.agents/skills/lib.sh

@@ -2381,6 +2381,23 @@ delegate_wait_started() {
   done
 }
 
+# delegate_wait_terminal <job_id> <timeout_s>
+# Issue #50: prints how the job ended - completed|error|cancelled - or
+# `timeout` when it has not ended after <timeout_s>, or `missing` when its
+# record is gone. The decision is lib_py.delegation.wrapper wait-terminal.
+delegate_wait_terminal() {
+  local job_id="$1" timeout_s="$2"
+  local reg_dir="${MAM_JOBS_DIR:-${WORKSPACE_ROOT:-$PWD}/.mam/jobs}"
+  PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" "$(_delegate_py_bin)" -m lib_py.delegation.wrapper wait-terminal \
+      --job "$job_id" --registry-dir "$reg_dir" --timeout "$timeout_s" --watch-pid "$$"
+}
+
+# delegate_onboard_exit <status>
+# Issue #50: create's exit code for an onboarding status (0, 44 or 45).
+delegate_onboard_exit() {
+  PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}" "$(_delegate_py_bin)" -m lib_py.delegation.wrapper onboard-exit "$1"
+}
+
 # ensure_subscriber_daemon <job_id> [workdir]
 # Start the monitor subscriber for this workspace unless one is already running.
 # Prints the PID(s) on stdout, exactly as start_watchdog always did.

.agents/skills/lib_py/delegation/wrapper.py

@@ -18,6 +18,12 @@ no answer) cannot pass for "no". The wrapper uses --print.
   finalize-begin / finalize-end ...          finalize_unfinished, split around the one
                                              herdr diagnostic probe bash still runs
 
+Issue #50 (create --onboard waits for the onboarding to end):
+  wait-terminal --job J --registry-dir R --timeout T [--watch-pid P]
+                                             prints the job's terminal status, or
+                                             `timeout` / `missing`
+  onboard-exit <status>                      create's exit code for it: 0, 44, 45
+
 finalize-end answers on fd 3 (stdout when fd 3 is closed): its stdout carries
 registry.py's close output to the wrapper's stdout, as before. It runs as a
 child of the wrapper and must not outlive it (review R1): with --watch-pid it
@@ -48,6 +54,10 @@ SUB_RC_COMPLETED, SUB_RC_ERROR, SUB_RC_NO_EVENT, SUB_RC_BROKER_UNAVAILABLE, SUB_
 
 TERMINAL = ("completed", "error", "cancelled")
 EXIT_CODES = {"completed": 0, "error": 1, "timeout": 2, "broker_unavailable": 3, "cancelled": 5}
+# Issue #50: create --onboard's exit code for how the onboarding job ended.
+# 44 = the agent ended it with error (or it was cancelled), 45 = it did not end
+# within MAM_ONBOARD_WAIT_S (or its record is gone). The session is kept either way.
+ONBOARD_EXIT_CODES = {"completed": 0, "error": 44, "cancelled": 44, "timeout": 45, "missing": 45}
 
 
 def _now() -> int:
@@ -169,6 +179,30 @@ def _tail(path: str, n: int) -> List[str]:
         return fh.read().splitlines()[-n:]
 
