.agents/skills/lib_py/update.py

@@ -31,9 +31,9 @@ from __future__ import annotations
 
 import argparse
 import fcntl
-import glob
 import json
 import os
+import shlex
 import shutil
 import sqlite3
 import subprocess
@@ -109,7 +109,14 @@ def server_agents(herdr: str, server: str, env: Mapping[str, str]) -> List[dict]
 # --------------------------------------------------------------------------- jobs
 
 def _job_records(d: str) -> Iterable[Tuple[str, Optional[dict]]]:
-    for p in sorted(glob.glob(os.path.join(d, "*.json"))):
+    """(path, record) per *.json; (path, None) when it cannot be read, and
+    (d, None) when d itself cannot be listed (not an empty registry)."""
+    try:
+        names = sorted(n for n in os.listdir(d) if n.endswith(".json") and not n.startswith("."))
+    except OSError:
+        yield d, None
+        return
+    for p in (os.path.join(d, n) for n in names):
         try:
             with open(p, encoding="utf-8") as fh:
                 rec = json.load(fh)
@@ -119,6 +126,18 @@ def _job_records(d: str) -> Iterable[Tuple[str, Optional[dict]]]:
         yield p, rec if isinstance(rec, dict) else None
 
 
+def _is_jobs_dir(d: str) -> bool:
+    """d is a directory, or cannot be looked at (an unreadable parent): only an
+    absent d (or a file) is skipped."""
+    try:
+        os.stat(d)
+    except (FileNotFoundError, NotADirectoryError):
+        return False
+    except OSError:
+        return True
+    return os.path.isdir(d)
+
+
 def _is_open(rec: dict) -> bool:
     return rec.get("status") not in TERMINAL_STATUSES and rec.get("dry_run") is not True
 
@@ -127,10 +146,10 @@ def open_jobs(workspace: str, state: dict, env: Mapping[str, str]) -> List[dict]
     """Every open record (not completed/error/cancelled, not dry_run) in this
     workspace's .mam/jobs and MAM_JOBS_DIR; in another row's
     control_plane.mam_jobs_dir only those addressed to a row of this registry.
-    A record that cannot be read is open (path only)."""
+    A record, or a directory, that cannot be read is open (path only)."""
     own, seen = [], set()
     for c in (os.path.join(workspace, ".mam", "jobs"), env.get("MAM_JOBS_DIR") or ""):
-        if c and os.path.isdir(c) and _real(c) not in seen:
+        if c and _is_jobs_dir(c) and _real(c) not in seen:
             seen.add(_real(c))
             own.append(c)
     rows = state.get("herdr_sessions") or []
@@ -138,7 +157,7 @@ def open_jobs(workspace: str, state: dict, env: Mapping[str, str]) -> List[dict]
     other = []
     for s in rows:
         c = (s.get("control_plane") or {}).get("mam_jobs_dir") or ""
-        if c and os.path.isdir(c) and _real(c) not in seen:
+        if c and _is_jobs_dir(c) and _real(c) not in seen:
             seen.add(_real(c))
             other.append(c)
     out = []
@@ -146,7 +165,7 @@ def open_jobs(workspace: str, state: dict, env: Mapping[str, str]) -> List[dict]
         for d in dirs:
             for path, rec in _job_records(d):
                 if rec is None:
-                    out.append({"path": path, "unreadable": True})
+                    out.append({"path": path, "unreadable": True, "dir": path == d})
                 elif _is_open(rec) and (not addressed_only or rec.get("agent_session") in names):
                     out.append({"path": path, "job_id": rec.get("job_id") or "",
                                 "agent_session": rec.get("agent_session") or "",
@@ -161,6 +180,9 @@ def precheck(workspace: str, state: dict, herdr: str, env: Mapping[str, str]) ->
     blockers: List[str] = []
     stop = ("bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session %s"
             " (resume it after the update with multi-agent-mux-resume)")
+    # A rowless agent: stop finds no row to take its server from (#71).
+    stop_rowless = ("bash .agents/skills/multi-agent-mux-stop/scripts/stop_session.sh --session %s"
+                    " --herdr-session %s")
 
