence": [
-    "multi-agent-mux-monitor/scripts/reconcile.sh:601"
+    "multi-agent-mux-monitor/scripts/reconcile.sh:593"
    ],
    "mismatch": null,
    "note": "drift A example"
@@ -245,7 +245,7 @@
    "class": "c",
    "kind": "example",
    "evidence": [
-    "multi-agent-mux-monitor/scripts/reconcile.sh:708"
+    "multi-agent-mux-monitor/scripts/reconcile.sh:705"
    ],
    "mismatch": null,
    "note": "drift B example"
@@ -259,15 +259,15 @@
    "class": "c",
    "kind": "example",
    "evidence": [
-    "multi-agent-mux-monitor/scripts/reconcile.sh:735"
+    "multi-agent-mux-monitor/scripts/reconcile.sh:732"
    ],
    "mismatch": null,
    "note": "drift C example (indented fence)"
   },
   {
    "skill": "multi-agent-mux-monitor",
-   "start": 182,
+   "start": 184,
-   "end": 210,
+   "end": 212,
    "lang": "markdown",
    "sha": "3f5d82c08fd9",
    "class": "b",
@@ -282,8 +282,8 @@
   },
   {
    "skill": "multi-agent-mux-monitor",
-   "start": 229,
+   "start": 231,
-   "end": 233,
+   "end": 235,
    "lang": "bash",
    "sha": "b3588563316e",
    "class": "c",
@@ -385,7 +385,7 @@
    "class": "c",
    "kind": "example",
    "evidence": [
-    "multi-agent-mux-status/scripts/status.sh:411"
+    "multi-agent-mux-status/scripts/status.sh:410"
    ],
    "mismatch": null,
    "note": "table output example"
@@ -393,15 +393,15 @@
   {
    "skill": "multi-agent-mux-status",
    "start": 74,
-   "end": 106,
+   "end": 105,
    "lang": "json",
-   "sha": "cfea3a10dc8d",
+   "sha": "8e55751f5e8d",
    "class": "c",
    "kind": "example",
    "evidence": [
     "multi-agent-mux-status/scripts/status.sh:31-36",
-    "multi-agent-mux-status/scripts/status.sh:209-232",
+    "multi-agent-mux-status/scripts/status.sh:209-231",
-    "multi-agent-mux-monitor/scripts/reconcile.sh:1084"
+    "multi-agent-mux-monitor/scripts/reconcile.sh:813"
    ],
    "mismatch": [
     "S1 (fixed): the example used rows/yaml_entries/unregistered; the real keys are reconcile.sh's drift object plus sessions_detail"
@@ -410,14 +410,14 @@
   },
   {
    "skill": "multi-agent-mux-stop",
-   "start": 42,
+   "start": 41,
-   "end": 55,
+   "end": 54,
    "lang": "bash",
    "sha": "301c347ff881",
    "class": "c",
    "kind": "invocation",
    "evidence": [
-    "multi-agent-mux-stop/scripts/stop_session.sh:1-33"
+    "multi-agent-mux-stop/scripts/stop_session.sh:1-36"
    ],
    "mismatch": [
     "T2 (fixed): the --purge-conversation example lacked --yes and would exit 3"
@@ -426,22 +426,22 @@
   },
   {
    "skill": "multi-agent-mux-stop",
-   "start": 81,
+   "start": 82,
-   "end": 85,
+   "end": 86,
    "lang": "-",
    "sha": "a973676cb2d1",
    "class": "c",
    "kind": "diagram",
    "evidence": [
-    "multi-agent-mux-stop/scripts/stop_session.sh:184-198"
+    "multi-agent-mux-stop/scripts/stop_session.sh:250-264"
    ],
    "mismatch": null,
    "note": "state machine"
   },
   {
    "skill": "multi-agent-mux-stop",
-   "start": 102,
+   "start": 103,
-   "end": 104,
+   "end": 105,
    "lang": "bash",
    "sha": "4189d73d6896",
    "class": "c",
@@ -454,8 +454,8 @@
   },
   {
    "skill": "multi-agent-mux-stop",
-   "start": 127,
+   "start": 128,
-   "end": 145,
+   "end": 146,
    "lang": "bash",
    "sha": "bcaa2a03484e",
    "class": "b",
@@ -463,6 +463,20 @@
    "evidence": [],
    "mismatch": null,
    "note": "post-stop checks; no script offers them as a command - stage 3"
+  },
+  {
+   "skill": "multi-agent-mux-update",
+   "start": 17,
+   "end": 19,
+   "lang": "bash",
+   "sha": "63f73ade58d3",
+   "class": "c",
+   "kind": "invocation",
+   "evidence": [
+    "multi-agent-mux-update/scripts/update.sh:3"
+   ],
+   "mismatch": null,
+   "note": "entry point call (Issue #72)"
   }
  ],
  "removed": [
@@ -476,11 +490,11 @@
    "evidence": [
