#!/usr/bin/env bash
# multi-agent-mux-delegate-job — user-facing orchestrator for the multi-agent-mux-delegate-job skill.
#
# Subcommands:
#   submit   register a job, start the subscriber FIRST, then run the agent,
#            then (optionally) run a validation script.
#   status   show one job record.
#   list     list all jobs.
#   verify   run a user-supplied --validate script against a job's artifacts.
#   wait     block until all running/pending jobs reach a terminal state.
#
# This is a reference wrapper: it shells out to the python scripts that live
# next to it. Copy it into your project and customise as needed. It never hard
# fails if `claude`/`codex`/`herdr` are missing — it prints what it would run.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

# Load local env file (.mam.env preferred, .env fallback) from workspace root or explicit MAM_ENV_FILE
REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
TARGET_ENV="${MAM_ENV_FILE:-}"
if [[ -z "$TARGET_ENV" ]]; then
  if [[ -f "$REPO_ROOT/.mam.env" ]]; then
    TARGET_ENV="$REPO_ROOT/.mam.env"
  elif [[ -f "$REPO_ROOT/.env" ]]; then
    TARGET_ENV="$REPO_ROOT/.env"
    echo "WARNING: Loading deprecated config file '$TARGET_ENV'. Please migrate to '.mam.env'." >&2
  elif [[ -f .mam.env ]]; then
    TARGET_ENV=".mam.env"
    echo "WARNING: Loading config from cwd relative path '$TARGET_ENV'." >&2
  elif [[ -f .env ]]; then
    TARGET_ENV=".env"
    echo "WARNING: Loading deprecated config from cwd relative path '$TARGET_ENV'. Please migrate to '.mam.env'." >&2
  fi
fi

# Issue #26: parsed by envfile.py (the Python loader's rules; environment wins),
# never sourced. Values come back as shlex-quoted exports over the pipe.
if [[ -n "$TARGET_ENV" && -f "$TARGET_ENV" ]]; then
  _env_exports="$("${DELEGATE_JOB_PYTHON:-python3}" -I "$SCRIPT_DIR/../lib_py/delegation/envfile.py" --shell "$TARGET_ENV")" \
    || { echo "ERROR: cannot read $TARGET_ENV" >&2; exit 1; }
  eval "$_env_exports"; unset _env_exports
fi

# Source EARLY (before any herdr usage in run_agent) — this is what turns
# plain `herdr` into the tmux-compat shim (herdr() function) and provides
# resolve_herdr_session/send_keys_safe. Sourcing it late meant the
# has-session pre-flight check below used to hit the real herdr binary with
# a nonexistent subcommand and always fail.
source "$SCRIPT_DIR/../lib.sh"

# Pick an interpreter: prefer a project .venv, else python3.
pick_python() {
  local py_bin
  if [[ -n "${DELEGATE_JOB_PYTHON:-}" ]]; then
    py_bin="$DELEGATE_JOB_PYTHON"
  elif [[ -n "${AGENT_PYTHON_BIN:-}" ]] && [[ -x "$AGENT_PYTHON_BIN" ]]; then
    py_bin="$AGENT_PYTHON_BIN"
  elif [[ -x "${WORKDIR:-.}/.venv/bin/python" ]]; then
    py_bin="${WORKDIR}/.venv/bin/python"
  elif [[ -x ".venv/bin/python" ]]; then
    py_bin="$(pwd)/.venv/bin/python"
  else
    py_bin="python3"
  fi
  if ! "$py_bin" -c "import paho.mqtt" 2>/dev/null; then
    echo "ERROR: paho-mqtt package is missing for $py_bin." >&2
    echo "       Please create a virtual environment and install it:" >&2
    echo "       python3 -m venv .venv && .venv/bin/pip install -r \"$SCRIPT_DIR/requirements.txt\"" >&2
    exit 1
  fi
  echo "$py_bin"
}

REGISTRY_DIR_DEFAULT="${MAM_JOBS_DIR:-.mam/jobs}"

# Issue #21: the injected brief path, the start/success/error commands and the
# Output Report Path must work from any cwd - a creator in a git worktree runs
# them from there. Called right after `cd "$WORKDIR"`, so a relative registry
# still resolves against WORKDIR, as before.
_abs_registry_dir() {
  mkdir -p "$REGISTRY_DIR"
  REGISTRY_DIR="$(cd -P "$REGISTRY_DIR" && pwd -P)"
  export SKS_REGISTRY_DIR="$REGISTRY_DIR"
}

# The audit-log root this wrapper's own subscriber resolves (same resolver),
# pinned into the injected commands so an agent publishing from another cwd
# does not fall back to <cwd>/.mam/delegate_job_logs.
_logs_dir_abs() {
  "$PY" -c 'import os, sys; sys.path.insert(0, sys.argv[1]); from lib_py.delegation.mqtt_common import get_logs_dir; print(os.path.abspath(get_logs_dir()))' "$SCRIPT_DIR/.."
}

# _pub_cmd <extra...>: the publish command as one shell-quoted string.
_pub_cmd() {
  local s
  s="$(
    if [ -n "${LOGS_DIR_ABS:-}" ]; then printf 'DELEGATE_JOB_LOGS_DIR=%q ' "$LOGS_DIR_ABS"; fi
    printf '%q ' "$PY" "$SCRIPT_DIR/scripts/publish_event.py" --registry-dir "$REGISTRY_DIR" --job "$JOB_ID" "$@"
  )"
  printf '%s' "${s% }"
}

# _instructions <pub> [iteration]: the prompt injected into the agent (direct
# and loop jobs share it; test18 pins parts of this wording, so Issue #34's
# sub-delegation sentence goes at the end).
_instructions() {
  local pub="$1" iter="${2:-}" brief="$REGISTRY_DIR/$JOB_ID/brief.md"
  printf 'Your job_id is "%s". Detailed task requirements, instructions, and target output paths%s are documented in the task brief file at: %s. Please READ and follow %s to complete your work. Commands: start='"'"'%s --event started --heartbeat %s'"'"' (run it FIRST, within %s s; it also starts an automatic heartbeat timer), success='"'"'%s --event completed --detail <summary>'"'"', error='"'"'%s --event error --detail <reason>'"'"'. If you delegate any part of this work with multi-agent-mux-delegate-job submit, add --parent-job %s so the orchestrator waits for it.' \
    "$JOB_ID" "${iter:+ for iteration $iter}" "$brief" "$brief" "$pub" "$HEARTBEAT_SEC" "$ACK_TIMEOUT" "$pub" "$pub" "$JOB_ID"
}

usage() {
  cat <<'EOF'
multi-agent-mux-delegate-job <command> [options]

  submit  --agent <name> (--prompt <text> | --prompt-file <path>) [--workdir <dir>] [--agent-session <label>]
          [--timeout <sec> (default: $MAM_JOB_TIMEOUT_S or 3600)] [--idle-timeout <sec>] [--validate <script>]
          [--heartbeat <sec>] [--heartbeat-misses <count>] [--ack-timeout <sec>]
          [--registry-dir <dir>] [--dry-run] [--role <role_name>]
          [--type <direct|loop|discuss>] [--reviewer <reviewer_agent>]
          [--reviewer-session <reviewer_session>] [--max-iterations <count>]
          [--counterpart-role <role_name>] [--strict-role-check] [--parent-job <id>]
          # --parent-job names the job this one is delegated from, so a loop
          # waiting on that job waits for this one too (Issue #34). It must
          # exist in the registry. Default: $MAM_JOB_ID (set by the remote
          # runner), ignored with a warning when the registry lacks it.
          # --prompt-file passes the prompt by file: one argv string is capped
          # at 131,072 bytes on Linux (Issue #36). The file is read, not kept.
          # --agent-session herdr:<name> injects into a local herdr pane;
          # --agent-session remote:<name> dispatches over the broker (Issue #18).
          # Liveness contract: the agent heartbeats every --heartbeat N s
          # (default 30, automatic), the job is unresponsive after
          # --heartbeat-misses K x N s (default 4 x 30 = 120; --idle-timeout
          # overrides), `started` must arrive within --ack-timeout T s (180).
  status  --job <id> [--registry-dir <dir>]
  list    [--registry-dir <dir>]
  verify  --job <id> --validate <script> [--registry-dir <dir>]
  wait    [--job <id>] [--timeout <sec>] [--registry-dir <dir>]
  logs    <job_id> | --list      # persistent audit log (delegate_job_logs/)
EOF
}