     # The caller (decision 7): its server and pane, both or nothing.
     me_server, me_pane = caller_server(env), env.get("HERDR_PANE_ID") or ""
@@ -193,7 +215,7 @@ def precheck(workspace: str, state: dict, herdr: str, env: Mapping[str, str]) ->
     for s in rows:
         if s.get("status") == "running" and s is not me_row:
             blockers.append("session %s is running (server %s); stop it: %s"
-                            % (s.get("name"), row_server(s), stop % s.get("name")))
+                            % (s.get("name"), row_server(s), stop % shlex.quote(s.get("name") or "")))
 
     row_keys = {(row_server(s), sanitize_herdr_agent_name(s["name"]))
                 for s in rows if s.get("status") == "running" and s.get("name")}
@@ -209,8 +231,9 @@ def precheck(workspace: str, state: dict, herdr: str, env: Mapping[str, str]) ->
                 continue   # already listed as its running row
             blockers.append("herdr agent %s (pane %s, server %s) runs in %s; stop it: %s"
                             % (name or "<unnamed>", a.get("pane_id"), server, a.get("cwd"),
-                               stop % name if name else
+                               stop_rowless % (shlex.quote(name), shlex.quote(server)) if name else
-                               "herdr --session %s pane close %s" % (server, a.get("pane_id"))))
+                               "herdr --session %s pane close %s"
+                               % (shlex.quote(server), shlex.quote(a.get("pane_id") or ""))))
 
     jobs = open_jobs(workspace, state, env)
     if me_row is not None:
@@ -220,7 +243,10 @@ def precheck(workspace: str, state: dict, herdr: str, env: Mapping[str, str]) ->
         if len(mine) == 1:
             jobs = [j for j in jobs if j is not mine[0]]
     for j in jobs:
-        if j.get("unreadable"):
+        if j.get("dir"):
+            blockers.append("jobs directory %s cannot be listed; fix its permissions, then try again"
+                            % j["path"])
+        elif j.get("unreadable"):
             blockers.append("job record %s cannot be read; check it, then move or delete it by hand"
                             % j["path"])
         else:

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

@@ -22,7 +22,7 @@ bash .agents/skills/multi-agent-mux-update/scripts/update.sh --yes
 |---|---|
 | Where | An installed workspace only (`.mam_deploy/remove.sh` present). A git checkout updates with `git pull`. |
 | Confirmation | `[y/N]` prompt; without a terminal `-y`/`--yes` is required. There is no force option. |
-| Refused when | a running registry row, a live herdr agent whose cwd is in the workspace (any running server), an open job (unreadable job JSON included, `dry_run` excluded), a live loop marker, `.mam/monitor.lock` held by a monitor the skills did not start, or another update. The calling agent (its herdr server + pane, row and one running job) is not counted. Each refusal lists the cleanup; nothing is changed. |
+| Refused when | a running registry row, a live herdr agent whose cwd is in the workspace (any running server), an open job (an unreadable job JSON or jobs directory included, `dry_run` excluded), a live loop marker, `.mam/monitor.lock` held by a monitor the skills did not start, or another update. The calling agent (its herdr server + pane, row and one running job) is not counted. Each refusal lists the cleanup; nothing is changed. |
 | During the update | create, resume, `run_loop.sh`, delegate submit, stop and orc-onboard refuse (`.mam/update-in-progress`, `.mam/update-admission.lock`). |
 | Monitor | stopped first, started again afterwards only if it ran (`MAM_NO_SUBSCRIBER_DAEMON=1`: not started). |
 | Install | the installer at `MAM_INSTALLER_URL` (default: Gitea `main`) runs in place; `.mam` is kept. On failure `.agents/`, `.mam_deploy/`, root files, `.venv`, the installer's `.mam` files and the registry are restored from `.mam/update-backup/`. |

tests/test_issue72_update.py

@@ -45,6 +45,15 @@ elif a[:2] == ["agent", "list"]:
     if spec.get("fail") == "agent-list:" + server:
         sys.exit(1)
     print(json.dumps({"result": {"agents": spec.get("agents", {}).get(server, [])}}))
+elif a[:2] == ["agent", "get"]:
+    hit = [x for x in spec.get("agents", {}).get(server, []) if a[2] in (x.get("name"), x.get("pane_id"))]
+    if not hit:
+        sys.exit(1)
+    print(json.dumps({"result": {"agent": hit[0]}}))
+elif a[:2] == ["pane", "close"]:
+    spec.setdefault("agents", {})[server] = [x for x in spec.get("agents", {}).get(server, [])
+                                             if x.get("pane_id") != a[2]]
+    json.dump(spec, open(os.environ["FAKE_HERDR_SPEC"], "w"))
 '''
 
