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

tests/test_issue9_server_env.py

@@ -15,6 +15,8 @@ import subprocess
 import sys
 from pathlib import Path
 
+import pytest
+
 REPO_ROOT = Path(__file__).resolve().parent.parent
 RECONCILE_SH = REPO_ROOT / ".agents" / "skills" / "multi-agent-mux-monitor" / "scripts" / "reconcile.sh"
 STATUS_SH = REPO_ROOT / ".agents" / "skills" / "multi-agent-mux-status" / "scripts" / "status.sh"
@@ -54,6 +56,24 @@ KEPT_CONFIG = {
     "MAM_CUSTOM_SETTING": "kept",
 }
 
+# What herdr 0.9 writes to stderr (exit 1) for `agent list` against a stopped
+# session server.
+REAL_DOWN_ENVELOPE = {
+    "id": "cli:agent:list",
+    "error": {
+        "code": "server_not_running",
+        "message": "no herdr server is running at /tmp/sessions/down-srv/herdr.sock; "
+                   "run `herdr session attach down-srv` to start or attach it",
+    },
+}
+
+# A successful list in which the down-server code appears only as data: in an
+# agent name (the sanitizer allows underscores) and in unrelated metadata.
+LISTING_WITH_SUBSTRING = {"result": {"agents": [
+    {"name": "server_not_running-codex", "agent": "codex"},
+    {"name": "creator-claude-01", "agent": "claude", "title": "server_not_running"},
+]}}
+
 
 def _install_fake_herdr(sandbox: Path) -> dict:
     fakebin = sandbox / "fakebin"
@@ -72,6 +92,12 @@ def _install_fake_herdr(sandbox: Path) -> dict:
     return env
 
 
+def _fake_agent_list(sandbox: Path, body: str) -> None:
+    """Replace the fake's fallback answer (what `agent list` gets) with `body`."""
+    fake = sandbox / "fakebin" / "herdr"
+    fake.write_text(FAKE_HERDR.replace('print(json.dumps({"result": {"agents": []}}))', body))
+
+
 def _calls(env: dict) -> list:
     log = Path(env["FAKE_HERDR_LOG"])
     if not log.exists():
@@ -90,6 +116,15 @@ def _run_through_shim(sandbox: Path, env: dict, session: str) -> subprocess.Comp
     )
 
 
+def _shim_ls(sandbox: Path, env: dict, server: str) -> subprocess.CompletedProcess:
+    """The exact `ls` query reconcile.sh sends for each registered server."""
+    lib = sandbox / ".agents" / "skills" / "lib.sh"
+    return subprocess.run(
+        ["bash", "-c", f'source "{lib}" >/dev/null 2>&1; herdr -L {server} ls -F "#{{session_name}}|#{{session_created}}"'],
+        capture_output=True, text=True, cwd=str(sandbox), env=env, timeout=60,
+    )
+
+
 def test_bootstrap_strips_agent_runtime_markers(mam_sandbox):
     env = _install_fake_herdr(mam_sandbox)
     env.update(RUNTIME_MARKERS)
@@ -160,22 +195,85 @@ def test_reconcile_and_status_opt_out_of_autostart_statically():
             f"{script.name} must opt out of the shim's server bootstrap"
 