# ---- arg parsing helpers --------------------------------------------------
AGENT="claude-code"; PROMPT=""; PROMPT_FILE=""; WORKDIR="$(pwd)"; AGENT_SESSION="herdr:claude"
TIMEOUT=3600; IDLE_TIMEOUT=""; VALIDATE=""; DRY_RUN=0
# job_subscriber.py exit codes (its RC_* constants; a test keeps the two equal).
SUB_RC_COMPLETED=0; SUB_RC_ERROR=1; SUB_RC_NO_EVENT=2; SUB_RC_BROKER_UNAVAILABLE=3; SUB_RC_WALL_CLOCK=4
# Issue #33: the job budget falls back to $MAM_JOB_TIMEOUT_S (--timeout > env > 3600).
if [[ -n "${MAM_JOB_TIMEOUT_S:-}" ]]; then
  if [[ "$MAM_JOB_TIMEOUT_S" =~ ^[0-9]+$ && "$MAM_JOB_TIMEOUT_S" -gt 0 ]]; then
    TIMEOUT="$MAM_JOB_TIMEOUT_S"
  else
    echo "WARNING: MAM_JOB_TIMEOUT_S=$MAM_JOB_TIMEOUT_S ignored (not a positive integer); using 3600" >&2
  fi
fi
# Issue #18 liveness contract (N / K / T). An unset --idle-timeout derives K x N.
HEARTBEAT_SEC="${MAM_HEARTBEAT_SEC:-30}"; HEARTBEAT_MISSES="${MAM_HEARTBEAT_MISSES:-4}"; ACK_TIMEOUT="${MAM_ACK_TIMEOUT_S:-180}"
JOB_ID=""; REGISTRY_DIR="$REGISTRY_DIR_DEFAULT"; DELEGATE_ROLE="Worker"
TYPE="direct"; REVIEWER="hermes"; REVIEWER_SESSION="herdr:hermes"; MAX_ITERATIONS=5
DEFAULT_COUNTERPART_ROLE="Reviewer"
COUNTERPART_ROLE="$DEFAULT_COUNTERPART_ROLE"
STRICT_ROLE_CHECK=0
ROLE_ALIASES_JSON='{"worker": ["worker", "creator"], "planner": ["planner"], "reviewer": ["reviewer"]}'
COUNTERPART_ROLE_EXPLICIT=0
PARENT_JOB=""

parse_opts() {
  while [[ $# -gt 0 ]]; do
    case "$1" in
      --agent) AGENT="$2"; shift 2;;
      --prompt) PROMPT="$2"; shift 2;;
      --prompt-file) PROMPT_FILE="$2"; shift 2;;
      --workdir) WORKDIR="$2"; shift 2;;
      --agent-session) AGENT_SESSION="$2"; shift 2;;
      --timeout) TIMEOUT="$2"; shift 2;;
      --idle-timeout) IDLE_TIMEOUT="$2"; shift 2;;
      --heartbeat) HEARTBEAT_SEC="$2"; shift 2;;
      --heartbeat-misses) HEARTBEAT_MISSES="$2"; shift 2;;
      --ack-timeout) ACK_TIMEOUT="$2"; shift 2;;
      --validate) VALIDATE="$2"; shift 2;;
      --job) JOB_ID="$2"; shift 2;;
      --registry-dir) REGISTRY_DIR="$2"; shift 2;;
      --dry-run) DRY_RUN=1; shift;;
      --role) DELEGATE_ROLE="$2"; shift 2;;
      --type) TYPE="$2"; shift 2;;
      --reviewer) REVIEWER="$2"; shift 2;;
      --reviewer-session) REVIEWER_SESSION="$2"; shift 2;;
      --max-iterations) MAX_ITERATIONS="$2"; shift 2;;
      --counterpart-role) COUNTERPART_ROLE="$2"; COUNTERPART_ROLE_EXPLICIT=1; shift 2;;
      --strict-role-check) STRICT_ROLE_CHECK=1; shift;;
      --parent-job) PARENT_JOB="$2"; shift 2;;
      *) echo "unknown option: $1" >&2; usage; exit 1;;
    esac
  done
  [ -n "$IDLE_TIMEOUT" ] || IDLE_TIMEOUT=$(( HEARTBEAT_SEC * HEARTBEAT_MISSES ))
  # lib.sh's send_keys_safe reads the job's own `started` from this registry.
  export SKS_REGISTRY_DIR="$REGISTRY_DIR"
}

# Issue #18: `remote:<name>` sessions get the prompt over the broker, not a pane.
_is_remote() { case "${1:-}" in remote:*) return 0;; *) return 1;; esac; }

_to_lower() {
  printf '%s' "$1" | tr '[:upper:]' '[:lower:]'
}

cmd_submit() {
  parse_opts "$@"
  if [[ -n "$PROMPT_FILE" ]]; then
    [[ -z "$PROMPT" ]] || { echo "submit takes --prompt or --prompt-file, not both" >&2; exit 1; }
    [[ "$PROMPT_FILE" == /* ]] || PROMPT_FILE="$(pwd)/$PROMPT_FILE"
    [[ -f "$PROMPT_FILE" && -r "$PROMPT_FILE" ]] || { echo "submit: cannot read --prompt-file $PROMPT_FILE" >&2; exit 1; }
    [[ -s "$PROMPT_FILE" ]] || { echo "submit: --prompt-file $PROMPT_FILE is empty" >&2; exit 1; }
    PROMPT="$(<"$PROMPT_FILE")"
  fi
  [[ -n "$PROMPT" || -n "$PROMPT_FILE" ]] || { echo "submit requires --prompt or --prompt-file" >&2; exit 1; }
  # Issue #36: the prompt reaches the registry by file when it came by file,
  # never as one argv string (capped at 131,072 bytes).
  local reg_prompt=(--prompt "$PROMPT")
  [[ -n "$PROMPT_FILE" ]] && reg_prompt=(--prompt-file "$PROMPT_FILE")
  PY="$(pick_python)"
  [[ "$PY" == */* && "$PY" != /* ]] && PY="$(pwd)/$PY"
  cd "$WORKDIR"
  _abs_registry_dir
  LOGS_DIR_ABS="$(_logs_dir_abs 2>/dev/null || true)"

  # Issue #34: an explicit --parent-job fails closed in the registry; the
  # $MAM_JOB_ID default may name a job of another host's registry (a remote
  # mirror), so it is only used when this registry has it.
  local reg_parent=()
  if [[ -n "$PARENT_JOB" ]]; then
    reg_parent=(--parent-job "$PARENT_JOB")
  elif [[ -n "${MAM_JOB_ID:-}" ]]; then
    if [[ -f "$REGISTRY_DIR/$MAM_JOB_ID.json" ]]; then
      PARENT_JOB="$MAM_JOB_ID"; reg_parent=(--parent-job "$PARENT_JOB")
    else
      echo "WARNING: MAM_JOB_ID=$MAM_JOB_ID is not in $REGISTRY_DIR; registering without a parent job" >&2
    fi
  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" \
      --timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
      --heartbeat-sec "$HEARTBEAT_SEC" --heartbeat-misses "$HEARTBEAT_MISSES" --ack-timeout "$ACK_TIMEOUT" \
      --transport "$(_is_remote "$AGENT_SESSION" && echo remote || echo herdr)" \
      --job-type "$TYPE" --reviewer "$REVIEWER" --reviewer-session "$REVIEWER_SESSION" \
      --max-iterations "$MAX_ITERATIONS" ${reg_parent[@]+"${reg_parent[@]}"})"
  echo "registered job: $JOB_ID"

