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

@@ -24,9 +24,20 @@ import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Set, Tuple
 
+from lib_py.delegation import registry as job_registry
 from lib_py.loop import checkpoint, eager, parser
 
 UNAVAILABLE_MARKER = "!!! CHANGE SET UNAVAILABLE !!!"  # diff_collect.sh MAM_DIFF_UNAVAILABLE_MARKER
+# Issue #34: what a finished sub-job's record does and does not say. A job the
+# orchestrator closed (deadline, no ack) says nothing about its agent, which is
+# not interrupted and may still be writing; a job that never reached its agent
+# was cancelled before injection.
+TERMINAL = ("completed", "error", "cancelled")
+ORCHESTRATOR_CLOSED = ("deadline_timeout", "agent_blocked")
+SUBJOB_RULE = ("규칙: 열린(OPEN)·미확인 종결(CLOSED-UNCONFIRMED)·실패 하위 잡이 하나라도 있으면 산출물을 미완으로 보고 "
+               "[VERDICT: NOT PASS] 를 내십시오. creator 리포트가 해당 부분의 대체 완료를 입증하면 예외입니다. "
+               "CLOSED-UNCONFIRMED 는 오케스트레이터가 마감으로 닫은 잡이며 그 에이전트는 계속 일하고 있을 수 있습니다. "
+               "리뷰 중 소스가 바뀌면 이 회차의 승인은 무효가 됩니다.")
 SELF_REVIEW_PROMPT = ("작업 완료 상태에 대해 스스로 검증(Self-Review)하여 결함이 없음을 확인하고 종결해주세요. "
                       "리뷰 리포트 마지막에 단독 행으로 반드시 '[VERDICT: PASS]' 혹은 '[VERDICT: NOT PASS]' 태그를 명시해주세요.")
 
@@ -87,6 +98,9 @@ class LoopRunner:
         self._rounds: List[Dict[str, Any]] = []
         self._accepted_round: Optional[Dict[str, Any]] = None
         self.created_jobs: List[str] = []
+        # Issue #34: the creator jobs whose sub-job trees this round's reviewers see
+        self.round_roots: List[str] = []
+        self.wait_open_jobs = False
         self.failed_submit_jobs: Set[str] = set()
         self.current_plan = ""
         self.plan_job_id: Optional[str] = None
@@ -128,6 +142,7 @@ class LoopRunner:
             "  --review-only          Skip implementation; review <base>..HEAD (requires --base)",
             "  --review-isolation <v> Review tree with --worktree/--base: worktree (default) or env",
             "  --remote-review <v>    Remote reviewers with --worktree/--base: refuse (default) or diff-only",
+            "  --wait-open-jobs       Also wait for open jobs registered without --parent-job during the creator's work",
         ]
         print("\n".join(lines))
 
@@ -202,6 +217,9 @@ class LoopRunner:
             elif arg == "--cleanup":
                 self.cleanup = True
                 i += 1
+            elif arg == "--wait-open-jobs":
+                self.wait_open_jobs = True
+                i += 1
             elif arg == "--worktree":
                 if i + 1 >= len(args):
                     self.print_usage()
@@ -599,6 +617,113 @@ class LoopRunner:
         log_error(f"Job '{job_id}' timed out after {max_wait}s.")
         return False
 