 STUB_MONITOR = r'''#!/usr/bin/env bash
@@ -366,6 +375,28 @@ def test_refuses_a_rowless_agent_on_any_running_server(box):
     assert '"down"' not in calls
 
 
+def test_the_rowless_agent_hint_stops_it_on_the_server_it_was_found_on(box):
+    """R3: the printed stop command names the server; without it stop looks on
+    the workspace's server, where a same-named agent runs outside the workspace."""
+    write_rows(box.ws, [])
+    box.herdr(sessions={"default": True, "unrecorded-server": True},
+              agents={"unrecorded-server": [{"name": "stray", "pane_id": "w3:p1", "cwd": str(box.ws / "sub")}],
+                      "default": [{"name": "stray", "pane_id": "w1:p1", "cwd": str(box.root / "elsewhere")}]})
+    res = box.update()
+    assert res.returncode == 1, res.stdout + res.stderr
+    line = next(ln for ln in res.stderr.splitlines() if "herdr agent stray" in ln)
+    cmd = line.split("stop it: ", 1)[1]
+    assert "--herdr-session unrecorded-server" in cmd, cmd
+    stop = subprocess.run(["bash", "-c", cmd], cwd=str(box.ws), env=box.env, stdin=subprocess.DEVNULL,
+                          capture_output=True, text=True, timeout=120)
+    assert stop.returncode == 0, stop.stdout + stop.stderr
+    agents = json.loads(box.spec.read_text())["agents"]
+    assert agents["unrecorded-server"] == []
+    assert [x["pane_id"] for x in agents["default"]] == ["w1:p1"], "the same name elsewhere is left alone"
+    res = box.update()
+    assert res.returncode == 0, res.stdout + res.stderr
+
+
 def test_an_agent_outside_the_workspace_does_not_refuse(box):
     box.herdr(agents={"default": [{"name": "other", "pane_id": "w1:p2", "cwd": str(box.root / "elsewhere")}]})
     res = box.update()
@@ -406,6 +437,34 @@ def test_open_jobs_refuse_and_terminal_or_dry_run_do_not(box, tmp_path):
     del box.env["MAM_JOBS_DIR"]
 
 
+@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a mode-000 directory")
+def test_a_jobs_directory_that_cannot_be_listed_refuses(box, tmp_path):
+    """R2: an unreadable .mam/jobs (or MAM_JOBS_DIR under an unreadable parent)
+    is not an empty registry."""
+    jobs = box.mam / "jobs"
+    write_job(jobs, "hidden1", status="running")
+    before = snapshot(box.ws)
+    jobs.chmod(0)
+    try:
+        res = box.update()
+    finally:
+        jobs.chmod(0o755)
+    assert_refused_unchanged(box, before, res, "jobs directory %s cannot be listed" % jobs)
+    (jobs / "hidden1.json").unlink()
+
+    parent = tmp_path / "locked"
+    write_job(parent / "jobs", "env1", status="running")
+    box.env["MAM_JOBS_DIR"] = str(parent / "jobs")
+    before = snapshot(box.ws)
+    parent.chmod(0)
+    try:
+        res = box.update()
+    finally:
+        parent.chmod(0o755)
+    assert_refused_unchanged(box, before, res, "jobs directory %s cannot be listed" % (parent / "jobs"))
+    del box.env["MAM_JOBS_DIR"]
+
+
 def test_other_control_planes_count_only_jobs_addressed_to_this_registry(box, tmp_path):
     other = tmp_path / "other-plane" / "jobs"
     write_job(other, "theirs", status="running", session="herdr:not-ours")