  # 1-1) Provision job directory and write direct brief.md (MAM Job Restructuring)
  local job_dir="$REGISTRY_DIR/$JOB_ID"
  if [[ "$DRY_RUN" != "1" ]]; then
    mkdir -p "$job_dir"
    cat <<EOF > "$job_dir/brief.md"
# 📋 Brief: Job $JOB_ID Delegation

- **Job ID**: $JOB_ID
- **Target Agent**: $AGENT (session: $AGENT_SESSION)
- **Role**: $DELEGATE_ROLE
- **Timeout**: $TIMEOUT s (Idle: $IDLE_TIMEOUT s)
- **Liveness contract**: heartbeat every $HEARTBEAT_SEC s (automatic once you publish \`started --heartbeat $HEARTBEAT_SEC\`), unresponsive after $HEARTBEAT_MISSES missed heartbeats, \`started\` expected within $ACK_TIMEOUT s
- **Output Report Path**: $REGISTRY_DIR/$JOB_ID/$AGENT-reports/report-final.md
- **Parent for sub-delegations**: pass \`--parent-job $JOB_ID\` to \`multi-agent-mux-delegate-job submit\`

## 🔎 Task Description
$PROMPT
EOF
    echo "provisioned job directory: $job_dir"
  fi

  local START_TIME
  START_TIME=$(date +%s)

  if [[ "$TYPE" == "direct" ]]; then
    # 1) Read dispatch token and attempt id for this dispatch
    local _disp_tok=""
    local _attempt_id=""
    _disp_tok="$("$PY" -c "import json, os; p=os.path.join('$REGISTRY_DIR', '$JOB_ID.json'); print(json.load(open(p)).get('dispatch_token','') or '') if os.path.exists(p) else print('')" 2>/dev/null || true)"
    _attempt_id="$("$PY" -c "import json, os; p=os.path.join('$REGISTRY_DIR', '$JOB_ID.json'); print(json.load(open(p)).get('attempt_id','') or '') if os.path.exists(p) else print('')" 2>/dev/null || true)"
    local pub_extra=()
    [ -n "$_disp_tok" ] && pub_extra+=(--expect-dispatch-token "$_disp_tok")
    [ -n "$_attempt_id" ] && pub_extra+=(--attempt-id "$_attempt_id")
    local pub instructions
    pub="$(_pub_cmd ${pub_extra[@]+"${pub_extra[@]}"})"
    instructions="$(_instructions "$pub")"

    if [[ "$DRY_RUN" == "1" ]]; then
      run_agent "$JOB_ID" "$instructions"
      local logs_root_dry="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
      echo "$logs_root_dry/$JOB_ID"
      return 0
    fi

    # 1) Preflight (a remote session has no local pane to check: Issue #18)
    if ! _is_remote "$AGENT_SESSION" && ! preflight_agent "$JOB_ID" "$AGENT_SESSION" 0; then
      finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "preflight"
      local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
      echo "$logs_root/$JOB_ID"
      exit 5
    fi

    # 2) TUI idle handshake
    if [ "$AGENT" != "human" ] && ! _is_remote "$AGENT_SESSION"; then
      local idle_rc=0
      wait_for_agent_idle "$AGENT_SESSION" || idle_rc=$?
      export _SKS_IDLE_RC="$idle_rc"
      if [ $idle_rc -eq 1 ] || [ $idle_rc -eq 2 ]; then
        finalize_unfinished "$JOB_ID" "error" "$idle_rc" "idle_wait"
        local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
        echo "$logs_root/$JOB_ID"
        exit 5
      fi
    fi

    # 3) START THE SUBSCRIBER
    local logf="$REGISTRY_DIR/$JOB_ID.subscriber.out"
    # Before the first event the subscriber is bounded by the wall clock only:
    # delivery (T from the injection, which happens after the subscriber is
    # up and can take a while itself) is judged by _wait_started, and a failed
    # injection reaps the subscriber. From the first event on, K x N applies.
    local sub_extra_args=(--ack-timeout "$TIMEOUT")
    [ -n "$_disp_tok" ] && sub_extra_args+=(--expect-dispatch-token "$_disp_tok")
    _is_remote "$AGENT_SESSION" && sub_extra_args+=(--remote)
    "$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
        --job "$JOB_ID" --timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
        ${sub_extra_args[@]+"${sub_extra_args[@]}"} \
        >"$logf" 2>&1 &
    local sub_pid=$!
    echo "subscriber pid: $sub_pid (log: $logf)"
    # Wait for the subscriber to CONNACK + SUBSCRIBE (reactive handshake)
    local sub_ready=0
    for ((i = 0; i < 25; i++)); do
      if kill -0 "$sub_pid" 2>/dev/null; then
        if grep -q '^SUBSCRIBED ' "$logf" 2>/dev/null; then
          sub_ready=1
          break
        fi
      else
        local sub_exit=0
        wait "$sub_pid" 2>/dev/null || sub_exit=$?
        if [ $sub_exit -eq $SUB_RC_COMPLETED ] || [ $sub_exit -eq $SUB_RC_BROKER_UNAVAILABLE ]; then
          sub_ready=1
          break
        else
          echo "ERROR: subscriber died early (pid=$sub_pid, exit=$sub_exit, check $logf)" >&2
          local mapped_st
          mapped_st="$(_map_sub_rc "$sub_exit" "$JOB_ID")"
          finalize_unfinished "$JOB_ID" "$mapped_st" "$sub_exit" "subscriber"
          mapped_st="${FINAL_JOB_STATUS:-$mapped_st}"
          local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
          echo "$logs_root/$JOB_ID"
          if [ "${MAM_DELEGATE_FAIL_CLOSED:-1}" = "0" ]; then
            exit 0
          fi
          exit "$(_rc_for "$mapped_st")"
        fi
      fi
      sleep 0.2
    done
    if [ "$sub_ready" -ne 1 ]; then
      echo "WARNING: subscriber subscribe handshake timed out — falling back to proceed" >&2
    fi

    # 5) Deliver the prompt (herdr pane or remote dispatch) and wait for `started`
    if ! deliver_prompt "$JOB_ID" "$instructions" "$AGENT_SESSION" "$logf"; then
      reap_subscriber "$sub_pid"
      finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "inject"
      local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
      echo "$logs_root/$JOB_ID"
      exit 1
    fi
    start_stall_watch "$AGENT_SESSION" "$AGENT" "$_disp_tok" "$_attempt_id"

    # 6) optional validation hook
    if [[ -n "$VALIDATE" ]]; then
      echo "running validation: $VALIDATE"
      if JOB_ID="$JOB_ID" REGISTRY_DIR="$REGISTRY_DIR" bash "$VALIDATE"; then
        echo "validation: PASS"
      else
        local rc=$?
        echo "validation: FAIL (exit $rc)"
      fi
    fi

    local sub_rc=0
    wait "$sub_pid" || sub_rc=$?
    stop_stall_watch
    echo "subscriber output:"; cat "$logf" || true

    local job_status
    job_status="$(_map_sub_rc "$sub_rc" "$JOB_ID")"

    finalize_unfinished "$JOB_ID" "$job_status" "$sub_rc" "direct"
    job_status="${FINAL_JOB_STATUS:-$job_status}"

    # Last stdout line: the persistent audit-log dir for this job (see SKILL.md
    # "Audit Logs"). Callers can scrape `tail -n1` to find it.
    local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
    echo "$logs_root/$JOB_ID"
    if [ "${MAM_DELEGATE_FAIL_CLOSED:-1}" = "0" ]; then
      exit 0
    fi
    exit "$(_rc_for "$job_status")"
  else
    # Implement loop/discuss orchestrator
    local iteration=1
    local current_prompt="$PROMPT"
    local current_session="$AGENT_SESSION"
    local _phase="worker"
    local display_role="$DELEGATE_ROLE"
    local attempt=0
    local final_loop_rc=0

    if [[ "$DRY_RUN" == "1" ]]; then
      echo "[dry-run] orchestrator loop would start for job: $JOB_ID type: $TYPE"
      echo "worker session: $AGENT_SESSION, reviewer session: $REVIEWER_SESSION"
      local logs_root_dry="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
      echo "$logs_root_dry/$JOB_ID"
      return 0
    fi

    while true; do
      echo "=================================================="
      echo "Iteration $iteration - Role: $display_role"
      echo "Session: $current_session"
      echo "=================================================="