 
+# ---------------------------------------------------------------------------
+# Issue #50 A: create --onboard waits for the onboarding job to end
+# ---------------------------------------------------------------------------
+
+def onboard_exit(status: str) -> int:
+    return ONBOARD_EXIT_CODES.get(status, 45)
+
+
+def wait_terminal(a: argparse.Namespace) -> str:
+    """The job's terminal status once it has one; `timeout` after --timeout s,
+    `missing` when the record is gone. Reads the disk every second."""
+    deadline = _now() + a.timeout
+    record = os.path.join(a.registry_dir, f"{a.job}.json")
+    while True:
+        disk = disk_status(a.registry_dir, a.job)
+        if disk in TERMINAL:
+            return disk
+        if not os.path.isfile(record):
+            return "missing"
+        if _now() >= deadline:
+            return "timeout"
+        _sleep(a, 1)
+
+
 def finalize_begin(a: argparse.Namespace) -> str:
     """`keep` (FINAL_JOB_STATUS untouched), `done <final>`, or
     `go|probe <final> <evidence_until> <deadline>`."""
@@ -307,6 +341,12 @@ def _parser() -> argparse.ArgumentParser:
     s.add_argument("session")
     s.add_argument("agent")
     s.add_argument("--print", action="store_true", help="print yes/no and exit 0")
+    s = sub.add_parser("wait-terminal")
+    s.add_argument("--job", required=True)
+    s.add_argument("--registry-dir", required=True)
+    s.add_argument("--timeout", type=int, required=True)
+    s.add_argument("--watch-pid", type=int, default=None, help="the caller's pid; gone -> stop waiting")
+    sub.add_parser("onboard-exit").add_argument("status")
     for name in ("finalize-begin", "finalize-end"):
         s = sub.add_parser(name)
         s.add_argument("--job", required=True)
@@ -353,6 +393,13 @@ def main(argv: Optional[List[str]] = None) -> int:
         return _yes_no(stall_watch(a.session, a.agent), a.print)
     elif a.cmd == "finalize-begin":
         print(finalize_begin(a))
+    elif a.cmd == "wait-terminal":
+        try:
+            print(wait_terminal(a))
+        except OwnerGone:
+            print(f"wait-terminal: caller pid {a.watch_pid} is gone; stopped waiting on job {a.job}", file=sys.stderr)
+    elif a.cmd == "onboard-exit":
+        print(onboard_exit(a.status))
     else:
         try:
             _answer(finalize_end(a))

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

@@ -91,7 +91,12 @@ The bootstrapped server receives a **sanitized copy of the caller's environment*
    this script applies to a TUI that never signalled ready). Re-send with
    `multi-agent-mux-delegate-job submit` once the agent is up; the prompt is
    never re-injected automatically. `MAM_ONBOARD_ACK_S` overrides how long that
-   wait is — distinct from the wrapper's `MAM_INJECT_ACK_GRACE_S`.
+   wait is — distinct from the wrapper's `MAM_INJECT_ACK_GRACE_S`. After the
+   handshake the script waits for the onboarding job to **end** (Issue #50,
+   `MAM_ONBOARD_WAIT_S`, default 600 s) and prints `onboarding completed: job <id>
+   (<n>s)`; an onboarding that ends with `error` exits 44 and one that does not
+   end in time exits 45, both keeping the session, with
+   `last_visible_status: onboarding-<status>` on the row.
 
    **Start-up dialogs** are answered for every agent, not only claude (#24). The
    blocking-modal signatures and their accept keys live in each agent adapter
@@ -171,6 +176,8 @@ bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace
 | `--auto-trust` / `--no-auto-trust` | Answer a start-up directory-trust dialog or leave it to a human (`MAM_AUTO_TRUST`; default: answer) |
 | `--isolate` / `--no-isolate` | Legacy, no-op |
 
+`MAM_ONBOARD_WAIT_S` (default 600): how long `--onboard` waits for the onboarding job to end after the `started` handshake.
+
 | Exit | Meaning |
 |---|---|
 | 0 | Created; or `--dry-run` |
@@ -180,6 +187,8 @@ bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace
 | 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 |
 | 42 | The TUI never became ready and the process is gone, or it is alive and `MAM_KILL_ON_READY_TIMEOUT=1` (rolled back) |
 | 43 | The rollback could not kill the herdr session; it is still running |
+| 44 | The onboarding job ended with `error` (or was cancelled); the session is kept (Issue #50) |
+| 45 | The onboarding job did not end within `MAM_ONBOARD_WAIT_S`, or its record is gone; the session is kept |
 | other | A later step failed and its code is passed through. The EXIT trap (`cleanup_herdr_on_error`) rolls back the herdr session and closes the onboarding job as `cancelled`; if that kill fails, the exit is 43 instead |
 
