fix(reset): never take another live reset's fence, and fence absent row registries (#78)
Review round 4 (codex): - R1: fence_registries reads an existing marker under the registry lock and refuses the reset, changing nothing, when another live (or undecidable) reset holds it - registries may be shared between workspaces; only a stale marker is replaced, and the reset's exit removes only its own fences. - R2: the registries to fence come from update.jobs_dirs, the enumeration open_jobs now uses too, whether or not they exist; an absent row registry is created and fenced (a registration would create it), and one that cannot be created refuses the reset. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
568385c77a
commit
b49314c3d0
6 files changed
+213
-74
No files matched your search
@@ -147,34 +147,40 @@ def _is_open(rec: dict) -> bool:
|
||||
return rec.get("status") not in TERMINAL_STATUSES and rec.get("dry_run") is not True
|
||||
|
||||
|
||||
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, 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 _is_jobs_dir(c) and _real(c) not in seen:
|
||||
def jobs_dirs(workspace: str, state: dict, env: Mapping[str, str]) -> List[Tuple[str, bool]]:
|
||||
"""(dir, addressed_only) per registry an open-job check reads, once per
|
||||
real path, whether or not it exists yet: this workspace's .mam/jobs and
|
||||
MAM_JOBS_DIR, then another row's control_plane.mam_jobs_dir, where only
|
||||
records addressed to a row of this registry count (addressed_only)."""
|
||||
rows = state.get("herdr_sessions") or []
|
||||
cands = [(c, False) for c in (os.path.join(workspace, ".mam", "jobs"), env.get("MAM_JOBS_DIR") or "")]
|
||||
cands += [((s.get("control_plane") or {}).get("mam_jobs_dir") or "", True) for s in rows]
|
||||
out, seen = [], set()
|
||||
for c, addressed_only in cands:
|
||||
if c and _real(c) not in seen:
|
||||
seen.add(_real(c))
|
||||
own.append(c)
|
||||
out.append((c, addressed_only))
|
||||
return out
|
||||
|
||||
|
||||
def open_jobs(workspace: str, state: dict, env: Mapping[str, str]) -> List[dict]:
|
||||
"""Every open record (not completed/error/cancelled, not dry_run) in the
|
||||
registries jobs_dirs names; in another row's control-plane registry only
|
||||
those addressed to a row of this registry. A record, or a directory, that
|
||||
cannot be read is open (path only)."""
|
||||
rows = state.get("herdr_sessions") or []
|
||||
names = {"herdr:%s" % s.get("name") for s in rows if s.get("name")}
|
||||
other = []
|
||||
for s in rows:
|
||||
c = (s.get("control_plane") or {}).get("mam_jobs_dir") or ""
|
||||
if c and _is_jobs_dir(c) and _real(c) not in seen:
|
||||
seen.add(_real(c))
|
||||
other.append(c)
|
||||
out = []
|
||||
for dirs, addressed_only in ((own, False), (other, True)):
|
||||
for d in dirs:
|
||||
for path, rec in _job_records(d):
|
||||
if rec is None:
|
||||
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 "",
|
||||
"status": rec.get("status"), "registry_dir": d})
|
||||
for d, addressed_only in jobs_dirs(workspace, state, env):
|
||||
if not _is_jobs_dir(d):
|
||||
continue
|
||||
for path, rec in _job_records(d):
|
||||
if rec is None:
|
||||
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 "",
|
||||
"status": rec.get("status"), "registry_dir": d})
|
||||
return out
|
||||
|
||||
|
||||
|
||||
Reference in new issue
Block a user