      # 1-1) Provision job directory and write iteration brief.md (MAM Job Restructuring)
      local job_dir="$REGISTRY_DIR/$JOB_ID"
      local clean_session="${current_session#herdr:}"
      mkdir -p "$job_dir"
      cat <<EOF > "$job_dir/brief.md"
# 📋 Brief: Job $JOB_ID Delegation (Iteration $iteration)
 
- **Job ID**: $JOB_ID
- **Target Agent/Session**: $current_session
- **Role**: $display_role
- **Iteration**: $iteration
- **Liveness contract**: heartbeat every $HEARTBEAT_SEC s (automatic once you publish \`started --heartbeat $HEARTBEAT_SEC\`), unresponsive after $HEARTBEAT_MISSES missed heartbeats, \`started\` expected within $ACK_TIMEOUT s
- **Output Report Path**: $REGISTRY_DIR/$JOB_ID/${clean_session}-reports/report-final.md
- **Parent for sub-delegations**: pass \`--parent-job $JOB_ID\` to \`multi-agent-mux-delegate-job submit\`
 
## 🔎 Task Description
$current_prompt
EOF
      # Issue #36: the registry gets the prompt by file, not as one argv string
      printf '%s' "$current_prompt" > "$job_dir/prompt.md"
      echo "provisioned iteration brief: $job_dir/brief.md"

      attempt=$((attempt + 1))

      local force_warn_only=0
      local cp_lower def_lower
      cp_lower=$(_to_lower "$COUNTERPART_ROLE")
      def_lower=$(_to_lower "$DEFAULT_COUNTERPART_ROLE")
      if [[ "$_phase" == "reviewer" && "$COUNTERPART_ROLE_EXPLICIT" -eq 1 \
            && "$cp_lower" != "$def_lower" ]]; then
        force_warn_only=1
      fi

      # Preflight (skipped for a remote session: Issue #18)
      if ! _is_remote "$current_session" && ! preflight_agent "$JOB_ID" "$current_session" "$force_warn_only"; then
        finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "preflight"
        local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
        echo "$logs_root/$JOB_ID"
        exit 5
      fi

      # Idle wait
      local cur_agent="$AGENT"
      [ "$_phase" = "reviewer" ] && cur_agent="$REVIEWER"
      if [ "$cur_agent" != "human" ] && ! _is_remote "$current_session"; then
        local idle_rc=0
        wait_for_agent_idle "$current_session" || idle_rc=$?
        export _SKS_IDLE_RC="$idle_rc"
        if [ $idle_rc -eq 1 ] || [ $idle_rc -eq 2 ]; then
          finalize_unfinished "$JOB_ID" "error" "$idle_rc" "idle_wait"
          local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
          echo "$logs_root/$JOB_ID"
          exit 5
        fi
      fi

      # Update job details in registry
      "$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" update \
          --job "$JOB_ID" \
          --agent-session "$current_session" \
          --prompt-file "$job_dir/prompt.md" \
          --iteration "$iteration" \
          --attempt-id "$attempt" \
          --role "$display_role" \
          --status "pending"

      local _disp_tok=""
      _disp_tok="$("$PY" -c "import json, os; p=os.path.join('$REGISTRY_DIR', '$JOB_ID.json'); print(json.load(open(p)).get('dispatch_token','') or '') if os.path.exists(p) else print('')" 2>/dev/null || true)"

      # Start subscriber
      local logf="$REGISTRY_DIR/${JOB_ID}.iter_${iteration}_${display_role}.subscriber.out"
      local loop_sub_args=(--attempt-id "$attempt" --ack-timeout "$TIMEOUT")
      [ -n "$_disp_tok" ] && loop_sub_args+=(--expect-dispatch-token "$_disp_tok")
      _is_remote "$current_session" && loop_sub_args+=(--remote)
      "$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
          --job "$JOB_ID" --timeout "$TIMEOUT" --idle-timeout "$IDLE_TIMEOUT" \
          "${loop_sub_args[@]}" \
          >"$logf" 2>&1 &
      local sub_pid=$!
      echo "subscriber pid: $sub_pid (log: $logf)"
      # Wait for the subscriber to CONNACK + SUBSCRIBE (reactive handshake)
      local sub_ready=0
      for ((i = 0; i < 25; i++)); do
        if kill -0 "$sub_pid" 2>/dev/null; then
          if grep -q '^SUBSCRIBED ' "$logf" 2>/dev/null; then
            sub_ready=1
            break
          fi
        else
          local sub_exit=0
          wait "$sub_pid" 2>/dev/null || sub_exit=$?
          if [ $sub_exit -eq $SUB_RC_COMPLETED ] || [ $sub_exit -eq $SUB_RC_BROKER_UNAVAILABLE ]; then
            sub_ready=1
            break
          else
            echo "ERROR: subscriber died early (pid=$sub_pid, exit=$sub_exit, check $logf)" >&2
            local mapped_st
            mapped_st="$(_map_sub_rc "$sub_exit" "$JOB_ID")"
            finalize_unfinished "$JOB_ID" "$mapped_st" "$sub_exit" "subscriber"
            mapped_st="${FINAL_JOB_STATUS:-$mapped_st}"
            local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
            echo "$logs_root/$JOB_ID"
            if [ "${MAM_DELEGATE_FAIL_CLOSED:-1}" = "0" ]; then
              exit 0
            fi
            exit "$(_rc_for "$mapped_st")"
          fi
        fi
        sleep 0.2
      done
      if [ "$sub_ready" -ne 1 ]; then
        echo "WARNING: subscriber subscribe handshake timed out — falling back to proceed" >&2
      fi

      # Format instruction block
      local loop_pub_extra=(--attempt-id "$attempt")
      [ -n "$_disp_tok" ] && loop_pub_extra+=(--expect-dispatch-token "$_disp_tok")
      local pub instructions
      pub="$(_pub_cmd "${loop_pub_extra[@]}")"
      instructions="$(_instructions "$pub" "$iteration")"

      # Trigger agent
      if ! deliver_prompt "$JOB_ID" "$instructions" "$current_session" "$logf"; then
        reap_subscriber "$sub_pid"
        finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "inject"
        local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
        echo "$logs_root/$JOB_ID"
        exit 1
      fi
      start_stall_watch "$current_session" "$cur_agent" "$_disp_tok" "$attempt"

      # Wait for subscriber
      local sub_rc=0
      wait "$sub_pid" || sub_rc=$?
      stop_stall_watch
      echo "subscriber output:"; cat "$logf" || true

      local job_status
      job_status="$(_map_sub_rc "$sub_rc" "$JOB_ID")"
      
      echo "Job role $display_role finished with status: $job_status"

      # Retrieve feedback from the last event
      local feedback
      feedback="$("$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" get-feedback --job "$JOB_ID")"
      echo "Feedback/Detail: $feedback"
      if [[ "$_phase" == "worker" ]]; then
        if [[ "$job_status" != "completed" ]]; then
          echo "Worker did not complete successfully (status: $job_status). Terminating workflow."
          finalize_unfinished "$JOB_ID" "$job_status" "$sub_rc" "worker" "$current_session"
          job_status="${FINAL_JOB_STATUS:-$job_status}"
          if [[ "$job_status" == "completed" ]]; then
            echo "Worker completed during grace period. Continuing to reviewer."
            feedback="$("$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" get-feedback --job "$JOB_ID")"
          else
            local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
            echo "$logs_root/$JOB_ID"
            if [ "${MAM_DELEGATE_FAIL_CLOSED:-1}" = "0" ]; then
              exit 0
            fi
            exit "$(_rc_for "$job_status")"
          fi
        fi