 ## Registering the session in agent-sessions.yaml
@@ -201,7 +210,7 @@ bash .agents/skills/multi-agent-mux-create/scripts/worktree_prepare.sh \
 - `--creator-agent` creates the creator through this skill with the control root's binding and `MAM_NO_SUBSCRIBER_DAEMON=1`; the row's `pane.cwd` is the worktree.
 - Prints `BASE=<sha>`: record it **before** delegating the implementation, then review with `run_loop.sh --worktree <WT> --base "$BASE" --review-only`.
 - A submodule path that is not initialised yet but already holds files refuses `--submodules` up front (exit 3, nothing changed): the clone would fail on it and a rollback could not tell those files from its own.
-- Exit codes: 0 ok, 1 git / submodule / create failure, 2 usage or path rule, 3 refused to protect existing content (nothing changed).
+- Exit codes: 0 ok, 1 git / submodule / create failure, 2 usage or path rule, 3 refused to protect existing content (nothing changed); 44/45 are create's (onboarding error / timeout with `--onboard`; session and worktree kept).
 - create itself: a control-plane binding that cannot be computed is refused (exit 2) for a `--workspace` other than the control root and warned about for the control root; the immediate reconcile and the watchdog run the control root's code.
 
 ## Pitfalls

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

@@ -19,6 +19,8 @@
 #   4  = agent-sessions.yaml append failure
 #   42 = agent TUI never became ready and the process is gone
 #   43 = rollback could not kill the herdr session; it is still running (#23)
+#   44 = the onboarding job ended with error (or was cancelled); the session is kept (#50)
+#   45 = the onboarding job did not end within MAM_ONBOARD_WAIT_S; the session is kept (#50)
 set -euo pipefail
 
 _script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
@@ -316,6 +318,21 @@ for s in d.get('herdr_sessions', []):
 PYEOF
 }
 
+# _mark_row_note <note>
+# Issue #50: last_visible_status only. The row stays `running` with its
+# delegate_job_id: the session is alive and the job record is the evidence.
+_mark_row_note() {
+  local note="$1"
+  [ "${ROW_APPENDED:-0}" = "1" ] || return 0
+  atomic_dump_yaml "$AGENT_SESSIONS_YAML" SESSION_NAME="$SESSION_NAME" ROW_NOTE="$note" <<'PYEOF' || true
+name = os.environ['SESSION_NAME']
+for s in d.get('herdr_sessions', []):
+    if s.get('name') == name:
+        s['last_visible_status'] = os.environ['ROW_NOTE']
+        break
+PYEOF
+}
+
 # Trap for rolling back/cleaning up herdr session if script exits due to error
 cleanup_herdr_on_error() {
   local exit_code=$?
@@ -698,12 +715,38 @@ If you delegate any part of it with multi-agent-mux-delegate-job submit, add --p
     esac
     JOB_TERMINALIZED=1
   fi
+  # Issue #50: the handshake only said the agent saw the prompt. Wait for the
+  # onboarding itself to end; its result is this script's exit code, so the
+  # orchestrator learns it from create (MULTI_AGENT_RULES §6) instead of
+  # guessing from herdr's agent_status. A job marked `error` just above is
+  # terminal and returns at once.
+  ONBOARD_WAIT_S=$(mam_int_knob MAM_ONBOARD_WAIT_S 600 1)
+  ONBOARD_T0=$(date +%s)
+  ONBOARD_STATUS="$(delegate_wait_terminal "$DELEGATE_JOB_ID" "$ONBOARD_WAIT_S")"
+  ONBOARD_STATUS="${ONBOARD_STATUS:-missing}"
   # Trigger immediate priority reconcile cycle asynchronously
   # Issue #21 phase 2 (A8): the control root's reconcile/watchdog, never the
   # (unreviewed) copy in a worktree --workspace; identical paths by default.
   (bash "$SKILL_DIR/multi-agent-mux-monitor/scripts/reconcile.sh" --once >/dev/null 2>&1 &) || true
   WD_PID=$(start_watchdog "$DELEGATE_JOB_ID" "$WORKSPACE_ROOT")
   echo "watchdog PID: $WD_PID"
+  case "$ONBOARD_STATUS" in
+    completed)
+      echo "onboarding completed: job $DELEGATE_JOB_ID ($(( $(date +%s) - ONBOARD_T0 ))s)"
+      ;;
+    *)
+      # The session is kept, as for a missing handshake above: the row says
+      # what happened and the exit code tells the caller. The trap is cleared
+      # first - a non-zero exit must not roll a live session back.
+      _mark_row_note "onboarding-$ONBOARD_STATUS"
+      echo "ERROR: onboarding $ONBOARD_STATUS for '$SESSION_NAME': job $DELEGATE_JOB_ID; the session is kept" >&2
+      trap - EXIT
+      case "$(delegate_onboard_exit "$ONBOARD_STATUS")" in
+        44) exit 44 ;;
+        *) exit 45 ;;
+      esac
+      ;;
+  esac
 fi
 # Clear cleanup trap as registration was fully successful
 trap - EXIT