     "multi-agent-mux-resume/scripts/resume_session.sh:111-130",
     "multi-agent-mux-resume/scripts/resume_session.sh:133-144",
-    "multi-agent-mux-resume/scripts/resume_session.sh:147-158",
+    "multi-agent-mux-resume/scripts/resume_session.sh:147-170",
-    "multi-agent-mux-resume/scripts/resume_session.sh:172-197",
+    "multi-agent-mux-resume/scripts/resume_session.sh:188-213",
-    "multi-agent-mux-resume/scripts/resume_session.sh:245",
+    "multi-agent-mux-resume/scripts/resume_session.sh:266",
-    "multi-agent-mux-resume/scripts/resume_session.sh:249",
+    "multi-agent-mux-resume/scripts/resume_session.sh:270",
-    "multi-agent-mux-resume/scripts/resume_session.sh:255-258",
+    "multi-agent-mux-resume/scripts/resume_session.sh:276-279",
     "lib_py/agents/adapters/claude.py:109"
    ],
    "mismatch": [
@@ -503,9 +517,9 @@
    "base_sha": "a7ed3e902cae",
    "class": "a",
    "evidence": [
-    "multi-agent-mux-stop/scripts/stop_session.sh:99",
+    "multi-agent-mux-stop/scripts/stop_session.sh:101",
-    "multi-agent-mux-stop/scripts/stop_session.sh:140-143",
+    "multi-agent-mux-stop/scripts/stop_session.sh:128-198",
-    "multi-agent-mux-stop/scripts/stop_session.sh:184-188"
+    "multi-agent-mux-stop/scripts/stop_session.sh:250-254"
    ],
    "mismatch": [
     "T1: the doc offered --force-no-yaml, which no script accepts"
@@ -547,8 +561,8 @@
     "multi-agent-mux-create/scripts/create_session.sh:166-168",
     "multi-agent-mux-create/scripts/create_session.sh:207",
     "multi-agent-mux-create/scripts/create_session.sh:259-274",
-    "multi-agent-mux-create/scripts/create_session.sh:361-398",
+    "multi-agent-mux-create/scripts/create_session.sh:365-402",
-    "multi-agent-mux-create/scripts/create_session.sh:410-412"
+    "multi-agent-mux-create/scripts/create_session.sh:414-416"
    ],
    "mismatch": [
     "C1: an existing session is exit 1 in the doc, exit 3 in the script",
@@ -568,7 +582,7 @@
    "base_sha": "f71be0f26fb8",
    "class": "a",
    "evidence": [
-    "multi-agent-mux-create/scripts/create_session.sh:491-610"
+    "multi-agent-mux-create/scripts/create_session.sh:490-608"
    ],
    "mismatch": [],
    "replacement": "bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace <path> --agent <agent> --role <role>",
@@ -596,10 +610,12 @@
     "2",
     "3",
     "4",
+    "5",
+    "6",
     "other"
    ],
    "passthrough": {
-    "1": "multi-agent-mux-stop/scripts/stop_session.sh:327"
+    "1": "multi-agent-mux-stop/scripts/stop_session.sh:389"
    }
   },
   "multi-agent-mux-create/scripts/create_session.sh": {
@@ -624,7 +640,7 @@
  "prose_mismatches": [
   "C4: create named a nonexistent `agent-sessions-yaml-edit` script; removed (create_session.sh writes the row)",
   "C5: create's cmd_full table (claude = `claude`) disagreed with adapter spawn-spec; replaced by \"decided by spawn-spec\"",
-  "C6: create_session.sh header lists exit 4 \"YAML append failure\"; there is no literal `exit 4`, but the YAML write raises SystemExit(4) for a duplicate running row (create_session.sh:515) and it passes through, so 4 IS a real exit code (the plan assumed it was not)",
+  "C6: create_session.sh header lists exit 4 \"YAML append failure\"; there is no literal `exit 4`, but the YAML write raises SystemExit(4) for a duplicate running row (create_session.sh:516) and it passes through, so 4 IS a real exit code (the plan assumed it was not)",
   "R6: resume's \"The script above re-passes them\" and \"as done in Workflow above\" pointed at the removed block; reworded (same for create's Verification note)",
   "R7 (review 08e1f1b2): stop's table said exit 1 is always pre-stop; the registry update after the kill chain also raises SystemExit(1) (stop_session.sh:310) when the row disappeared"
  ],