+    # ------------------------------------------------------------------
+    # Issue #34: a creator job's sub-jobs (registered with --parent-job)
+    # ------------------------------------------------------------------
+    def _created_at(self, job_id: str) -> str:
+        try:
+            return str(job_registry.load_job(job_id, str(self.jobs_dir)).get("created_at") or "")
+        except (OSError, ValueError):
+            return ""
+
+    def unattributed_open_jobs(self, since: str) -> List[Dict[str, Any]]:
+        """Open jobs registered without a parent since ``since`` that this loop
+        did not create - most likely a sub-delegation that left out --parent-job."""
+        return [r for r in job_registry.list_jobs(str(self.jobs_dir))
+                if r.get("status") in ("pending", "running") and not r.get("parent_job")
+                and r.get("job_id") not in self.created_jobs and str(r.get("created_at") or "") >= since]
+
+    def wait_for_descendants(self, root: str, interval: float = 3.0) -> bool:
+        """Wait until every record in root's sub-job tree is terminal. The tree
+        is re-read on each poll, so a grandchild registered meanwhile is waited
+        for too. Bounded by MAM_CHILD_WAIT_S (from now) and MAM_JOB_TREE_MAX.
+        A terminal record is not a stopped agent (a deadline close does not
+        interrupt it); that is left to the sub-job table and the stale-review
+        guard, since nothing signals such an agent's end."""
+        max_wait = float(os.environ.get("MAM_CHILD_WAIT_S", "3900"))
+        tree_max = int(os.environ.get("MAM_JOB_TREE_MAX", "50"))
+        since = self._created_at(root)
+        start = time.time()
+        last = None
+        while True:
+            if self.interrupted:
+                return False
+            tree = job_registry.descendants_of(root, str(self.jobs_dir))
+            if len(tree) > tree_max:
+                log_error(f"job {root} has {len(tree)} sub-jobs (over MAM_JOB_TREE_MAX={tree_max}); not waiting for them")
+                return False
+            open_jobs = [r for r in tree if r.get("status") not in TERMINAL]
+            if self.wait_open_jobs:
+                open_jobs += self.unattributed_open_jobs(since)
+            if not open_jobs:
+                return True
+            now = [(r.get("job_id"), r.get("status")) for r in open_jobs]
+            if now != last:
+                log_info(f"waiting for {len(open_jobs)} sub-job(s) of {root}: "
+                         + " ".join(f"{r.get('job_id')}({r.get('agent_session', '?')}, {r.get('status')})" for r in open_jobs))
+                last = now
+            if time.time() - start >= max_wait:
+                log_warn(f"sub-job wait for {root} ended after {int(max_wait)}s (MAM_CHILD_WAIT_S) with "
+                         f"{len(open_jobs)} open; reviewers see them as OPEN")
+                return False
+            time.sleep(interval)
+
+    def wait_for_job_tree(self, root: str) -> bool:
+        """wait_for_job, then (when the root succeeded) its sub-job tree. The
+        result is the root's own: sub-job outcomes are review evidence."""
+        if not self.wait_for_job(root):
+            return False
+        log_info(f"Creator job {root} finished; waiting for its sub-jobs...")
+        self.wait_for_descendants(root)
+        return True
+
+    def _subjob_state(self, r: Dict[str, Any]) -> Tuple[str, str]:
+        """(state, reason) for the sub-job table."""
+        status = str(r.get("status") or "?")
+        if status not in TERMINAL:
+            return "OPEN", "-"
+        reason = job_registry.get_feedback(str(r.get("job_id")), str(self.jobs_dir)) or ""
+        if status == "completed":
+            return "completed", reason or "-"
+        if reason in ORCHESTRATOR_CLOSED or (status == "error" and not reason):
+            # no recorded reason is not the agent's own report either
+            return "CLOSED-UNCONFIRMED", reason or "-"
+        if status == "cancelled" and (reason == "session_busy" or reason.startswith("rolled back")):
+            return "NOT-DISPATCHED", reason
+        return status, reason or "-"
+
+    def _subjobs_block(self, roots: List[str]) -> str:
+        """The [하위 위임 잡] evidence put in front of this round's review prompts."""
+        if not roots:
+            return ""
+        rows: List[str] = []
+        counts = {"open": 0, "unconfirmed": 0, "failed": 0, "completed": 0}
+        for root in roots:
+            for r in job_registry.descendants_of(root, str(self.jobs_dir)):
+                state, reason = self._subjob_state(r)
+                key = ("open" if state == "OPEN" else "unconfirmed" if state == "CLOSED-UNCONFIRMED"
+                       else "completed" if state == "completed" else "failed")
+                counts[key] += 1
+                if state == "CLOSED-UNCONFIRMED":
+                    log_warn(f"sub-job {r.get('job_id')} was closed by the orchestrator ({reason}); its agent may still "
+                             f"be writing to {self.worktree_root} - this round's approvals are void if the source changes")
+                rows.append(f"| {r.get('job_id')} | {r.get('agent_session', '-')} | {r.get('role', '-')} | {state} | "
+                            f"{reason} | {r.get('depth')} | {r.get('created_at', '-')} | {r.get('updated_at', '-')} |")
+        since = min((self._created_at(j) for j in roots), default="")
+        stray = self.unattributed_open_jobs(since)
+        stray_text = (" ".join(f"{r.get('job_id')}({r.get('agent_session', '?')}, {r.get('status')})" for r in stray)
+                      if stray else "없음")
+        stray_line = f"[귀속되지 않은 열린 잡] (부모 미표기, 이 작업 중 등록됨): {stray_text}\n"
+        if not rows and not stray:
+            return ""  # no sub-delegation: the prompts stay byte-identical (Issue #34 requirement 3)
+        if not rows:
+            return f"[하위 위임 잡] 없음 (creator 잡 {' '.join(roots)})\n{stray_line}\n"
+        return (f"[하위 위임 잡] (creator 잡 {' '.join(roots)} 의 자손, 깊이 순)\n"
+                "| job | 세션 | 역할 | 상태 | 사유 | 깊이 | 등록 | 갱신 |\n"
+                "|---|---|---|---|---|---|---|---|\n" + "\n".join(rows) + "\n"
+                f"열린 {counts['open']}, 미확인 종결 {counts['unconfirmed']}, 실패 {counts['failed']}, "
+                f"완료 {counts['completed']}.\n{SUBJOB_RULE}\n{stray_line}\n")
+
     def find_report(self, job_id: str) -> Optional[Path]:
         """Locate report-final.md for a job."""
         job_dir = self.jobs_dir / job_id
@@ -763,11 +888,12 @@ class LoopRunner:
                      "evidence (--remote-review diff-only)")
         return True
 
-    def _worktree_tree(self) -> Optional[str]:
+    def _worktree_tree(self, exclude: Tuple[str, ...] = ()) -> Optional[str]:
         """The source worktree's state as a tree, through a temporary index
         (the real index, status and refs are untouched); None on failure.
         A dirty submodule is a failure: the tree records only its gitlink, so
-        its uncommitted content would be neither reviewed nor pinned."""
+        its uncommitted content would be neither reviewed nor pinned.
+        exclude: source-relative paths left out of `add -A` (Issue #34)."""
         dirty_subs = self._dirty_submodules()
         if dirty_subs is None:
             log_error(f"review snapshot: cannot check the submodules of {self.worktree_root}")
@@ -781,7 +907,8 @@ class LoopRunner:
         os.unlink(idx)
         env = dict(os.environ, GIT_INDEX_FILE=idx)
         try:
-            for step in (("read-tree", "HEAD"), ("add", "-A"), ("write-tree",)):
+            add = ("add", "-A") + (("--", ".") + tuple(f":(exclude){p}" for p in exclude) if exclude else ())
+            for step in (("read-tree", "HEAD"), add, ("write-tree",)):
                 r = subprocess.run(["git", "-C", str(self.worktree_root), *step],
                                    capture_output=True, text=True, env=env)
                 if r.returncode != 0:
@@ -822,6 +949,27 @@ class LoopRunner:
     def _identity_now(self) -> Tuple[str, str]:
         return (self._source_head(), self._worktree_tree() or "")
 
+    def _fingerprint(self) -> Optional[Tuple[str, str]]:
+        """Issue #34 (D9): the source's head and tree for the stale-review guard
+        without --worktree/--base, where the control plane (.mam, the jobs and
+        audit-log dirs) usually lives inside the source and changes on every
+        job; it is left out. None when the source cannot be fingerprinted."""
+        head = self._source_head()
+        if not head:
+            return None
+        root = self.worktree_root.resolve()
+        logs = Path(os.environ.get("DELEGATE_JOB_LOGS_DIR") or self.mam_dir / "delegate_job_logs")
+        exclude = []
+        for d in (self.mam_dir, self.jobs_dir, self.workspace_root / logs):
+            try:
+                rel = d.resolve().relative_to(root)
+            except ValueError:
+                continue
+            if str(rel) != ".":
+                exclude.append(str(rel))
+        tree = self._worktree_tree(tuple(exclude))
+        return (head, tree) if tree else None
+
     def _snapshot(self, n: int) -> Optional[Dict[str, Any]]:
         """B3: pin the source state of review round n. Uncommitted and
         untracked (not ignored) files go into a ref-less snapshot commit on
@@ -1137,7 +1285,8 @@ class LoopRunner:
                 return 1
             log_info(f"Creator Job ID: {exec_jid}")
 
-            if not self.wait_for_job(exec_jid):
+            self.round_roots = [exec_jid]
+            if not self.wait_for_job_tree(exec_jid):
                 log_error("Creator execution failed.")
                 return 1
             log_success("Initial implementation finished.")
@@ -1160,6 +1309,8 @@ class LoopRunner:
 
         final_passed_reviewers: Dict[str, Tuple[str, Path]] = {}
         identity = self._context_active()
+        light: Optional[Tuple[str, str]] = None  # Issue #34: this round's source without --worktree/--base
+        guard_warned = False
         # Identity mode: a creator self-review is a verdict like any other, so it
         # takes the reviewer path - snapshot diff, evidence check, B10 re-check
         # and sidecar (loop B review B-R2/B-R3). A NOT PASS re-reviews, as before.
@@ -1189,17 +1340,32 @@ class LoopRunner:
                         return 1
                 else:
                     review_path = str(self.worktree_root)
+            else:
+                # Issue #34 (D9): the identity mode's B7 for every loop - a sub-job
+                # closed by deadline may still be writing to the source
+                light = self._fingerprint()
+                if light is None and not guard_warned:
+                    log_warn(f"cannot fingerprint the source at {self.worktree_root}; "
+                             "the stale-review guard is off for this run")
+                    guard_warned = True
+            subjobs = self._subjobs_block(self.round_roots)
 
             if not reviewers:
                 # Creator Self-Review
                 log_warn("No reviewers specified. Conducting Creator Self-Review...")
-                sr_prompt = SELF_REVIEW_PROMPT
+                sr_prompt = subjobs + SELF_REVIEW_PROMPT
                 sr_jid = self._dispatch(self.creator, creator_type, "Reviewer", sr_prompt)
                 if not sr_jid:
                     log_error("Failed to register Self-Review job.")
                     return 1
                 self.wait_for_job(sr_jid)
                 sr_report = self.find_report(sr_jid)
+                if light is not None and self._fingerprint() != light:
+                    log_warn("source changed during review; approvals discarded, re-reviewing")
+                    if loop_count == self.max_loop:
+                        log_error("the source changed during review in the last iteration; no approval to accept")
+                        return 1
+                    continue
                 if sr_report and parser.has_verdict(sr_report, "PASS") and not parser.has_verdict(sr_report, "NOT PASS"):
                     log_success("Self-Review PASS.")
                     break
@@ -1230,6 +1396,7 @@ class LoopRunner:
                 else:
                     r_prompt = f"다음 구현 사항(작업 목표: {self.task}) 및 누적 변경분(git diff)에 대해 린트, 동작성, 유실 등의 관점에서 교차 코드 리뷰를 수행해주세요. 확인 후 최종 Verdict로 '[VERDICT: PASS]' 혹은 '[VERDICT: NOT PASS]' 태그를 리뷰 리포트 마지막에 단독 행으로 명시적으로 작성해주세요. 만약 단순 버그 수정으로는 부족하고 설계 변경/재작업 수준의 재계획이 필요하다고 판단되면, 리포트 아무 곳에나 단독 행으로 '[ESCALATE: PLANNER]' 태그도 함께 남겨주세요. 변경분:\n{changes_diff}"
                 r_remote = rev in self._remote_recipients
+                r_prompt = subjobs + r_prompt
                 if identity:
                     r_prompt = self._identity_block(snap, review_path, r_remote) + r_prompt
                 r_jid = self._dispatch(rev, r_type, "Reviewer", r_prompt, remote=r_remote,
@@ -1288,6 +1455,14 @@ class LoopRunner:
                         log_error("the source changed during review in the last iteration; no approval to accept")
                         return 1
                     continue
+            elif light is not None and self._fingerprint() != light:
+                final_passed_reviewers.clear()
+                log_warn(f"source changed during review (head {light[0][:12]}, tree {light[1][:12]}); "
+                         "approvals discarded, re-reviewing")
+                if loop_count == self.max_loop:
+                    log_error("the source changed during review in the last iteration; no approval to accept")
+                    return 1
+                continue
 
             if all_passed:
                 if identity:
@@ -1335,7 +1510,9 @@ class LoopRunner:
                 correction_prompt += f"\n\n[이의제기 채널] 위 피드백 중 타당하지 않다고 판단되는 항목이 있다면, 그 항목은 구현하지 말고 반론을 제기하십시오. 반론 시 리포트에 단독 행으로 '[REBUT: <리뷰어_세션명>]' 태그를 남기고, 해당 리뷰어의 지적 중 어느 항목을 왜 거부하는지 근거를 함께 서술하십시오. 타당한 지적은 정상적으로 반영하십시오. 반론할 항목이 없으면 태그를 남기지 마십시오. 대상 리뷰어 세션명: {' '.join(fail_revs) if fail_revs else '(없음)'}"
 
             correct_jid = self._dispatch(self.creator, creator_type, "Worker", correction_prompt)
-            if not correct_jid or not self.wait_for_job(correct_jid):
+            if correct_jid:
+                self.round_roots = [correct_jid]
+            if not correct_jid or not self.wait_for_job_tree(correct_jid):
                 log_error("Failed to register Creator correction job.")
                 return 1
 
@@ -1404,10 +1581,17 @@ class LoopRunner:
                             rebut_budget = 0
                             comply_prompt = f"귀하의 반론은 재심 결과 기각되었습니다. 더 이상 반론하지 말고 다음 리뷰 피드백을 그대로 반영하여 코드를 수정하십시오. 피드백:\n{feedback_aggregate}"
                             comp_jid = self._dispatch(self.creator, creator_type, "Worker", comply_prompt)
-                            if not comp_jid or not self.wait_for_job(comp_jid):
+                            if comp_jid:
+                                self.round_roots.append(comp_jid)
+                            if not comp_jid or not self.wait_for_job_tree(comp_jid):
                                 log_error("Failed to register Creator compliance job.")
                                 return 1
 
+        if light is not None and self._fingerprint() != light:
+            # Issue #34: B10 without --worktree/--base, before anything is promoted
+            log_error("source changed after approval; not promoting")
+            return 1
+
         # Promotion
         if self.plan_mode and self.current_plan and self.plan_job_id:
             plan_dest_dir = self.workspace_root / ".agents" / "reports" / planner_session

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

@@ -38,6 +38,7 @@ LOOP_BASE=""
 LOOP_REVIEW_ONLY=0
 LOOP_REVIEW_ISOLATION=""
 LOOP_REMOTE_REVIEW=""
+LOOP_WAIT_OPEN_JOBS=0
 
 # Print usage instructions
 usage() {
@@ -59,6 +60,7 @@ usage() {
   echo "  --review-only          Skip implementation; review <base>..HEAD (requires --base)"
   echo "  --review-isolation <v> Review tree with --worktree/--base: worktree (default) or env"
   echo "  --remote-review <v>    Remote reviewers with --worktree/--base: refuse (default) or diff-only"
+  echo "  --wait-open-jobs       Also wait for open jobs registered without --parent-job during the creator's work"
   exit 1
 }
 
@@ -101,6 +103,7 @@ while [[ "$#" -gt 0 ]]; do
     --review-only) LOOP_REVIEW_ONLY=1; shift ;;
     --review-isolation) LOOP_REVIEW_ISOLATION="$2"; shift 2 ;;
     --remote-review) LOOP_REMOTE_REVIEW="$2"; shift 2 ;;
+    --wait-open-jobs) LOOP_WAIT_OPEN_JOBS=1; shift ;;
     -h|--help) usage ;;
     *) echo "Unknown option: $1"; usage ;;
   esac
@@ -130,8 +133,8 @@ fi
 if [ "${MAM_LOOP_PY:-1}" = "0" ] && { [ -n "$LOOP_WORKTREE" ] || [ -n "$LOOP_BASE" ] \
      || [ "$LOOP_REVIEW_ONLY" = "1" ] || [ -n "${MAM_LOOP_WORKTREE:-}" ] \
      || [ -n "$LOOP_REVIEW_ISOLATION" ] || [ -n "$LOOP_REMOTE_REVIEW" ] \
-     || [ -n "$LOOP_PLAN_FILE" ]; }; then
-  echo "ERROR: --worktree/--base/--review-only/--review-isolation/--remote-review/--plan-file require the Python loop (MAM_LOOP_PY=1)" >&2
+     || [ -n "$LOOP_PLAN_FILE" ] || [ "$LOOP_WAIT_OPEN_JOBS" = "1" ]; }; then
+  echo "ERROR: --worktree/--base/--review-only/--review-isolation/--remote-review/--plan-file/--wait-open-jobs require the Python loop (MAM_LOOP_PY=1)" >&2
   exit 1
 fi
 

tests/test_issue34_job_tree.py

@@ -0,0 +1,485 @@
+"""Issue #34: the loop waits for the creator job's sub-jobs, reviewers see them.
+
+A creator that hands part of its work to another agent (delegate-job submit)
+used to end its own job while the sub-job was still running; the loop went
+straight to review and the reviewers passed half-finished work. Jobs now record
+their parent (`submit --parent-job`), the loop waits for the creator job's
+sub-job tree, the review prompt carries a sub-job table, and a round whose
+source changed during review is void in every mode (a sub-job closed by its
+deadline is not interrupted and may still be writing).
+
+Sub-jobs are registered by the real wrapper (`submit --dry-run`, which returns
+after the real registry wrote the record) and closed by the real producers:
+`publish_event.py`, and for a deadline the wrapper's own sequence
+(`registry.py close --request deadline_timeout`, then `publish_event --event
+error --detail deadline_timeout`). The loop is a real `python -m lib_py.loop`
+process; only the loop's own agents are simulated, by an executable behind a
+wrapper at the control root (the #36 harness).
+
+T34_SKILLS points the harness at another copy of .agents/skills (used once to
+run T3/T5b against the base runner). Every test writes only under tmp_path.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import re
+import subprocess
+import sys
+import threading
+import time
+from pathlib import Path
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+SKILLS = Path(os.environ.get("T34_SKILLS") or REPO_ROOT / ".agents" / "skills")
+WRAPPER = SKILLS / "multi-agent-mux-delegate-job" / "multi-agent-mux-delegate-job"
+REGISTRY = SKILLS / "multi-agent-mux-delegate-job" / "scripts" / "registry.py"
+PUBLISH = SKILLS / "multi-agent-mux-delegate-job" / "scripts" / "publish_event.py"
+
+if str(SKILLS) not in sys.path:
+    sys.path.insert(0, str(SKILLS))
+
+UNREACHABLE = {"MQTT_BROKER": "127.0.0.1", "MQTT_PORT": "9", "MQTT_TLS": "0"}
+GIT_ID = {"GIT_AUTHOR_NAME": "t", "GIT_AUTHOR_EMAIL": "t@example.invalid",
+          "GIT_COMMITTER_NAME": "t", "GIT_COMMITTER_EMAIL": "t@example.invalid"}
+
+
+def _env(home: Path, extra=None, drop=()) -> dict:
+    env = dict(os.environ)
+    env["DELEGATE_JOB_PYTHON"] = sys.executable
+    env["AGENT_PYTHON_BIN"] = sys.executable
+    env["HOME"] = str(home)
+    env["MAM_ENV_FILE"] = str(home / ".mam.env.absent")
+    env["PYTHONPATH"] = str(SKILLS)
+    for k in ("MQTT_BROKER", "MQTT_HOST", "MQTT_PORT", "MQTT_TLS", "MQTT_USERNAME", "MQTT_PASSWORD",
+              "MAM_JOBS_DIR", "DELEGATE_JOB_LOGS_DIR", "WORKSPACE_ROOT", "MAM_REAL_ROOT", "MAM_JOB_ID",
+              "MAM_CHILD_WAIT_S", "MAM_JOB_TREE_MAX"):
+        env.pop(k, None)
+    env.update(UNREACHABLE)
+    env.update(GIT_ID)
+    env["DELEGATE_JOB_LOGS_DIR"] = str(home / ".mam-logs")
+    env["WORKSPACE_ROOT"] = str(home)
+    if extra:
+        env.update({k: str(v) for k, v in extra.items()})
+    for k in drop:
+        env.pop(k, None)
+    return env
+
+
+def _git(cwd: Path, *args: str) -> str:
+    return subprocess.run(["git", "-C", str(cwd), *args], capture_output=True, text=True,
+                          check=True, env={**os.environ, **GIT_ID}).stdout.strip()
+
+
+def _repo(path: Path) -> Path:
+    path.mkdir(parents=True, exist_ok=True)
+    _git(path, "init", "-q")
+    (path / "a.txt").write_text("a\n")
+    _git(path, "add", "a.txt")
+    _git(path, "commit", "-q", "-m", "init")
+    return path
+
+
+def _submit(env: dict, reg: Path, *extra: str) -> subprocess.CompletedProcess:
+    """The real wrapper; --dry-run returns right after the real registration."""
+    return subprocess.run(["bash", str(WRAPPER), "submit", "--agent", "human", "--agent-session", "herdr:img",
+                           "--dry-run", "--registry-dir", str(reg), "--prompt", "draw the figures", *extra],
+                          capture_output=True, text=True, env=env, cwd=env["HOME"], timeout=120)
+
+
+def _jid(res: subprocess.CompletedProcess) -> str:
+    assert res.returncode == 0, res.stdout + res.stderr
+    m = re.search(r"registered job:\s*(\S+)", res.stdout)
+    assert m, res.stdout
+    return m.group(1)
+
+
+def _record(reg: Path, jid: str) -> dict:
+    return json.loads((reg / f"{jid}.json").read_text(encoding="utf-8"))
+
+
+def _publish(env: dict, reg: Path, jid: str, event: str, detail: str) -> None:
+    """The real producer, with the dispatch token the agent is given. The
+    broker is unreachable here: publish_event exits 2 after the record and
+    the events log were already written."""
+    tok = _record(reg, jid)["dispatch_token"]
+    res = subprocess.run([sys.executable, str(PUBLISH), "--registry-dir", str(reg), "--job", jid,
+                          "--event", event, "--detail", detail, "--expect-dispatch-token", tok],
+                         capture_output=True, text=True, env=env, timeout=120)
+    assert res.returncode in (0, 2), res.stderr
+    if event in ("completed", "error"):
+        assert _record(reg, jid)["status"] in ("completed", "error"), res.stderr
+
+
+def _deadline_close(env: dict, reg: Path, jid: str) -> None:
+    """What the wrapper's finalize_unfinished does at a job's deadline."""
+    tok = _record(reg, jid)["dispatch_token"]
+    res = subprocess.run([sys.executable, str(REGISTRY), "--registry-dir", str(reg), "close", "--job", jid,
+                          "--request", "deadline_timeout", "--expect-dispatch-token", tok],
+                         capture_output=True, text=True, env=env, timeout=120)
+    assert res.returncode == 0, res.stderr
+    _publish(env, reg, jid, "error", "deadline_timeout")
+
+
+# ---------------------------------------------------------------------------
+# T1 - a job records its parent
+# ---------------------------------------------------------------------------
+
+def test_t1_submit_records_the_parent_job(tmp_path):
+    env = _env(tmp_path)
+    reg = tmp_path / "reg"
+    p_res = _submit(env, reg)
+    p = _jid(p_res)
+    assert _record(reg, p)["parent_job"] is None
+    # the injected instructions tell the agent how to pass itself on
+    assert f"add --parent-job {p} so the orchestrator waits for it." in p_res.stdout
+
+    c = _jid(_submit(env, reg, "--parent-job", p))
+    assert _record(reg, c)["parent_job"] == p
+
+    bad = _submit(env, reg, "--parent-job", "nope1234")
+    assert bad.returncode == 1 and "unknown parent job nope1234" in bad.stderr
+    assert "registered job:" not in bad.stdout
+
+    # the remote runner's MAM_JOB_ID is the default ...
+    e = _jid(_submit(_env(tmp_path, {"MAM_JOB_ID": p}), reg))
+    assert _record(reg, e)["parent_job"] == p
+    # ... ignored with a warning when this registry lacks it (another host's mirror)
+    stray = _submit(_env(tmp_path, {"MAM_JOB_ID": "feedf00d"}), reg)
+    assert _record(reg, _jid(stray))["parent_job"] is None
+    assert "MAM_JOB_ID=feedf00d is not in" in stray.stderr
+    # ... and the flag wins over it
+    f = _jid(_submit(_env(tmp_path, {"MAM_JOB_ID": p}), reg, "--parent-job", c))
+    assert _record(reg, f)["parent_job"] == c
+
+    listed = subprocess.run([sys.executable, str(REGISTRY), "--registry-dir", str(reg), "list", "--parent", p],
+                            capture_output=True, text=True, env=env, timeout=60)
+    assert listed.returncode == 0
+    assert {line.split()[0] for line in listed.stdout.splitlines()} == {c, e}
+
+
+# ---------------------------------------------------------------------------
+# T2 / T7 - LoopRunner waits for the tree (real records, real events)
+# ---------------------------------------------------------------------------
+
+def _runner(tmp_path, monkeypatch, **env):
+    monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path))
+    monkeypatch.setenv("MAM_JOBS_DIR", str(tmp_path / "reg"))
+    monkeypatch.setenv("DELEGATE_JOB_LOGS_DIR", str(tmp_path / ".mam-logs"))
+    monkeypatch.delenv("MAM_REAL_ROOT", raising=False)
+    for k in ("MAM_CHILD_WAIT_S", "MAM_JOB_TREE_MAX"):
+        monkeypatch.delenv(k, raising=False)
+    for k, v in env.items():
+        monkeypatch.setenv(k, str(v))
+    from lib_py.loop import runner as lr
+    return lr.LoopRunner(["--creator", "c", "--task", "t"])
+
+
+def test_t2_the_runner_waits_for_children_and_grandchildren(tmp_path, monkeypatch):
+    env = _env(tmp_path)
+    reg = tmp_path / "reg"
+    p = _jid(_submit(env, reg))
+    c = _jid(_submit(env, reg, "--parent-job", p))
+    g = _jid(_submit(env, reg, "--parent-job", c))
+
+    def finish():
+        time.sleep(2)
+        _publish(env, reg, g, "completed", "grandchild done")
+        time.sleep(2)
+        _publish(env, reg, c, "completed", "child done")
+
+    t = threading.Thread(target=finish)
+    start = time.time()
+    t.start()
+    try:
+        # the cap only keeps a broken helper thread from hanging the suite
+        assert _runner(tmp_path, monkeypatch, MAM_CHILD_WAIT_S=60).wait_for_descendants(p, interval=0.5) is True
+        elapsed = time.time() - start
+    finally:
+        t.join()
+    assert elapsed >= 4
+    assert _record(reg, c)["status"] == "completed" and _record(reg, g)["status"] == "completed"
+
+
+def test_t2b_the_wait_is_bounded_in_time_and_in_size(tmp_path, monkeypatch, capsys):
+    env = _env(tmp_path)
+    reg = tmp_path / "reg"
+    p = _jid(_submit(env, reg))
+    c = _jid(_submit(env, reg, "--parent-job", p))
+    g = _jid(_submit(env, reg, "--parent-job", c))
+
+    start = time.time()
+    assert _runner(tmp_path, monkeypatch, MAM_CHILD_WAIT_S=2).wait_for_descendants(p, interval=0.5) is False
+    assert 2 <= time.time() - start < 10
+    out = capsys.readouterr().out
+    assert f"waiting for 2 sub-job(s) of {p}" in out and c in out and g in out
+    assert "with 2 open" in out
+
+    start = time.time()
+    assert _runner(tmp_path, monkeypatch, MAM_JOB_TREE_MAX=1).wait_for_descendants(p, interval=0.5) is False
+    assert time.time() - start < 2
+    assert "over MAM_JOB_TREE_MAX=1" in capsys.readouterr().err
+
+
+def test_t7_a_job_without_children_is_waited_for_as_before(tmp_path, monkeypatch):
+    env = _env(tmp_path)
+    reg = tmp_path / "reg"
+    p = _jid(_submit(env, reg))
+    _publish(env, reg, p, "completed", "done")
+    r = _runner(tmp_path, monkeypatch)
+    start = time.time()
+    assert r.wait_for_job_tree(p) is True
+    assert time.time() - start < 2  # one registry scan on top of wait_for_job
+    assert r.wait_for_job(p) is True
+
+
+# ---------------------------------------------------------------------------
+# Loop e2e: a real loop process; the loop's own agents are simulated. The
+# simulated creator registers its sub-job with the REAL wrapper.
+# ---------------------------------------------------------------------------
+
+FAKE_AGENT = r"""
+import json, os, re, secrets, subprocess, sys, time
+from pathlib import Path
+opts = dict(zip(sys.argv[2::2], sys.argv[3::2]))  # argv[1] = "submit"
+prompt = Path(opts["--prompt-file"]).read_text(encoding="utf-8")
+jobs = Path(opts["--registry-dir"])
+jobs.mkdir(parents=True, exist_ok=True)
+role = opts["--role"]
+now = lambda: time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
+jid = "f" + secrets.token_hex(4)
+rec = {"job_id": jid, "status": "running", "created_at": now(), "updated_at": now(), "created_ts": time.time(),
+       "agent_session": opts["--agent-session"], "role": role}
+path = jobs / (jid + ".json")
+path.write_text(json.dumps(rec))
+late = False
+if role == "Worker":
+    act = os.environ.get("FAKE_WORKER", "none")
+    marker = Path(".mam/child-id")
+    if act in ("child", "stray") and not marker.exists():  # the implementation job only
+        cmd = ["bash", os.environ["FAKE_REAL_WRAPPER"], "submit", "--agent", "human", "--agent-session",
+               "herdr:img", "--dry-run", "--registry-dir", str(jobs), "--prompt", "draw the figures"]
+        if act == "child":
+            cmd += ["--parent-job", jid]
+        out = subprocess.run(cmd, capture_output=True, text=True)
+        if out.returncode != 0:
+            print(out.stdout + out.stderr, file=sys.stderr)
+            sys.exit(2)
+        marker.write_text(re.search(r"registered job:\s*(\S+)", out.stdout).group(1))
+    report = "done\n"
+else:
+    counter = Path(".mam/review-count")
+    n = int(counter.read_text()) + 1 if counter.exists() else 1
+    counter.write_text(str(n))
+    Path(".mam/review-prompt-%d.md" % n).write_text(prompt, encoding="utf-8")
+    rule = os.environ.get("FAKE_REVIEW", "pass")
+    unfinished = re.search(r"(열린|미확인 종결|실패) [1-9]", prompt)
+    verdict = "NOT PASS" if rule == "rule" and unfinished else "PASS"
+    report = "reviewed\n\n[VERDICT: %s]\n" % verdict
+    late = os.environ.get("FAKE_LATE_WRITE") == str(n)
+dest = jobs / jid / "agent-reports"
+dest.mkdir(parents=True)
+(dest / "report-final.md").write_text(report, encoding="utf-8")
+rec.update(status="completed", updated_at=now())
+path.write_text(json.dumps(rec))
+if late:  # stands in for a sub-job agent that keeps writing after its deadline close
+    Path("late.txt").write_text("written during review\n")
+print("registered job: " + jid)
+"""
+
+
+def _loop_ctl(tmp_path: Path, git: bool = True) -> Path:
+    ctl = tmp_path / "ctl"
+    if git:
+        _repo(ctl)
+    else:
+        ctl.mkdir(parents=True)
+    agent = ctl / "fake-agent.py"
+    agent.write_text(FAKE_AGENT, encoding="utf-8")
+    w = ctl / ".agents" / "skills" / "multi-agent-mux-delegate-job" / "multi-agent-mux-delegate-job"
+    w.parent.mkdir(parents=True, exist_ok=True)
+    w.write_text(f'#!/usr/bin/env bash\nexec "{sys.executable}" "{agent}" "$@"\n', encoding="utf-8")
+    w.chmod(0o755)
+    (ctl / ".mam").mkdir(exist_ok=True)
+    if git:
+        (ctl / "plan.md").write_text("# plan\n\ndo it\n", encoding="utf-8")
+        _git(ctl, "add", "-A")
+        _git(ctl, "commit", "-q", "-m", "harness")
+    else:
+        (ctl / "plan.md").write_text("# plan\n\ndo it\n", encoding="utf-8")
+    return ctl
+
+
+def _loop_env(ctl: Path, **extra) -> dict:
+    return _env(ctl, extra={
+        "WORKSPACE_ROOT": ctl,
+        "MAM_JOBS_DIR": ctl / ".mam" / "jobs",
+        "DELEGATE_JOB_LOGS_DIR": ctl / ".mam" / "logs",
+        "MAM_SESSION_BUSY_RETRY_S": "0",
+        "MAM_CHILD_WAIT_S": "60",  # a broken helper thread fails the test instead of hanging it
+        "FAKE_REAL_WRAPPER": WRAPPER,
+        "MAM_STATE_JSON": json.dumps({"herdr_sessions": [
+            {"name": "c", "agent": "claude", "role": "creator", "status": "running"},
+            {"name": "r", "agent": "claude", "role": "reviewer", "status": "running"}]}),
+        **extra,
+    }, drop=("MAM_LOOP_WORKTREE", "MAM_LOOP_BASE", "MAM_VERSION"))
+
+
+def _run_loop(ctl: Path, env: dict, *argv: str, on_child=None) -> subprocess.CompletedProcess:
+    """Run the loop; on_child(child_id) runs in a thread once the simulated
+    creator registered its sub-job."""
+    marker = ctl / ".mam" / "child-id"
+    stop = threading.Event()
+    seen = {}
+
+    def watch():
+        while not stop.is_set():
+            if marker.exists() and marker.read_text().strip():
+                seen["id"] = marker.read_text().strip()
+                on_child(seen["id"])
+                return
+            time.sleep(0.2)
+
+    t = threading.Thread(target=watch) if on_child else None
+    if t:
+        t.start()
+    try:
+        return subprocess.run([sys.executable, "-m", "lib_py.loop", "--creator", "c", "--task", "t34",
+                               "--reviewer", "r", "--plan-file", str(ctl / "plan.md"), *argv],
+                              capture_output=True, text=True, env=env, cwd=str(ctl), timeout=300)
+    finally:
+        stop.set()
+        if t:
+            t.join()
+
+
+def _review_prompt(ctl: Path, n: int = 1) -> str:
+    return (ctl / ".mam" / f"review-prompt-{n}.md").read_text(encoding="utf-8")
+
+
+def _review_records(ctl: Path) -> list:
+    recs = [json.loads(p.read_text()) for p in (ctl / ".mam" / "jobs").glob("f*.json")]
+    return sorted((r for r in recs if r.get("role") == "Reviewer"), key=lambda r: r["created_ts"])
+
+
+def test_t3_the_loop_waits_for_the_sub_job_before_review(tmp_path):
+    ctl = _loop_ctl(tmp_path)
+    env = _loop_env(ctl, FAKE_WORKER="child")
+    jobs = ctl / ".mam" / "jobs"
+    done = {}
+
+    def finish_later(cid):
+        time.sleep(5)
+        done["ts"] = time.time()
+        _publish(env, jobs, cid, "completed", "figures drawn")