        # Worker completed successfully, now switch to reviewer
        _phase="reviewer"
        display_role="$COUNTERPART_ROLE"
        current_session="$REVIEWER_SESSION"
        # Build reviewer prompt based on type
        if [[ "$TYPE" == "loop" ]]; then
          current_prompt="Review the changes/artifacts generated for job $JOB_ID. Check if they meet the requirements. If correct, publish completed event with 'PASS'. If there are issues, publish error event with detailed feedback/nits. CRITICAL: When raising issues or giving a review, you MUST include the exact reason for the issue and a clear direction for improvement (문제 제시에 대한 이유와 확실한 개선 방향을 반드시 포함해야 합니다)."
        elif [[ "$TYPE" == "discuss" ]]; then
          current_prompt="Read draft/documents generated for job $JOB_ID. Review the feasibility and content. Write your feedback/objections. If you agree with the plan, reply with 'AGREE'."
        fi
      else
        if [[ "$job_status" != "completed" ]]; then
          echo "Reviewer did not complete successfully (status: $job_status). Terminating workflow."
          finalize_unfinished "$JOB_ID" "$job_status" "$sub_rc" "reviewer" "$current_session"
          job_status="${FINAL_JOB_STATUS:-$job_status}"
          if [[ "$job_status" == "completed" ]]; then
            echo "Reviewer completed during grace period. Continuing evaluation."
            feedback="$("$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" get-feedback --job "$JOB_ID")"
          else
            local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
            echo "$logs_root/$JOB_ID"
            if [ "${MAM_DELEGATE_FAIL_CLOSED:-1}" = "0" ]; then
              exit 0
            fi
            exit "$(_rc_for "$job_status")"
          fi
        fi

        # Reviewer finished. Check if pass/agree
        local success=0
        local fb_lower
        fb_lower=$(_to_lower "$feedback")
        if [[ "$TYPE" == "loop" ]]; then
          if [[ "$fb_lower" == *"pass"* ]]; then
            success=1
          fi
        elif [[ "$TYPE" == "discuss" ]]; then
          if [[ "$fb_lower" == *"agree"* ]]; then
            success=1
          fi
        fi

        if [[ "$success" == "1" ]]; then
          echo "Reviewer approved the work. Finalizing job as completed."
          "$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" status --job "$JOB_ID" --set "completed"
          final_loop_rc=0
          break
        else
          # Reviewer rejected/provided feedback. Increment & check max iterations
          if [[ $iteration -ge $MAX_ITERATIONS ]]; then
            echo "Max iterations ($MAX_ITERATIONS) reached without approval. Terminating workflow."
            "$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" status --job "$JOB_ID" --set "error"
            final_loop_rc=1
            break
          fi
          
          iteration=$((iteration + 1))
          _phase="worker"
          display_role="$DELEGATE_ROLE"
          current_session="$AGENT_SESSION"
          current_prompt="The reviewer provided the following feedback for job $JOB_ID: $feedback. Please modify the code/artifacts to address these comments. CRITICAL: As the Developer Team Leader, you must thoroughly review the suggested modifications, verify their validity, adopt/implement them if valid, and if you judge any recommendation to be invalid, do NOT implement it but instead explain your reasons clearly in your response and send it back to the reviewer (수정안을 최대한 꼼꼼히 검토하여 타당성을 검증하고, 타당하다면 수렴하여 수정을 진행하되, 타당하지 않다고 판단되는 부분이 있다면 그 이유를 명확히 밝혀 리뷰어에게 전달하십시오)."
        fi
      fi
    done

    # 4) optional validation hook
    if [[ -n "$VALIDATE" ]]; then
      echo "running validation: $VALIDATE"
      if JOB_ID="$JOB_ID" REGISTRY_DIR="$REGISTRY_DIR" bash "$VALIDATE"; then
        echo "validation: PASS"
      else
        local rc=$?
        echo "validation: FAIL (exit $rc)"
        final_loop_rc=$rc
      fi
    fi

    # Last stdout line: the persistent audit-log dir
    local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
    echo "$logs_root/$JOB_ID"
    exit "$final_loop_rc"
  fi
}

reap_subscriber() {
  if [ -n "${1:-}" ]; then
    kill "$1" 2>/dev/null || true
    wait "$1" 2>/dev/null || true
  fi
}

# Issue #30: a notify-only stall watcher for a job with a local herdr pane
# (lib_py.stall_watch decides; it never closes the job). A remote
# or human job has no pane to watch. Sets STALL_PID ("" when none started).
start_stall_watch() {
  local session="$1" agent="$2" tok="${3:-}" att="${4:-}"
  STALL_PID=""
  [ "${MAM_STALL_WATCH:-1}" = "0" ] && return 0
  if _is_remote "$session"; then
    echo "stall watch: remote job, no local pane - stall detection off" >&2; return 0
  fi
  if [ "$agent" = "human" ] || [ "${session#herdr:}" = "human" ]; then
    echo "stall watch: human job, no local pane - stall detection off" >&2; return 0
  fi
  local args=(--job "$JOB_ID" --registry-dir "$REGISTRY_DIR" --target "${session#herdr:}"
              --agent "$agent" --herdr-session "${HERDR_SESSION_NAME:-}" --watch-pid "$$")
  [ -n "$tok" ] && args+=(--expect-dispatch-token "$tok")
  [ -n "$att" ] && args+=(--attempt-id "$att")
  PYTHONPATH="$SCRIPT_DIR/..${PYTHONPATH:+:$PYTHONPATH}" "$PY" -m lib_py.stall_watch "${args[@]}" \
      >"$REGISTRY_DIR/$JOB_ID.stall.out" 2>&1 &
  STALL_PID=$!
  echo "stall watch pid: $STALL_PID (log: $REGISTRY_DIR/$JOB_ID.stall.out)"
}

# A watcher that already ended on its own with an error (herdr unavailable)
# is not left silent: its last lines go to this wrapper's stderr.
# The stop is KILL, not TERM: a TERM can be swallowed (it hung this wrapper in
# `wait`, PR #41 review N1), and a TERM budget in front of the job's close
# clock delayed deadline_timeout (round-2 review). The watcher holds nothing
# to flush - its TERM handler is a bare os._exit - so KILL loses nothing, and
# `wait` returns at once.
stop_stall_watch() {
  [ -n "${STALL_PID:-}" ] || return 0
  local rc=0
  if kill -0 "$STALL_PID" 2>/dev/null; then
    kill -9 "$STALL_PID" 2>/dev/null || true
    wait "$STALL_PID" 2>/dev/null || true
  else
    wait "$STALL_PID" 2>/dev/null || rc=$?
  fi
  if [ "$rc" -ne 0 ]; then
    echo "stall watch for $JOB_ID exited rc=$rc:" >&2
    tail -n 3 "$REGISTRY_DIR/$JOB_ID.stall.out" >&2 2>/dev/null || true
  fi
  STALL_PID=""
}

_disk_status() {
  local jid="$1"
  "$PY" -c "import json, os; p=os.path.join('$REGISTRY_DIR', '$jid.json'); print(json.load(open(p)).get('status','')) if os.path.exists(p) else print('')" 2>/dev/null || true
}

