refactor(maintenance): DRY the recover_stalled head-run twins (#161)

recover_stalled_head_training_runs and recover_stalled_head_auto_apply_runs
were near-exact copies (coalesce-flip + keep-last-N prune, differing only in
model + two constants). Extract _recover_stalled_runs(model, stall_minutes,
keep_runs, label); the two tasks become thin wrappers. The other two recover
tasks are deliberately NOT folded in (library-audit has no prune tail; backup
uses a single started_at cutoff). test_recover_stalled_head_runs.py covers
both wrappers (stalled→error, fresh survives) — previously untested.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NsmJSQxnNxGgtM5Yz4GAqi
This commit is contained in:
2026-07-13 21:41:34 -04:00
parent 666b3a2ec8
commit c87f8a1bb3
2 changed files with 108 additions and 72 deletions
+45 -72
View File
@@ -776,89 +776,62 @@ def recover_stalled_library_audit_runs() -> int:
return recovered
def _recover_stalled_runs(model, *, stall_minutes: int, keep_runs: int, label: str) -> int:
"""Shared recovery + retention sweep for the head run-tracking tables
(HeadTrainingRun / HeadAutoApplyRun, which share the
status/last_progress_at/started_at/finished_at/error/id columns): flip 'running'
rows with no progress past `stall_minutes` to 'error', then prune to the last
`keep_runs` (rule 89). Returns the number recovered. NOTE the two other recover
tasks are deliberately NOT folded in — library-audit has no prune tail and
backup uses a single started_at cutoff."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
cutoff = now - timedelta(minutes=stall_minutes)
with SessionLocal() as session:
result = session.execute(
update(model)
.where(model.status == "running")
.where(func.coalesce(model.last_progress_at, model.started_at) < cutoff)
.values(
status="error", finished_at=now,
error=f"stranded by recovery sweep (no progress for {stall_minutes} min)",
)
)
keep = session.execute(
select(model.id).order_by(model.id.desc()).limit(keep_runs)
).scalars().all()
if keep:
session.execute(delete(model).where(model.id.not_in(keep)))
session.commit()
recovered = result.rowcount or 0
if recovered:
log.info("%s: recovered %d rows", label, recovered)
return recovered
@celery.task(name="backend.app.tasks.maintenance.recover_stalled_head_training_runs")
def recover_stalled_head_training_runs() -> int:
"""Flip HeadTrainingRun rows stuck in 'running' past the stall threshold to
'error', and prune old runs to the last HEAD_TRAINING_KEEP_RUNS (retention,
rule 89). Runs every 5 min on the maintenance lane; no-op when idle."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
cutoff = now - timedelta(minutes=HEAD_TRAINING_STALL_THRESHOLD_MINUTES)
with SessionLocal() as session:
result = session.execute(
update(HeadTrainingRun)
.where(HeadTrainingRun.status == "running")
.where(
func.coalesce(
HeadTrainingRun.last_progress_at, HeadTrainingRun.started_at
)
< cutoff
)
.values(
status="error", finished_at=now,
error=(
f"stranded by recovery sweep (no progress for "
f"{HEAD_TRAINING_STALL_THRESHOLD_MINUTES} min)"
),
)
)
keep = session.execute(
select(HeadTrainingRun.id).order_by(HeadTrainingRun.id.desc())
.limit(HEAD_TRAINING_KEEP_RUNS)
).scalars().all()
if keep:
session.execute(
delete(HeadTrainingRun).where(HeadTrainingRun.id.not_in(keep))
)
session.commit()
recovered = result.rowcount or 0
if recovered:
log.info(
"recover_stalled_head_training_runs: recovered %d rows", recovered
)
return recovered
return _recover_stalled_runs(
HeadTrainingRun,
stall_minutes=HEAD_TRAINING_STALL_THRESHOLD_MINUTES,
keep_runs=HEAD_TRAINING_KEEP_RUNS,
label="recover_stalled_head_training_runs",