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

@@ -15,7 +15,8 @@
 # creator session registered in the control root's .mam -> summary with BASE=.
 #
 # Exit codes: 0 ok, 1 git / submodule / create failure, 2 usage or path rule,
-# 3 refused to protect existing content (nothing changed).
+# 3 refused to protect existing content (nothing changed); 44/45 are create's
+# (onboarding error / timeout; session and worktree kept, Issue #50).
 set -euo pipefail
 
 _script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
@@ -239,7 +240,11 @@ if [ -n "$CREATOR_AGENT" ]; then
   rc=0
   env "${env_add[@]}" bash "$SKILL_DIR/multi-agent-mux-create/scripts/create_session.sh" "${args[@]}" || rc=$?
   if [ "$rc" -ne 0 ]; then
-    echo "ERROR: create_session.sh failed (rc=$rc); the worktree is kept - remove it with worktree_remove.sh --path '$WT'" >&2
+    case "$rc" in
+      44) echo "ERROR: onboarding error for '$SESSION' (create_session.sh rc=44); session and worktree kept" >&2 ;;
+      45) echo "ERROR: onboarding timeout for '$SESSION' (create_session.sh rc=45); session and worktree kept" >&2 ;;
+      *) echo "ERROR: create_session.sh failed (rc=$rc); the worktree is kept - remove it with worktree_remove.sh --path '$WT'" >&2 ;;
+    esac
     exit "$rc"
   fi
 fi

tests/conftest.py

@@ -281,6 +281,12 @@ def mam_sandbox(tmp_path, monkeypatch, request):
     # Create-specific on purpose: MAM_INJECT_ACK_GRACE_S is the delegate-job
     # wrapper's knob and its own tests assert on the value they pass.
     monkeypatch.setenv("MAM_ONBOARD_ACK_S", "3")
+    # Issue #50: create now waits for the onboarding job to end as well. The
+    # mock herdr acts as the agent for create's onboarding prompt (it runs the
+    # publish commands the prompt names, through the real publish_event.py),
+    # so the wait ends at once; this cap is for a test that turns that off
+    # (MAM_MOCK_ONBOARD_HANDSHAKE=0 / started) and expects 44 / 45.
+    monkeypatch.setenv("MAM_ONBOARD_WAIT_S", "3")
     monkeypatch.delenv("HERDR_SESSION_NAME", raising=False)
     monkeypatch.delenv("HERDR_SERVER_NAME", raising=False)
     monkeypatch.delenv("HERDR_WORKSPACE_ID", raising=False)
@@ -356,6 +362,27 @@ if os.path.exists(state_file):
             pass
         time.sleep(0.02)
 