# ISSUE-18: delivery is confirmed by the protocol, not the screen. After the
# prompt was handed over (herdr accepted the submission, or the dispatch was
# published for a remote session) the job's own `started` must arrive within
# the ack timeout T. The evidence is lib.sh's delegate_started_recorded - the
# same predicate create_session's onboarding ack uses, so the two waits share
# one contract (ack-finding req. 2, review R1): the local publisher's line in
# events.log, or the subscriber's HMAC-verified, dispatch-attributed audit
# record of a `started` it received (a remote agent has no shared disk). The
# registry status is not evidence - a record leaves `pending` when another
# writer closes it (error, cancelled) or another dispatch claims it, none of
# which says this agent saw this prompt. No `started` within T is a delivery
# failure: fail closed, never re-inject (single-injection contract). A job
# that is already terminal is handled by the terminal logic after this, not
# turned into a success here.
_wait_started() {
  local job_id="$1" ack_s="${2:-$ACK_TIMEOUT}" sub_log="${3:-}" deadline wall
  # sub_log is retained for callers' signatures; the subscriber's evidence is
  # read from its audit record, which is attributable, not from its console.
  deadline=$(( $(date +%s) + ack_s ))
  # The ack wait never outlives this dispatch's wall clock (START_TIME + TIMEOUT).
  wall=$(( ${START_TIME:-$(date +%s)} + ${TIMEOUT:-3600} ))
  [ "$deadline" -gt "$wall" ] && deadline=$wall
  local budget=$(( deadline - $(date +%s) ))
  while :; do
    # publish_event records `started` locally before its wire publish and
    # before the status sync, so a slow broker cannot delay the acknowledgement.
    if MAM_JOBS_DIR="$REGISTRY_DIR" delegate_started_recorded "$job_id" "${_disp_tok:-}" "${LOGS_DIR_ABS:-}"; then
      echo "inject: job $job_id recorded 'started' in events.log; treating the prompt as delivered and continuing." >&2
      return 0
    fi
    if [ "$(date +%s)" -ge "$deadline" ]; then
      ACK_WAITED_S="$budget"
      return 1
    fi
    sleep 1
  done
}

# Legacy name retained for callers/tests of the ISSUE-14 guard.
_inject_acknowledged() { _wait_started "$1" "${MAM_INJECT_ACK_GRACE_S:-$ACK_TIMEOUT}" "${2:-}"; }

# ISSUE-14 / ISSUE-18: herdr's agent_status and the pane busy token describe
# the screen, not the protocol. They are no longer liveness *evidence* (a
# headless or remote agent shows neither, and a CLI update can change both
# silently); finalize_unfinished logs them as a diagnostic so an operator can
# tell "dead" from "silent" on the same host. Liveness itself is the contract:
# an event on disk or on the wire within K x N seconds.
_agent_still_working() {
  local sess="$1" target="$2"
  [ "$(_sks_agent_status "$sess" "$target")" = "working" ] && return 0
  _pane_tail "$sess" 8 2>/dev/null | grep -Fq "esc to interrupt"
}

# _within_deadline <deadline_epoch> <cmd...>
# Run a probe that can block (a herdr RPC, a pane capture) without letting it
# outlive a wall-clock deadline: once the clock reaches <deadline> the probe
# and its children are killed and the result is rc 124, i.e. "no evidence".
_within_deadline() {
  local deadline="$1" pid
  shift
  "$@" &
  pid=$!
  while kill -0 "$pid" 2>/dev/null; do
    if [ "$(date +%s)" -ge "$deadline" ]; then
      pkill -P "$pid" 2>/dev/null || true
      kill "$pid" 2>/dev/null || true
      wait "$pid" 2>/dev/null || true
      return 124
    fi
    sleep 0.1
  done
  wait "$pid"
}

# ISSUE-14: agent-agnostic liveness. publish_event appends every event to the
# job's on-disk events.log BEFORE its wire publish (record_local_event), so a
# `progress` heartbeat the subscriber never saw (it had already idled out, or
# the broker dropped it) is visible here the moment it is sent - a slow or
# failing broker no longer delays it by its publish retries. An agent running
# its tests in a background shell looks idle to herdr and shows no busy
# token, yet keeps heartbeating - this is the only evidence that covers that
# case.
_recent_disk_heartbeat() {
  local job_id="$1" window="$2" f="$REGISTRY_DIR/$job_id.events.log"
  [ -f "$f" ] || return 1
  "$PY" - "$f" "$window" <<'PYEOF'
import calendar, json, sys, time
path, window = sys.argv[1], float(sys.argv[2])
last = ""
with open(path) as fh:
    for line in fh:
        if line.strip():
            last = line
try:
    stamp = json.loads(last)["timestamp"]
    seen = calendar.timegm(time.strptime(stamp, "%Y-%m-%dT%H:%M:%SZ"))
except Exception:
    sys.exit(1)
sys.exit(0 if time.time() - seen <= window else 1)
PYEOF
}

_map_sub_rc() {
  local sub_rc="$1" job_id="$2"
  local job_status="running"
  if [[ $sub_rc -eq $SUB_RC_COMPLETED ]]; then
    job_status="completed"
  elif [[ $sub_rc -eq $SUB_RC_ERROR ]]; then
    job_status="error"
  elif [[ $sub_rc -eq $SUB_RC_BROKER_UNAVAILABLE ]]; then
    job_status="broker_unavailable"
    local disk_st
    disk_st="$(_disk_status "$job_id")"
    if [[ "$disk_st" == "completed" || "$disk_st" == "error" || "$disk_st" == "cancelled" ]]; then
      job_status="$disk_st"
    fi
  else
    job_status="timeout"  # SUB_RC_NO_EVENT, SUB_RC_WALL_CLOCK (and any other code)
  fi
  echo "$job_status"
}

_rc_for() {
  case "$1" in
    completed) echo 0 ;;
    error) echo 1 ;;
    timeout) echo 2 ;;
    broker_unavailable) echo 3 ;;
    cancelled) echo 5 ;;
    *) echo 1 ;;
  esac
}

finalize_unfinished() {
  local job_id="$1" job_status="$2" sub_rc="$3" phase="${4:-}" FINALIZE_CLOCK=""
  if [ "${MAM_DELEGATE_FAIL_CLOSED:-1}" = "0" ]; then
    return 0
  fi
  if [ "$job_status" = "completed" ]; then
    return 0
  fi
  # Issue #30: what the stall watcher saw goes with an unfinished job's close.
  if [ -s "$REGISTRY_DIR/$job_id.stall.out" ]; then
    echo "stall watch log for $job_id (last 3 lines):" >&2
    tail -n 3 "$REGISTRY_DIR/$job_id.stall.out" >&2 || true
  fi

  local cur_disk_st="$(_disk_status "$job_id")"
  if [ "$cur_disk_st" = "completed" ] || [ "$cur_disk_st" = "error" ] || [ "$cur_disk_st" = "cancelled" ]; then
    FINAL_JOB_STATUS="$cur_disk_st"
    [ "$cur_disk_st" = "completed" ] && return 0
  else
    FINAL_JOB_STATUS="$job_status"
  fi
  # broker_unavailable: re-observe the disk at 3 s intervals until this
  # dispatch's wall-clock deadline (START_TIME + TIMEOUT). The deadline is read
  # off the clock on every pass; summing the sleeps alone ignores the time the
  # disk probes themselves take and overruns TIMEOUT.
  if [ "$job_status" = "broker_unavailable" ]; then
    local deadline left disk_st
    deadline=$(( ${START_TIME:-$(date +%s)} + TIMEOUT ))
    while :; do
      left=$(( deadline - $(date +%s) ))
      [ "$left" -le 0 ] && break
      [ "$left" -gt 3 ] && left=3
      sleep "$left"
      disk_st="$(_disk_status "$job_id")"
      if [ "$disk_st" = "completed" ] || [ "$disk_st" = "error" ] || [ "$disk_st" = "cancelled" ]; then
        job_status="$disk_st"
        FINAL_JOB_STATUS="$disk_st"
        [ "$disk_st" = "completed" ] && return 0
        break
      fi
    done
    # Issue #33 (review R3): a wait that ran into the deadline is the wall clock.
    [ "$(date +%s)" -ge "$deadline" ] && FINALIZE_CLOCK="wall"
  fi

  # timeout: if subscriber timed out, check if agent is still actively working in herdr
  if [ "$job_status" = "timeout" ]; then
    local target_sess="${5:-${current_session:-${target_session:-$AGENT_SESSION}}}"
    local sess="${target_sess#herdr:}"
    local target_agent
    target_agent=$(_sanitize_herdr_agent_name "$sess")