 
-def test_ls_reports_down_server_as_no_server_running(mam_sandbox):
+@pytest.mark.parametrize("envelope", [
+    {"error": {"code": "server_not_running"}},
+    REAL_DOWN_ENVELOPE,
+], ids=["minimal", "herdr-0.9"])
+def test_ls_reports_down_server_as_no_server_running(mam_sandbox, envelope):
     """reconcile.sh treats a nonzero `ls` as 'empty' only when stderr says
     'no server running'; anything else flips herdr_confirmed=False for every
     server. The shim must therefore translate server_not_running explicitly."""
     env = _install_fake_herdr(mam_sandbox)
     env["MAM_NO_AUTOSTART"] = "1"
-    fake = mam_sandbox / "fakebin" / "herdr"
-    fake.write_text(FAKE_HERDR.replace(
-        'print(json.dumps({"result": {"agents": []}}))',
-        'sys.stderr.write(json.dumps({"error": {"code": "server_not_running"}}) + "\\n"); sys.exit(1)',
-    ))
-    lib = mam_sandbox / ".agents" / "skills" / "lib.sh"
-    res = subprocess.run(
-        ["bash", "-c", f'source "{lib}" >/dev/null 2>&1; herdr -L down-srv ls -F "#{{session_name}}|#{{session_created}}"'],
-        capture_output=True, text=True, cwd=str(mam_sandbox), env=env, timeout=60,
-    )
+    _fake_agent_list(mam_sandbox,
+                     f'sys.stderr.write({json.dumps(json.dumps(envelope))} + "\\n"); sys.exit(1)')
+
+    res = _shim_ls(mam_sandbox, env, "down-srv")
     assert res.returncode != 0
     assert "no server running" in res.stderr, res.stderr
     assert res.stdout.strip() == ""
+
+
+def test_ls_lists_agents_whose_names_contain_server_not_running(mam_sandbox):
+    """A successful list is never a down server, whatever text it carries.
+    Matching the bare substring let one agent named server_not_running-codex
+    hide every agent its server returned."""
+    env = _install_fake_herdr(mam_sandbox)
+    env["MAM_NO_AUTOSTART"] = "1"
+    _fake_agent_list(mam_sandbox, f"print({json.dumps(json.dumps(LISTING_WITH_SUBSTRING))})")
+
+    res = _shim_ls(mam_sandbox, env, "live-srv")
+    assert res.returncode == 0, res.stderr
+    assert "no server running" not in res.stderr, res.stderr
+    names = [line.split("|", 1)[0] for line in res.stdout.splitlines() if line.strip()]
+    assert names == ["server_not_running-codex", "creator-claude-01"], res.stdout
+
+
+@pytest.mark.parametrize("stderr_text", [
+    json.dumps({"error": {"code": "transport_error",
+                          "message": "socket reset while probing server_not_running"}}),
+    "warning: server_not_running cache entry is stale",
+    "",
+], ids=["other-code", "plain-text", "empty"])
+def test_ls_leaves_other_failures_unknown(mam_sandbox, stderr_text):
+    """Only the structured code means "down". Any other failure keeps the
+    unknown path (nonzero exit without 'no server running'), so reconcile
+    drops herdr_confirmed instead of reading a confirmed-empty server."""
+    env = _install_fake_herdr(mam_sandbox)
+    env["MAM_NO_AUTOSTART"] = "1"
+    _fake_agent_list(mam_sandbox,
+                     f'sys.stderr.write({json.dumps(stderr_text)} + "\\n"); sys.exit(1)')
+
+    res = _shim_ls(mam_sandbox, env, "flaky-srv")
+    assert res.returncode != 0
+    assert "no server running" not in res.stderr, res.stderr
+    assert res.stdout.strip() == ""
+
+
+def test_reconcile_keeps_live_rows_when_a_name_contains_server_not_running(mam_sandbox):
+    """End to end through reconcile.sh: the server answers a successful list in
+    which the down-server code appears as data. Both registered rows must stay
+    alive with herdr_confirmed intact, so drift A cannot mark them terminated."""
+    env = _install_fake_herdr(mam_sandbox)
+    _fake_agent_list(mam_sandbox, f"print({json.dumps(json.dumps(LISTING_WITH_SUBSTRING))})")
+    rows = "".join(
+        f"  - name: {name}\n"
+        "    status: running\n"
+        "    herdr_session: live-srv\n"
+        "    pane:\n"
+        "      cwd: /tmp/nonexistent-workspace\n"
+        for name in ("server_not_running-codex", "creator-claude-01")
+    )
+    (mam_sandbox / ".mam" / "agent-sessions.yaml").write_text("herdr_sessions:\n" + rows)
+    reconcile = mam_sandbox / "skills" / "multi-agent-mux-monitor" / "scripts" / "reconcile.sh"
+
+    res = subprocess.run(["bash", str(reconcile), "--once", "--emit-diff", "--dry-run"],
+                         capture_output=True, text=True, cwd=str(mam_sandbox), env=env, timeout=120)
+    assert res.returncode == 0, res.stderr
+
+    report = json.loads(res.stdout)
+    assert report["herdr_confirmed"] is True, report
+    alive = set(report["herdr_sessions_alive"])
+    assert {"server_not_running-codex|live-srv", "creator-claude-01|live-srv"} <= alive, alive
+    drift_a = [d for d in report["drifts"] if d.get("class") == "A"]
+    assert not drift_a, drift_a