+def _onboard_handshake(text):
+    # Issue #50: create's onboarding prompt names the publish commands it
+    # expects the agent to run. This fake agent runs them - through the real
+    # publish_event.py, as a real agent would - so create's wait for the
+    # onboarding to end is satisfied. MAM_MOCK_ONBOARD_HANDSHAKE=0 publishes
+    # nothing (create exits 44: no started), `started` publishes only the
+    # first (create exits 45: never completed). The delegate-job wrapper's
+    # prompt has another shape and is never answered here.
+    import re
+    import subprocess
+    mode = os.environ.get("MAM_MOCK_ONBOARD_HANDSHAKE", "1")
+    if mode == "0" or "On start run:" not in text:
+        return
+    for label in ("On start run:", "On success run:"):
+        m = re.search(r"^" + re.escape(label) + r"\\s+(.+?)\\.?\\s*$", text, re.M)
+        if m:
+            subprocess.run(["bash", "-c", m.group(1)], stdout=subprocess.DEVNULL,
+                           stderr=subprocess.DEVNULL, timeout=120)
+        if mode == "started":
+            break
+
 # Record the command call
 state.setdefault("calls", []).append(sys.argv[1:])
 try:
@@ -659,6 +686,7 @@ elif cmd1 == "pane":
             sys.exit(1)
         pane_id = args[2]
         text = args[3]
+        _onboard_handshake(text)
         found = False
         for a_name, data in state.get("agents", {}).items():
             if data.get("pane_id") == pane_id or a_name == pane_id:
@@ -1147,6 +1175,7 @@ elif cmd1 == "agent":
         target_agent = agents[matched_k]
         target_agent["sent_text"] = target_agent.get("sent_text", "") + text
         target_agent["buffer"] = target_agent.get("buffer", "") + "\\n" + text + "\\n\\nesc to interrupt"
+        _onboard_handshake(text)
         if wait_flag:
             p_res = state.get("prompt_wait_result")
             if p_res is None:

tests/data/skill_code_blocks.json

@@ -60,8 +60,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 129,
-   "end": 147,
+   "start": 134,
+   "end": 152,
    "lang": "yaml",
    "sha": "2dd608d04ae0",
    "class": "c",
@@ -74,8 +74,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 153,
-   "end": 155,
+   "start": 158,
+   "end": 160,
    "lang": "bash",
    "sha": "613003708f19",
    "class": "c",
@@ -88,8 +88,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 193,
-   "end": 197,
+   "start": 202,
+   "end": 206,
    "lang": "bash",
    "sha": "38836d31bf38",
    "class": "c",
@@ -103,8 +103,8 @@
   },
   {
    "skill": "multi-agent-mux-create",
-   "start": 219,
-   "end": 241,
+   "start": 228,
+   "end": 250,
    "lang": "bash",
    "sha": "d90cfd2555fd",
    "class": "b",
@@ -612,10 +612,12 @@
     "4",
     "42",
     "43",
+    "44",
+    "45",
     "other"
    ],
    "passthrough": {
-    "4": "multi-agent-mux-create/scripts/create_session.sh:515"
+    "4": "multi-agent-mux-create/scripts/create_session.sh:532"
    }
   }
  },

tests/test_issue42_skill_blocks.py

@@ -218,7 +218,7 @@ def test_literal_exit_rule_on_base_scripts():
     and stop's `sys.exit(7)` are not counted."""
     assert literal_exit_codes("multi-agent-mux-resume/scripts/resume_session.sh") == {"0", "1", "2"}
     assert literal_exit_codes("multi-agent-mux-stop/scripts/stop_session.sh") == {"0", "1", "2", "3", "4"}
-    assert literal_exit_codes("multi-agent-mux-create/scripts/create_session.sh") == {"0", "1", "2", "3", "42", "43"}
+    assert literal_exit_codes("multi-agent-mux-create/scripts/create_session.sh") == {"0", "1", "2", "3", "42", "43", "44", "45"}
 