)
@celery.task(name="backend.app.tasks.maintenance.recover_stalled_head_auto_apply_runs")
def recover_stalled_head_auto_apply_runs() -> int:
"""Flip stalled HeadAutoApplyRun 'running' rows to 'error' + prune to the
last HEAD_AUTO_APPLY_KEEP_RUNS (retention, rule 89). 5-min maintenance lane."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
cutoff = now - timedelta(minutes=HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES)
with SessionLocal() as session:
result = session.execute(
update(HeadAutoApplyRun)
.where(HeadAutoApplyRun.status == "running")
.where(
func.coalesce(
HeadAutoApplyRun.last_progress_at, HeadAutoApplyRun.started_at
)
< cutoff
)
.values(
status="error", finished_at=now,
error=(
f"stranded by recovery sweep (no progress for "
f"{HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES} min)"
),
)
)
keep = session.execute(
select(HeadAutoApplyRun.id).order_by(HeadAutoApplyRun.id.desc())
.limit(HEAD_AUTO_APPLY_KEEP_RUNS)
).scalars().all()
if keep:
session.execute(
delete(HeadAutoApplyRun).where(HeadAutoApplyRun.id.not_in(keep))
)
session.commit()
recovered = result.rowcount or 0
if recovered:
log.info(
"recover_stalled_head_auto_apply_runs: recovered %d rows", recovered
)
return recovered
return _recover_stalled_runs(
HeadAutoApplyRun,
stall_minutes=HEAD_AUTO_APPLY_STALL_THRESHOLD_MINUTES,
keep_runs=HEAD_AUTO_APPLY_KEEP_RUNS,
label="recover_stalled_head_auto_apply_runs",
)
# Keep ~6 months of daily head-metric snapshots (enough to see tuning trends).
+63
View File
@@ -0,0 +1,63 @@
"""recover_stalled_head_training_runs + recover_stalled_head_auto_apply_runs share
one helper (_recover_stalled_runs, DRY pass #161). These pin BOTH wrappers so the
shared source stays correct: a 'running' row with no progress past the stall
threshold flips to 'error'; a fresh 'running' row is left alone."""
from datetime import UTC, datetime, timedelta
import pytest
from sqlalchemy import select
from backend.app.models import HeadAutoApplyRun, HeadTrainingRun
pytestmark = pytest.mark.integration
def test_recover_stalled_head_training_runs_flips_stalled_keeps_fresh(db_sync):
from backend.app.tasks.maintenance import recover_stalled_head_training_runs
stale = HeadTrainingRun(
params={}, status="running",
last_progress_at=datetime.now(UTC) - timedelta(days=1),
)
fresh = HeadTrainingRun(
params={}, status="running", last_progress_at=datetime.now(UTC),
)
db_sync.add_all([stale, fresh])
db_sync.commit()
stale_id, fresh_id = stale.id, fresh.id
assert recover_stalled_head_training_runs.apply().get() == 1
db_sync.expire_all()
assert db_sync.execute(
select(HeadTrainingRun.status).where(HeadTrainingRun.id == stale_id)
).scalar_one() == "error"
assert db_sync.execute(
select(HeadTrainingRun.status).where(HeadTrainingRun.id == fresh_id)
).scalar_one() == "running"
def test_recover_stalled_head_auto_apply_runs_flips_stalled_keeps_fresh(db_sync):
from backend.app.tasks.maintenance import recover_stalled_head_auto_apply_runs
stale = HeadAutoApplyRun(
dry_run=False, params={}, status="running",
last_progress_at=datetime.now(UTC) - timedelta(days=1),
)
fresh = HeadAutoApplyRun(
dry_run=False, params={}, status="running",
last_progress_at=datetime.now(UTC),
)
db_sync.add_all([stale, fresh])
db_sync.commit()
stale_id, fresh_id = stale.id, fresh.id
assert recover_stalled_head_auto_apply_runs.apply().get() == 1
db_sync.expire_all()
assert db_sync.execute(
select(HeadAutoApplyRun.status).where(HeadAutoApplyRun.id == stale_id)
).scalar_one() == "error"
assert db_sync.execute(
select(HeadAutoApplyRun.status).where(HeadAutoApplyRun.id == fresh_id)
).scalar_one() == "running"