fix(issue-9): translate only a structured server_not_running error in the shim's ls

The ls translation searched stderr and the whole stdout for the substring
server_not_running, so a successful `agent list` that merely carried the text
(an agent named server_not_running-codex, or metadata) made the shim report
"no server running". reconcile.sh reads that as a confirmed-empty server, and
drift A would then mark every live row on it terminated (codex review of
0918917).

- keep the RPC exit code and translate only a failed call whose error
  envelope (the whole stream or any line of it) has
  error.code == "server_not_running"; every other failure keeps the unknown
  path (nonzero exit, herdr_confirmed False) as before
- tests: the real herdr 0.9 envelope, a successful list carrying the
  substring in a name and in metadata, other failures staying unknown, and
  reconcile keeping both live rows with no drift A; the new cases fail on
  0918917
- delegate wrapper: log a non-pending status seen during the inject ack
  grace as "registry advanced" instead of attributing it to the agent
- VERSIONS.md v4.4.2: describe the structured check and count 16 new tests

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe

.agents/skills/lib.sh

@@ -1245,15 +1245,42 @@ except Exception:
     # running", tmux's phrasing) instead of an opaque parse failure, which
     # would flip herdr_confirmed=False and freeze drift detection for every
     # server on the next heartbeat.
+    # Only a FAILED call whose structured error envelope carries
+    # error.code == "server_not_running" means "down". A successful list can
+    # legitimately contain that text (an agent named server_not_running-codex),
+    # and reading it as "down" made reconcile terminate every live row on that
+    # server. Any other failure falls through to the unknown path below.
     _ls_err=$(mktemp 2>/dev/null || echo "/tmp/mam_ls_err_$$")
-    _ls_raw="$(_real_herdr agent list 2>"$_ls_err")" || true
-    if grep -q server_not_running "$_ls_err" 2>/dev/null \
-       || printf '%s' "$_ls_raw" | grep -q server_not_running; then
-      rm -f "$_ls_err" 2>/dev/null || true
+    _ls_rc=0
+    _ls_raw="$(_real_herdr agent list 2>"$_ls_err")" || _ls_rc=$?
+    _ls_down=0
+    if [ "$_ls_rc" -ne 0 ]; then
+      _ls_down=$(printf '%s' "$_ls_raw" | MAM_LS_ERR_FILE="$_ls_err" python3 -c '
+import json, os, sys
+out = sys.stdin.read()
+try:
+    with open(os.environ["MAM_LS_ERR_FILE"]) as f:
+        err_text = f.read()
+except Exception:
+    err_text = ""
+down = 0
+for text in [out, err_text] + out.splitlines() + err_text.splitlines():
+    try:
+        doc = json.loads(text)
+    except Exception:
+        continue
+    err = doc.get("error") if isinstance(doc, dict) else None
+    if isinstance(err, dict) and err.get("code") == "server_not_running":
+        down = 1
+        break
+print(down)
+' 2>/dev/null || echo 0)
+    fi
+    rm -f "$_ls_err" 2>/dev/null || true
+    if [ "$_ls_down" = "1" ]; then
       echo "no server running (herdr session ${_sess:-default})" >&2
       exit 1
     fi
-    rm -f "$_ls_err" 2>/dev/null || true
     printf '%s\n' "$_ls_raw" | \
       MAM_LS_FORMAT="$format" MAM_REAL_HERDR="$REAL_HERDR" MAM_LS_SESSION="$_sess" \
       TZ=UTC LC_ALL=C python3 -c '

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

@@ -569,15 +569,18 @@ _disk_status() {
 # reports `working`, yet publishes `started` within seconds. Closing such a job
 # as agent_blocked strands a live agent whose later `completed` the CAS table
 # then refuses. Before finalising, give the registry MAM_INJECT_ACK_GRACE_S
-# (default 10 s) to show the agent's own acknowledgement: any status other than
-# pending means the prompt was delivered.
+# (default 10 s) to advance past pending. Any other status means the job moved
+# on - normally the agent's own `started` - so the prompt is treated as
+# delivered. The status is not pinned to this dispatch and may come from an
+# external writer; the terminal handling after this still keeps such an
+# error/cancelled as it is rather than turning it into success.
 _inject_acknowledged() {
   local job_id="$1" deadline st
   deadline=$(( $(date +%s) + ${MAM_INJECT_ACK_GRACE_S:-10} ))
   while :; do
     st="$(_disk_status "$job_id")"
     if [ -n "$st" ] && [ "$st" != "pending" ]; then
-      echo "inject: herdr could not confirm delivery, but job $job_id is already '$st' — the agent acknowledged it; continuing." >&2
+      echo "inject: herdr could not confirm delivery, but job $job_id already advanced to '$st' in the registry; treating the prompt as delivered and continuing." >&2
       return 0
     fi
     [ "$(date +%s)" -ge "$deadline" ] && return 1