 
 # 5. Evidence exists.

tests/test_issue50_onboard.py

@@ -0,0 +1,201 @@
+"""Issue #50 A: `create --onboard` waits for the onboarding job to end.
+
+- U: the decisions (lib_py.delegation.wrapper wait-terminal / onboard-exit).
+- S: create_session.sh in the sandbox (mock herdr whose fake agent answers
+  the onboarding prompt through the real publish_event.py): completed -> 0
+  and a one-line result; error -> 44; never ended -> 45; the session is kept
+  and the row says why; worktree_prepare.sh passes 44/45 through.
+"""
+from __future__ import annotations
+
+import json
+import os
+import subprocess
+import sys
+import time
+from pathlib import Path
+
+import pytest
+import yaml
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+SKILLS = REPO_ROOT / ".agents" / "skills"
+if str(SKILLS) not in sys.path:
+    sys.path.insert(0, str(SKILLS))
+
+from lib_py.delegation import registry, wrapper as decide  # noqa: E402
+
+
+# ---------------------------------------------------------------------------
+# U - decisions
+# ---------------------------------------------------------------------------
+
+@pytest.mark.parametrize("status,code", [("completed", 0), ("error", 44), ("cancelled", 44),
+                                         ("timeout", 45), ("missing", 45), ("", 45), ("garbage", 45)])
+def test_u1_onboard_exit_table(status, code):
+    assert decide.onboard_exit(status) == code
+
+
+def _wait_terminal(reg, job, timeout=1, watch_pid=None):
+    cmd = [sys.executable, "-m", "lib_py.delegation.wrapper", "wait-terminal", "--job", job,
+           "--registry-dir", str(reg), "--timeout", str(timeout)]
+    if watch_pid is not None:
+        cmd += ["--watch-pid", str(watch_pid)]
+    return subprocess.run(cmd, capture_output=True, text=True, cwd=str(SKILLS),
+                          env=dict(os.environ, PYTHONPATH=str(SKILLS)), timeout=60)
+
+
+@pytest.mark.parametrize("terminal", ["completed", "error", "cancelled"])
+def test_u2_wait_terminal_prints_the_terminal_status_at_once(tmp_path, terminal):
+    jid = registry.register_job(prompt="onboarding", agent="claude-code", agent_session="herdr:s",
+                                registry_dir=str(tmp_path))
+    rec = json.loads((tmp_path / f"{jid}.json").read_text())
+    rec["status"] = terminal
+    (tmp_path / f"{jid}.json").write_text(json.dumps(rec))
+    t0 = time.time()
+    res = _wait_terminal(tmp_path, jid, timeout=30)
+    assert res.stdout.strip() == terminal and res.returncode == 0, res.stderr
+    assert time.time() - t0 < 10
+
+
+def test_u2b_wait_terminal_times_out_on_a_job_that_never_ends(tmp_path):
+    jid = registry.register_job(prompt="onboarding", agent="claude-code", agent_session="herdr:s",
+                                registry_dir=str(tmp_path))
+    res = _wait_terminal(tmp_path, jid, timeout=1)
+    assert res.stdout.strip() == "timeout", res.stdout + res.stderr
+
+
+def test_u2c_wait_terminal_reports_a_missing_record(tmp_path):
+    res = _wait_terminal(tmp_path, "nothere", timeout=30)
+    assert res.stdout.strip() == "missing"
+
+
+def test_u2d_wait_terminal_stops_with_its_caller(tmp_path):
+    jid = registry.register_job(prompt="onboarding", agent="claude-code", agent_session="herdr:s",
+                                registry_dir=str(tmp_path))
+    gone = subprocess.Popen(["true"])
+    gone.wait()
+    res = _wait_terminal(tmp_path, jid, timeout=30, watch_pid=gone.pid)