    # ISSUE-14 / ISSUE-18: the subscriber's idle clock only counts events it
    # received over the wire. Keep re-observing the disk while the *contract*
    # says the agent is alive: an event in events.log at most IDLE_TIMEOUT
    # (K x N) old (_recent_disk_heartbeat - publish_event records every event
    # there before its wire publish, the automatic heartbeat timer included).
    # herdr status and the pane are NOT evidence any more; they are logged
    # once here as a diagnostic, so an operator can tell a dead agent from a
    # silent one on the same host. Window policy: entering this grace opens
    # one IDLE_TIMEOUT window and every disk event re-opens it from the time
    # of that poll, so an agent that leaves no event at all is closed about
    # 2 x IDLE_TIMEOUT after its last wire event. Evidence only ever extends
    # the idle window, never this dispatch's wall clock: the loop ends at
    # START_TIME + TIMEOUT read off the clock on every pass.
    local deadline evidence_until left disk_st
    deadline=$(( ${START_TIME:-$(date +%s)} + TIMEOUT ))
    evidence_until=$(( $(date +%s) + IDLE_TIMEOUT ))
    if [ "$AGENT" != "human" ] && [ "$sess" != "human" ] && [ -n "$sess" ] && ! _is_remote "$target_sess"; then
      local diag="no"
      _within_deadline "$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
    while [ "$(date +%s)" -lt "$deadline" ]; do
      disk_st="$(_disk_status "$job_id")"
      if [ "$disk_st" = "completed" ] || [ "$disk_st" = "error" ] || [ "$disk_st" = "cancelled" ]; then
        job_status="$disk_st"
        FINAL_JOB_STATUS="$disk_st"
        [ "$disk_st" = "completed" ] && return 0
        break
      fi
      if _recent_disk_heartbeat "$job_id" "$IDLE_TIMEOUT"; then
        evidence_until=$(( $(date +%s) + IDLE_TIMEOUT ))
      elif [ "$(date +%s)" -ge "$evidence_until" ]; then
        break
      fi
      left=$(( deadline - $(date +%s) ))
      [ "$left" -le 0 ] && break
      sleep 1
    done
    [ "$(date +%s)" -ge "$deadline" ] && FINALIZE_CLOCK="wall"
  fi

  # Issue #33: the subscriber's rc says which clock ran out (4 wall clock,
  # 2 no event); the disk-heartbeat grace above that ends on the deadline is
  # the wall clock too. bash only carries the label.
  local clock="${FINALIZE_CLOCK:-idle}"
  [ "$sub_rc" = "$SUB_RC_WALL_CLOCK" ] && clock="wall"
  local close_req="deadline_timeout"
  [ "$clock" = "wall" ] && [ "$phase" != "inject" ] && close_req="wall_clock_timeout"
  local detail=""
  if [ "$phase" = "preflight" ] || [ "$phase" = "idle_wait" ]; then
    close_req="cancelled"
    detail="session_busy"
    # Issue #34: a target the preflight could not see was never busy
    [ "$phase" = "preflight" ] && [ -n "${PREFLIGHT_REASON:-}" ] && detail="$PREFLIGHT_REASON"
  fi

  [ "$close_req" != "cancelled" ] && echo "finalize: $job_id closed by $([ "$clock" = "wall" ] && echo wall_clock || echo no_event) clock (budget ${TIMEOUT}s / idle ${IDLE_TIMEOUT}s)" >&2
  local close_args=(--job "$job_id" --request "$close_req")
  [ -n "$detail" ] && close_args+=(--detail "$detail")
  [ -n "${_disp_tok:-}" ] && close_args+=(--expect-dispatch-token "$_disp_tok")

  local close_rc=0
  "$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" close "${close_args[@]}" 2>&1 || close_rc=$?

  # If close failed due to dispatch token mismatch (rc=4), suppress secondary event emission
  # to prevent CAS/ABA bypass
  if [ $close_rc -eq 4 ]; then
    echo "finalize_unfinished: dispatch token mismatch (stale attempt); suppressing event emission" >&2
    return 0
  fi

  # Check if job completed on disk (universal, for all TYPEs)
  local cur_disk_st
  cur_disk_st="$(_disk_status "$job_id")"
  if [ "$cur_disk_st" = "completed" ]; then
    FINAL_JOB_STATUS="completed"
    return 0
  fi

  # direct path only: publish MQTT error/cancelled event (loop/discuss forbidden: O-1)
  if [ "$TYPE" = "direct" ]; then
    local disp_arg=()
    [ -n "${_disp_tok:-}" ] && disp_arg=(--expect-dispatch-token "$_disp_tok")
    if [ "$close_req" = "cancelled" ]; then
      "$PY" "$SCRIPT_DIR/scripts/publish_event.py" --registry-dir "$REGISTRY_DIR" --job "$job_id" --event cancelled --detail "$detail" ${disp_arg[@]+"${disp_arg[@]}"} 2>/dev/null || true
    elif [ "$sub_rc" -ne "$SUB_RC_ERROR" ] || [ "$phase" = "inject" ]; then
      local err_detail="$close_req"
      [ "$phase" = "inject" ] && err_detail="agent_blocked"
      "$PY" "$SCRIPT_DIR/scripts/publish_event.py" --registry-dir "$REGISTRY_DIR" --job "$job_id" --event error --detail "$err_detail" ${disp_arg[@]+"${disp_arg[@]}"} 2>/dev/null || true
    fi
  fi
}

preflight_agent() {
  local job_id="$1" target_session="${2:-$AGENT_SESSION}" force_warn_only="${3:-0}"
  if [ "$AGENT" = "human" ]; then
    return 0
  fi
  local sess="${target_session#herdr:}"

  # B-3: must probe for the real binary, not the herdr() function / shim wrapper.
  if ! has_real_herdr; then
    echo "ERROR: this skill requires herdr (interactive agent sessions)." >&2
    echo "       Ensure herdr is installed and executable." >&2
    return 1
  fi

  export HERDR_SESSION_NAME="$(resolve_herdr_session "$sess" "$WORKDIR")"

  if ! herdr has-session -t "$sess" 2>/dev/null; then
    PREFLIGHT_REASON="target_not_found"  # Issue #34: not a busy session
    echo "ERROR: 에이전트 세션 '$sess'이 존재하지 않습니다. 작업을 위임하기 전에 먼저 에이전트 세션을 기동해 주세요." >&2
    echo "       팁: 'multi-agent-mux-resume' 또는 'multi-agent-mux-create'를 통해 에이전트를 먼저 생성할 수 있습니다." >&2
    return 1
  fi

  # Check role suitability
  local sess_role job_role
  sess_role=$(SESS_NAME="$sess" MAM_STATE_JSON="$(load_state_json)" "$PY" -c "
import os, json
d = json.loads(os.environ.get('MAM_STATE_JSON', '{}'))
name = os.environ.get('SESS_NAME')
for s in d.get('herdr_sessions', []):
    if s.get('name') == name:
        print(s.get('role', ''))
        break
" 2>/dev/null || echo "")

  job_role=$("$PY" -c "
import json
try:
    with open('$REGISTRY_DIR/$job_id.json') as f:
        print(json.load(f).get('role', ''))
except Exception:
    pass
" 2>/dev/null || echo "")

  if [[ -n "$job_role" && -n "$sess_role" ]]; then
    local check_result
    check_result=$(JOB_ROLE="$job_role" SESS_ROLE="$sess_role" ROLE_ALIASES_JSON="$ROLE_ALIASES_JSON" "$PY" -c "
import os, json
job = os.environ.get('JOB_ROLE', '').lower()
sess = os.environ.get('SESS_ROLE', '').lower()
aliases = json.loads(os.environ.get('ROLE_ALIASES_JSON', '{}'))
candidates = aliases.get(job, [job])
if any(c in sess for c in candidates):
    print('OK')
else:
    print('MISMATCH')
" 2>/dev/null || echo "OK")

    if [[ "$check_result" == "MISMATCH" ]]; then
      local mismatch_msg="Target session '$sess' has role '$sess_role' which does not match job role '$job_role'."
      if [[ "$STRICT_ROLE_CHECK" -eq 1 && "$force_warn_only" -ne 1 ]]; then
        echo "ERROR: role suitability mismatch. $mismatch_msg" >&2
        return 1
      else
        echo "WARNING: $mismatch_msg" >&2
      fi
    fi
  fi
  return 0
}

inject_agent() {
  local job_id="$1" instructions="$2" target_session="${3:-$AGENT_SESSION}"
  # $4: subscriber log (a started line there also confirms delivery)
  if [ "$AGENT" = "human" ]; then
    echo "[human agent] complete the task, then run publish_event.py --event completed"
    return 0
  fi
  local sess="${target_session#herdr:}"

