Un-key stage-cache rows written before the current key shape

CACHE_SHAPE_SINCE marks the last change that moved every cache key. The
run service's periodic sweep clears cache_key on rows of runs created
before it, which nothing can match any more. Their outputs stay.
This commit is contained in:
2026-10-15 10:54:22 +02:00
parent 6fa44bacf3
commit a95be36dba
5 changed files with 69 additions and 4 deletions
+34 -1
View File
@@ -19,7 +19,7 @@ from fluksio.core.db import engine as db_engine
from fluksio.flow.artifacts import ArtifactStore
from fluksio.flow.controller import FlowController
from fluksio.flow.messages import DType, MessageSpec
from fluksio.flow.pipeline import NodeOutcome
from fluksio.flow.pipeline import CACHE_SHAPE_SINCE, NodeOutcome
from fluksio.flow.runs import (
LEASE_STALE_S,
OUTPUT_CAP,
@@ -28,6 +28,7 @@ from fluksio.flow.runs import (
RunService,
_cacheable,
new_run_id,
prune_stale_cache,
resolve_references,
seed_values,
)
@@ -106,6 +107,38 @@ def test_what_may_be_stored_as_a_cache_entry():
assert _cacheable(ok.model_copy(update={"output_values": big})) is None
def test_a_row_keyed_before_the_current_shape_is_unkeyed():
"""It matches nothing any more, but it is still the run's record."""
outputs = json.dumps({"study.loss": 1.0})
with Session(db_engine) as session:
for run_id, made in (
("shape-old", CACHE_SHAPE_SINCE - timedelta(days=1)),
("shape-new", CACHE_SHAPE_SINCE + timedelta(seconds=1)),
):
session.add(Run(id=run_id, flow="study", status="ok", created_at=made))
session.add(
RunNode(
run_id=run_id,
node="study.a",
cache_key=run_id,
outputs=outputs,
)
)
session.commit()
try:
assert prune_stale_cache() == 1
with Session(db_engine) as session:
old = session.get(RunNode, ("shape-old", "study.a"))
new = session.get(RunNode, ("shape-new", "study.a"))
assert old is not None and old.cache_key == "" and old.outputs == outputs
assert new is not None and new.cache_key == "shape-new"
finally:
with Session(db_engine) as session:
for run_id in ("shape-old", "shape-new"):
session.delete(session.get(Run, run_id))
session.commit()
# -----------------------------------------------------------------------------
# Naming an artifact from outside the process that made it
#