tests/test_deploy_layout.py

@@ -48,7 +48,7 @@ class TestDeployLayout(unittest.TestCase):
         self.assertTrue(os.path.exists(os.path.join(self.test_dir, ".agents", "skills", "lib.sh")))
 
     def test_td6_td7_td8_mam_deploy_layout_and_removal(self):
-        """T-D6~D8: Verify remove.sh/update.sh installed in .mam_deploy and work properly."""
+        """T-D6~D8: Verify remove.sh installed in .mam_deploy (update.sh not, Issue #72) and works properly."""
         subprocess.run(
             ["bash", os.path.join(self.repo_root, "deploy/install.sh"), self.test_dir],
             env=self.env,
@@ -59,7 +59,7 @@ class TestDeployLayout(unittest.TestCase):
         remover = os.path.join(self.test_dir, ".mam_deploy", "remove.sh")
         updater = os.path.join(self.test_dir, ".mam_deploy", "update.sh")
         self.assertTrue(os.path.exists(remover))
-        self.assertTrue(os.path.exists(updater))
+        self.assertFalse(os.path.exists(updater))
         self.assertTrue(os.access(remover, os.X_OK))
 
         # T-D8: Execution from inside .mam_deploy directory targets parent workspace
@@ -129,17 +129,29 @@ class TestDeployLayout(unittest.TestCase):
         self.assertTrue(os.path.exists(backups_dir))
 
     def test_td27_td28_update_preserves_mam_state(self):
-        """T-D27~D28: Verify update.sh preserves .mam state files across cycles (B-5 gate)."""
+        """T-D27~D28: Verify the update skill preserves .mam state files across cycles (B-5 gate)."""
         subprocess.run(
             ["bash", os.path.join(self.repo_root, "deploy/install.sh"), self.test_dir],
             env=self.env,
             check=True
         )
 
-        # Run update.sh
+        # Run the update skill (Issue #72: .mam_deploy/update.sh is gone)
-        updater = os.path.join(self.test_dir, ".mam_deploy", "update.sh")
+        updater = os.path.join(self.test_dir, ".agents", "skills", "multi-agent-mux-update", "scripts", "update.sh")
-        res = subprocess.run(["bash", updater, "--force"], cwd=self.test_dir, env=self.env, capture_output=True, text=True)
+        env = {k: v for k, v in self.env.items() if not k.startswith("HERDR_")
-        self.assertEqual(res.returncode, 0, f"update.sh failed: {res.stderr}")
+               and k not in ("WORKSPACE_ROOT", "AGENT_SESSIONS_YAML", "MAM_JOBS_DIR")}
+        env["MAM_NO_SUBSCRIBER_DAEMON"] = "1"
+        # The update lists the live herdr agents; never ask a real server here.
+        fake = os.path.join(self.temp_dir, "fake-herdr-bin")
+        os.makedirs(fake)
+        with open(os.path.join(fake, "herdr"), "w") as f:
+            f.write('#!/bin/sh\necho \'{"sessions": []}\'\n')
+        os.chmod(os.path.join(fake, "herdr"), 0o755)
+        env["PATH"] = fake + ":" + env["PATH"]
+        res = subprocess.run(["bash", updater, "--yes"], cwd=self.test_dir, env=env, capture_output=True, text=True,
+                             stdin=subprocess.DEVNULL)
+        self.assertEqual(res.returncode, 0, f"the update skill failed: {res.stdout}{res.stderr}")
+        self.assertFalse(os.path.exists(os.path.join(self.test_dir, ".mam_deploy", "update.sh")))
 
         # Verify asset_hashes.txt and version.txt still exist
         self.assertTrue(os.path.exists(os.path.join(self.test_dir, ".mam", "asset_hashes.txt")))

tests/test_issue21_worktree_prereqs.py

@@ -581,7 +581,7 @@ def test_t3_1_create_persists_and_forwards_a_foreign_binding(mam_sandbox, mock_h
     for k, v in zip(FORWARDED_ENV, list(_binding(tmp).values())[:3]):
         assert f"{k}={v}" in flags, flags
     assert "WORKSPACE_ROOT=" not in row["pane"]["cmd_full"]
-    assert "WORKSPACE_ROOT=" not in row["start_command"]
+    assert "WORKSPACE_ROOT=" not in row["attach_command"]
     _assert_no_env_in_agent_args(mock_herdr)