+    assert res.stdout == "" and "is gone" in res.stderr, res.stdout + res.stderr
+
+
+# ---------------------------------------------------------------------------
+# S - create_session.sh
+# ---------------------------------------------------------------------------
+
+def _create(sandbox, *extra, env=None):
+    script = sandbox / ".agents" / "skills" / "multi-agent-mux-create" / "scripts" / "create_session.sh"
+    cmd = ["bash", str(script), "--workspace", str(sandbox), "--agent", "claude", "--role", "creator",
+           "--session", "t50-creator-claude", "--onboard", *extra]
+    return subprocess.run(cmd, capture_output=True, text=True, cwd=str(sandbox), env=env, timeout=300)
+
+
+def _row(sandbox):
+    (row,) = yaml.safe_load((sandbox / ".mam" / "agent-sessions.yaml").read_text())["herdr_sessions"]
+    return row
+
+
+def _job(sandbox, jid):
+    return json.loads((sandbox / ".mam" / "jobs" / f"{jid}.json").read_text())
+
+
+def _mock_state(mock_herdr):
+    return json.loads(Path(mock_herdr).read_text())
+
+
+def test_s1_create_ends_with_the_onboarding_completed(mam_sandbox, mock_herdr, mock_agents):
+    res = _create(mam_sandbox)
+    assert res.returncode == 0, res.stdout + res.stderr
+    row = _row(mam_sandbox)
+    jid = row["delegate_job_id"]
+    assert f"onboarding completed: job {jid} (" in res.stdout, res.stdout
+    assert _job(mam_sandbox, jid)["status"] == "completed"
+    assert not str(row.get("last_visible_status", "")).startswith("onboarding-")
+    assert "onboarding" not in res.stderr.lower() or "WARNING" not in res.stderr
+
+
+def test_s2_an_onboarding_that_ends_with_error_exits_44_and_keeps_the_session(mam_sandbox, mock_herdr, mock_agents,
+                                                                               monkeypatch):
+    monkeypatch.setenv("MAM_MOCK_ONBOARD_HANDSHAKE", "0")   # no agent answer: no started -> error
+    res = _create(mam_sandbox)
+    assert res.returncode == 44, res.stdout + res.stderr
+    row = _row(mam_sandbox)
+    jid = row["delegate_job_id"]
+    assert jid, row
+    assert f"onboarding error for 't50-creator-claude': job {jid}; the session is kept" in res.stderr, res.stderr
+    assert _job(mam_sandbox, jid)["status"] == "error"
+    assert row["status"] == "running" and row["last_visible_status"] == "onboarding-error"
+    state = _mock_state(mock_herdr)
+    assert "t50-creator-claude" in state["agents"], "the session was rolled back"
+    assert not any(c[:1] == ["kill-session"] for c in state["calls"]), "the EXIT trap ran"
+    assert "onboarding completed" not in res.stdout
+
+
+def test_s3_an_onboarding_that_never_ends_exits_45_and_keeps_the_session(mam_sandbox, mock_herdr, mock_agents,
+                                                                          monkeypatch):
+    monkeypatch.setenv("MAM_MOCK_ONBOARD_HANDSHAKE", "started")   # started, never completed
+    t0 = time.time()
+    res = _create(mam_sandbox)
+    assert res.returncode == 45, res.stdout + res.stderr
+    row = _row(mam_sandbox)
+    jid = row["delegate_job_id"]
+    assert f"onboarding timeout for 't50-creator-claude': job {jid}; the session is kept" in res.stderr, res.stderr
+    assert _job(mam_sandbox, jid)["status"] == "running"
+    assert row["status"] == "running" and row["last_visible_status"] == "onboarding-timeout"
+    assert "t50-creator-claude" in _mock_state(mock_herdr)["agents"]
