Let every harness work on a copy of the frozen store

copy_store lived in dense_scale, so the two harnesses that also needed it reached back into a
measurement module for a plumbing helper. It now sits in systems beside the product path it
protects, and bench.run passes a scratch directory to the live check: the product path migrates
whatever database it opens, and the frozen baseline is cited evidence.
This commit is contained in:
ZacharyZhang-NY committed 2026-10-08 15:11:27 -04:00
1 parent b8f83f422a
commit 91fbff34ee
5 files changed
+39 -22

No files matched your search

+1 -16
View File
@@ -10,7 +10,6 @@ from __future__ import annotations
import argparse
import json
import shutil
import sqlite3
import time
from collections.abc import Sequence
@@ -22,7 +21,7 @@ import numpy as np
from bench.query_set import load_queries, scale_probes
from bench.report import git_commit
from bench.run import latency
from bench.systems import DENSE_MODEL, MODELS, machine_facts
from bench.systems import DENSE_MODEL, MODELS, copy_store, machine_facts
if TYPE_CHECKING:
from ely_eye.db import Database
@@ -65,20 +64,6 @@ def vector_footprint(database: Any, table: str) -> tuple[int, str]:
return int(payload), "vector bytes only, this sqlite3 has no dbstat"
def copy_store(home: Path, scratch: Path) -> tuple[Path, float]:
"""Work on a copy: the baseline store is frozen evidence and must not be migrated in place."""
source = home / "data" / "ely_eye.sqlite"
if not source.is_file():
raise SystemExit(f"{source}: no product database, build it with python -m bench.ingest_baseline")
data = scratch / "data"
data.mkdir(parents=True, exist_ok=True)
began = time.perf_counter()
for suffix in ("", "-wal", "-shm"):
if (path := Path(str(source) + suffix)).is_file():
shutil.copyfile(path, data / (source.name + suffix))
return scratch, time.perf_counter() - began
def stored_vectors(database: Database) -> tuple[list[str], np.ndarray]:
"""Every vector the engine holds, for a scan it can be checked against."""
with database.connect() as connection: