tmpl/multi-agent-mux
1
0 Fork 0
Code Issues 8 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(update): an unlistable jobs directory refuses; the rowless-agent hint names its server (Issue #72, review R2, R3)

Browse Source 
R2: glob() hid a listing error, so an unreadable .mam/jobs (or MAM_JOBS_DIR,
or another row's jobs dir) counted as empty and the update installed over an
open job. Records are now listed with os.listdir; a directory that cannot be
listed, or stat'ed, is a blocker with its path.

R3: a discovered agent with no row was told to run stop with --session only;
stop then looked on the workspace's server, not the one the agent was found
on. The hint now carries --herdr-session <server>, quoted.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
GodopuandClaude Opus 5.5 committed 2026-10-27 08:15:23 +00:00
1 parent e3394655b3
commit ba75718ac3
3 files changed
+96 -11
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.agents/skills/lib_py/update.py
+36 -10
View File
@@ -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
"herdr --session %s pane close %s" % (server, a.get("pane_id"))))
stop_rowless % (shlex.quote(name), shlex.quote(server)) if name else
"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
+1 -1
View File
@@ -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/`. |