+    assert time.time() - t0 < 120, "MAM_ONBOARD_WAIT_S=3 bounds the wait in the sandbox"
+
+
+def test_s3b_the_wait_knob_follows_the_integer_rule(mam_sandbox, mock_herdr, mock_agents, monkeypatch):
+    monkeypatch.setenv("MAM_MOCK_ONBOARD_HANDSHAKE", "started")
+    monkeypatch.setenv("MAM_ONBOARD_WAIT_S", "0")   # below the floor of 1: the default (600) with a warning
+    monkeypatch.setenv("MAM_ONBOARD_ACK_S", "2")
+    script = mam_sandbox / ".agents" / "skills" / "multi-agent-mux-create" / "scripts" / "create_session.sh"
+    src = script.read_text()
+    # bound the run: the default would wait 600 s; cap the python wait by a stub of the knob call
+    assert 'ONBOARD_WAIT_S=$(mam_int_knob MAM_ONBOARD_WAIT_S 600 1)' in src
+    script.write_text(src.replace('ONBOARD_WAIT_S=$(mam_int_knob MAM_ONBOARD_WAIT_S 600 1)',
+                                  'ONBOARD_WAIT_S=$(mam_int_knob MAM_ONBOARD_WAIT_S 600 1); echo "KNOB=$ONBOARD_WAIT_S"; ONBOARD_WAIT_S=1'))
+    res = _create(mam_sandbox)
+    assert "KNOB=600" in res.stdout, res.stdout
+    assert res.returncode == 45
+
+
+def test_s4_the_source_clears_the_trap_before_the_named_exits():
+    src = (SKILLS / "multi-agent-mux-create" / "scripts" / "create_session.sh").read_text()
+    tail = src.split('_mark_row_note "onboarding-$ONBOARD_STATUS"')[1].split("esac")[0]
+    assert tail.index("trap - EXIT") < tail.index("exit 44") < tail.index("exit 45")
+    assert "delegate_wait_terminal" in src and "delegate_onboard_exit" in src
+
+
+# ---------------------------------------------------------------------------
+# S5 - worktree_prepare.sh passes 44 / 45 through with its own message
+# ---------------------------------------------------------------------------
+
+def _git(repo, *args):
+    subprocess.run(["git", "-c", "user.email=t@example.com", "-c", "user.name=t", *args],
+                   cwd=str(repo), check=True, capture_output=True, text=True)
+
+
+@pytest.mark.parametrize("rc,word", [(44, "error"), (45, "timeout")])
+def test_s5_worktree_prepare_passes_create_exit_through(mam_sandbox, rc, word):
+    main = mam_sandbox
+    _git(main, "init", "-q")
+    (main / "README").write_text("x\n")
+    _git(main, "add", "README")
+    _git(main, "commit", "-q", "-m", "init")
+    stub = main / ".agents" / "skills" / "multi-agent-mux-create" / "scripts" / "create_session.sh"
+    stub.write_text(f'#!/usr/bin/env bash\necho "stub create: $*" >&2\nexit {rc}\n')
+    prep = main / ".agents" / "skills" / "multi-agent-mux-create" / "scripts" / "worktree_prepare.sh"
+    wt = main.parent / f"{main.name}-wt{rc}"
+    res = subprocess.run(["bash", str(prep), "--path", str(wt), "--branch", f"b-{rc}",
+                          "--creator-agent", "claude", "--onboard"],
+                         capture_output=True, text=True, cwd=str(main), timeout=300)
+    try:
+        assert res.returncode == rc, res.stdout + res.stderr
+        assert f"onboarding {word} for 'creator-claude-b-{rc}' (create_session.sh rc={rc}); session and worktree kept" in res.stderr, res.stderr
+        assert "worktree_remove.sh" not in res.stderr
+        assert "--onboard" in res.stderr and "stub create" in res.stderr
+        assert (wt / "README").exists(), "the worktree is kept"
+    finally:
+        subprocess.run(["git", "worktree", "remove", "--force", str(wt)], cwd=str(main), capture_output=True)