  # Before launching the agent, set up error trap to publish error event
  if [ -n "${job_id:-}" ] && [ -n "${PY:-}" ]; then
    pub_script="$SCRIPT_DIR/scripts/publish_event.py"
    trap "rc=\$?; if [ \$rc -ne 0 ]; then \"$PY\" \"$pub_script\" --registry-dir '$REGISTRY_DIR' --job '$job_id' --event error --detail 'agent bootstrap failed (exit '\$rc')'; fi" EXIT
  fi

  echo "살아있는 에이전트 세션 '$sess'에 작업을 위임합니다..."
  # ISSUE-18: send_keys_safe is the injection *means*. rc 0 (accepted, herdr
  # saw it working) and rc 4 (accepted, no screen signal) both hand over to
  # the protocol: the job's own `started` within ACK_TIMEOUT decides. Any
  # other rc means the input never reached the agent (pane never quiesced,
  # dialog, paste failure) - fail at once, never re-inject.
  local sks_rc=0
  send_keys_safe "$sess" "$instructions" "$job_id" || sks_rc=$?
  case "$sks_rc" in
    0|4) ;;
    *)
      trap - EXIT
      echo "ERROR: 프롬프트 주입 실패 (send_keys_safe rc=$sks_rc) — 세션 '$sess'" >&2
      return 1 ;;
  esac
  local ack_s="${MAM_INJECT_ACK_GRACE_S:-$ACK_TIMEOUT}"
  if ! _wait_started "$job_id" "$ack_s" "${4:-}"; then
    trap - EXIT
    echo "ERROR: 프롬프트 주입 실패 — 세션 '$sess': no 'started' within ${ACK_WAITED_S:-$ack_s}s (ack timeout ${ack_s}s, bounded by the wall clock); not re-injecting" >&2
    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)"
  trap - EXIT
  return 0
}

# remote_dispatch <job_id> <instructions> <remote:session> <subscriber_log>
# ISSUE-18: no pane, no shared disk. Publish the retained dispatch on the job's
# topic and wait for the agent's own `started` (seen by the subscriber) within
# ACK_TIMEOUT. The dispatch is signed with MAM_DISPATCH_SECRET (.mam.env).
remote_dispatch() {
  local job_id="$1" instructions="$2" target_session="$3" sub_log="${4:-}"
  local sess="${target_session#remote:}"
  echo "원격 세션 '$sess'에 작업을 dispatch 합니다 (broker)..."
  local d_args=(--job "$job_id" --registry-dir "$REGISTRY_DIR" --session "$sess" --instructions "$instructions")
  [ "${MAM_ALLOW_UNSIGNED_DISPATCH:-0}" = "1" ] && d_args+=(--allow-unsigned)
  if ! "$PY" "$SCRIPT_DIR/scripts/remote.py" dispatch "${d_args[@]}" >/dev/null; then
    echo "ERROR: dispatch publish failed for job $job_id (remote:$sess)" >&2
    return 1
  fi
  local ack_s="${MAM_INJECT_ACK_GRACE_S:-$ACK_TIMEOUT}"
  if ! _wait_started "$job_id" "$ack_s" "$sub_log"; then
    echo "ERROR: remote session '$sess' published no 'started' within ${ACK_WAITED_S:-$ack_s}s (ack timeout ${ack_s}s, bounded by the wall clock); not re-dispatching" >&2
    return 1
  fi
  echo "작업이 원격 세션 '$sess'에 전달되었습니다."
  return 0
}

# deliver_prompt <job_id> <instructions> <session> <subscriber_log>
deliver_prompt() {
  if _is_remote "$3"; then
    remote_dispatch "$1" "$2" "$3" "${4:-}"
  else
    inject_agent "$1" "$2" "$3" "${4:-}"
  fi
}

run_agent() {
  local job_id="$1" instructions="$2" target_session="${3:-$AGENT_SESSION}" force_warn_only="${4:-0}"
  local sess="${target_session#herdr:}"
  if [[ "$DRY_RUN" == "1" ]]; then
    echo "[dry-run] would delegate task to running agent '$AGENT' in herdr session '$sess' with instructions:"
    echo "----"; echo "$instructions"; echo "----"
    return 0
  fi
  preflight_agent "$job_id" "$target_session" "$force_warn_only" || return $?
  inject_agent "$job_id" "$instructions" "$target_session" || return $?
}

cmd_status() {
  parse_opts "$@"
  [[ -n "$JOB_ID" ]] || { echo "status requires --job" >&2; exit 1; }
  PY="$(pick_python)"
  "$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" get --job "$JOB_ID"
}

cmd_list() {
  parse_opts "$@"
  PY="$(pick_python)"
  "$PY" "$SCRIPT_DIR/scripts/registry.py" --registry-dir "$REGISTRY_DIR" list
}

cmd_verify() {
  parse_opts "$@"
  [[ -n "$JOB_ID" ]] || { echo "verify requires --job" >&2; exit 1; }
  [[ -n "$VALIDATE" ]] || { echo "verify requires --validate <script>" >&2; exit 1; }
  echo "verifying job $JOB_ID with $VALIDATE"
  if JOB_ID="$JOB_ID" REGISTRY_DIR="$REGISTRY_DIR" bash "$VALIDATE"; then
    echo "verify: PASS (exit 0)"; exit 0
  else
    rc=$?; echo "verify: FAIL (exit $rc)"; exit "$rc"
  fi
}

cmd_logs() {
  # logs <job_id> | logs --list — delegates to registry.py's logs CLI, which
  # reads the persistent audit log under $DELEGATE_JOB_LOGS_DIR (or
  # <cwd>/delegate_job_logs). Run from your project dir so the default resolves.
  PY="$(pick_python)"
  if [[ "${1:-}" == "--list" ]]; then
    "$PY" "$SCRIPT_DIR/scripts/registry.py" logs --list
  else
    local jid="${1:-}"
    [[ -n "$jid" ]] || { echo "logs requires <job_id> or --list" >&2; exit 1; }
    "$PY" "$SCRIPT_DIR/scripts/registry.py" logs "$jid"
  fi
}

cmd_wait() {
  parse_opts "$@"
  PY="$(pick_python)"
  local rc=0
  if [[ -n "$JOB_ID" ]]; then
    "$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
        --job "$JOB_ID" --timeout "$TIMEOUT" || rc=$?
  else
    "$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
        --wait-any --timeout "$TIMEOUT" || rc=$?
  fi
  # Issue #33: either clock is a timeout (rc 2) to callers of `wait`, as before;
  # the subscriber's own log says which clock it was.
  [ "$rc" -eq "$SUB_RC_WALL_CLOCK" ] && rc=$SUB_RC_NO_EVENT
  return "$rc"
}

main() {
  local sub="${1:-}"; shift || true
  case "$sub" in
    submit) cmd_submit "$@";;
    status) cmd_status "$@";;
    list)   cmd_list "$@";;
    verify) cmd_verify "$@";;
    wait)   cmd_wait "$@";;
    logs)   cmd_logs "$@";;
    ""|-h|--help|help) usage;;
    *) echo "unknown command: $sub" >&2; usage; exit 1;;
  esac
}

# Tests source this file to exercise single helpers (MAM_DELEGATE_JOB_NO_MAIN=1).
if [ "${MAM_DELEGATE_JOB_NO_MAIN:-0}" != "1" ]; then
  main "$@"
fi