+
+    res = _run_loop(ctl, env, "--max-loop", "1", on_child=finish_later)
+    out = res.stdout + res.stderr
+    assert res.returncode == 0, out
+    cid = (ctl / ".mam" / "child-id").read_text().strip()
+    assert _record(jobs, cid)["parent_job"]  # registered by the real wrapper, under the creator job
+    assert "waiting for 1 sub-job(s)" in res.stdout
+    # the loop registered the review only after the sub-job was completed
+    assert _review_records(ctl)[0]["created_ts"] > done["ts"]
+    prompt = _review_prompt(ctl)
+    assert "[하위 위임 잡]" in prompt
+    assert re.search(rf"\| {cid} \| herdr:img \| Worker \| completed \| figures drawn \| 1 \|", prompt), prompt
+    assert "열린 0, 미확인 종결 0, 실패 0, 완료 1." in prompt
+    assert "100% PASS" in res.stdout
+
+
+def test_t4_an_open_sub_job_is_evidence_and_the_review_blocks(tmp_path):
+    ctl = _loop_ctl(tmp_path)
+    env = _loop_env(ctl, FAKE_WORKER="child", FAKE_REVIEW="rule", MAM_CHILD_WAIT_S="3")
+    res = _run_loop(ctl, env, "--max-loop", "1")
+    out = res.stdout + res.stderr
+    assert res.returncode == 1, out
+    assert "with 1 open; reviewers see them as OPEN" in res.stdout
+    cid = (ctl / ".mam" / "child-id").read_text().strip()
+    prompt = _review_prompt(ctl)
+    assert re.search(rf"\| {cid} \| .* \| OPEN \|", prompt) and "열린 1," in prompt
+    assert "100% PASS" not in res.stdout
+    # the success pair is T3: the same harness and rule pass once the child completed
+
+
+def test_t5_a_failed_sub_job_reaches_the_review_and_blocks_it(tmp_path):
+    ctl = _loop_ctl(tmp_path)
+    env = _loop_env(ctl, FAKE_WORKER="child", FAKE_REVIEW="rule")
+    jobs = ctl / ".mam" / "jobs"
+    res = _run_loop(ctl, env, "--max-loop", "1",
+                    on_child=lambda cid: _publish(env, jobs, cid, "error", "simulated"))
+    out = res.stdout + res.stderr
+    assert res.returncode == 1, out
+    assert "Requesting code review" in res.stdout  # a failed child does not stop the loop
+    cid = (ctl / ".mam" / "child-id").read_text().strip()
+    prompt = _review_prompt(ctl)
+    assert re.search(rf"\| {cid} \| .* \| error \| simulated \|", prompt), prompt
+    assert "실패 1," in prompt
+    assert "100% PASS" not in res.stdout
+
+
+@pytest.mark.parametrize("late_write", [True, False])
+def test_t5b_a_deadline_closed_sub_job_is_unconfirmed_and_a_late_write_voids_the_round(tmp_path, late_write):
+    ctl = _loop_ctl(tmp_path)
+    extra = {"FAKE_WORKER": "child", "FAKE_REVIEW": "pass"}
+    if late_write:
+        extra["FAKE_LATE_WRITE"] = "1"
+    env = _loop_env(ctl, **extra)
+    jobs = ctl / ".mam" / "jobs"
+    res = _run_loop(ctl, env, "--max-loop", "1", on_child=lambda cid: _deadline_close(env, jobs, cid))
+    out = res.stdout + res.stderr
+    cid = (ctl / ".mam" / "child-id").read_text().strip()
+    assert _record(jobs, cid)["status"] == "error"
+    prompt = _review_prompt(ctl)
+    assert re.search(rf"\| {cid} \| .* \| CLOSED-UNCONFIRMED \| deadline_timeout \|", prompt), prompt
+    assert "its agent may still be writing" in res.stdout
+    if late_write:
+        assert res.returncode == 1, out
+        assert "source changed during review" in res.stdout
+        assert "100% PASS" not in res.stdout
+    else:  # the guard reacts to a source change only
+        assert res.returncode == 0, out
+        assert "source changed" not in out
+        assert "100% PASS" in res.stdout
+
+
+def test_t6_an_unattributed_open_job_is_shown_and_waited_for_only_on_request(tmp_path):
+    ctl = _loop_ctl(tmp_path)
+    env = _loop_env(ctl, FAKE_WORKER="stray")
+    res = _run_loop(ctl, env, "--max-loop", "1")
+    assert res.returncode == 0, res.stdout + res.stderr
+    uid = (ctl / ".mam" / "child-id").read_text().strip()
+    assert "sub-job(s) of" not in res.stdout  # nothing to wait for by default
+    prompt = _review_prompt(ctl)
+    assert "[하위 위임 잡] 없음" in prompt
+    assert re.search(rf"\[귀속되지 않은 열린 잡\] .*: {uid}\(herdr:img, pending\)", prompt), prompt
+
+    ctl2 = _loop_ctl(tmp_path / "strict")
+    res2 = _run_loop(ctl2, _loop_env(ctl2, FAKE_WORKER="stray", MAM_CHILD_WAIT_S="3"),
+                     "--max-loop", "1", "--wait-open-jobs")
+    uid2 = (ctl2 / ".mam" / "child-id").read_text().strip()
+    assert f"{uid2}(herdr:img, pending)" in res2.stdout and "waiting for 1 sub-job(s)" in res2.stdout
+    assert "ended after 3s" in res2.stdout
+
+
+def test_t8_the_stale_review_guard_without_worktree_or_base(tmp_path):
+    ctl = _loop_ctl(tmp_path)
+    res = _run_loop(ctl, _loop_env(ctl, FAKE_LATE_WRITE="1"), "--max-loop", "2")
+    out = res.stdout + res.stderr
+    assert res.returncode == 0, out
+    assert res.stdout.count("approvals discarded, re-reviewing") == 1
+    assert len(_review_records(ctl)) == 2
+    assert "100% PASS" in res.stdout
+    # the control plane inside the source (.mam: jobs, logs, checkpoint) is not a change
+    res_quiet = _run_loop(ctl, _loop_env(ctl), "--max-loop", "1")
+    assert res_quiet.returncode == 0 and "source changed" not in res_quiet.stdout
+
+    # no repository: no fingerprint, the guard is off and says so; behaviour as before
+    plain = _loop_ctl(tmp_path / "plain", git=False)
+    res_plain = _run_loop(plain, _loop_env(plain, FAKE_LATE_WRITE="1"), "--max-loop", "1")
+    assert res_plain.returncode == 0, res_plain.stdout + res_plain.stderr
+    assert "the stale-review guard is off for this run" in res_plain.stdout
+    assert "100% PASS" in res_plain.stdout