feat(settings): Settings → System shows table sizes and what the last cleanup removed (#5469)
CI / lint (push) Successful in 2s
CI / integration (push) Successful in 1m12s
CI / unit (push) Successful in 1m28s
CI / publish (push) Successful in 1m4s

#5469 "Settings → System: table sizes and what the last cleanup removed".

- Storage: each table's size on disk (pg_total_relation_size, indexes and TOAST
  included) and Postgres's row estimate (reltuples), largest first, the 15
  largest by name and the rest summed, under the database's total size. Read
  from the catalog only, never by counting rows.
- Last cleanup: when it ran, how long it took, and what each pass removed (each
  aged table, run log files, the metric and Docker rollups, the log ring), or
  "Nothing was past its window". run_cleanup now returns that summary and keeps
  it as the cleanup.last_run setting, as reports.last_sent_at does; cleanup_secs
  (#5467) is recorded from the same figure.
- A hint links to where each retention window is set.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-09 14:29:55 -04:00
co-authored by Claude Opus 5.5
parent a81b578247
commit 0b2fbf13fc
8 changed files with 227 additions and 30 deletions
+53 -3
View File
@@ -8,6 +8,16 @@ from quart import render_template, session
from steward.core import health
AT = datetime(2026, 10, 9, 12, 0, tzinfo=timezone.utc)
STORAGE = {"total": 3 * 2**30, "rest": {"count": 0, "bytes": 0},
"tables": [{"name": "plugin_metrics", "bytes": 2 * 2**30, "rows": 41_000_000},
{"name": "docker_logs", "bytes": 512 * 2**20, "rows": None}]}
async def _page(app, ctx, storage=STORAGE, cleanup=None):
async with app.test_request_context("/settings/system/"):
session["user_role"] = "admin"
page = await render_template("settings/system.html", **ctx, storage=storage, cleanup=cleanup)
return " ".join(page.split())
def _previews(**over):
@@ -52,10 +62,50 @@ async def test_the_page_reads_as_a_verdict_then_each_measure(app, previews):
got = await health.process_health(None)
for r in got["rows"]:
r["spark"] = ""
async with app.test_request_context("/settings/system/"):
session["user_role"] = "admin"
page = " ".join((await render_template("settings/system.html", **got)).split())
page = await _page(app, got)
assert '<span class="tone-warn">Steward wasn&#39;t watching for up to 7m' in page
assert 'title="<' not in page # a <time> element never lands inside an attribute
assert "Database round trip" in page and "4 ms" in page and "2 ms – 9 ms" in page
assert page.index("page-verdict") < page.index("Agent posts per minute")
# ── Storage and the last cleanup (#5469) ─────────────────────────────────────
async def test_tables_largest_first_then_what_the_cleanup_removed(app, previews):
previews()
got = await health.process_health(None)
for r in got["rows"]:
r["spark"] = ""
cleanup = {"at": AT, "secs": 12.5, "passes": 14,
"removed": [("plugin_metrics: raw samples rolled into hourly", 86_400)]}
page = await _page(app, got, cleanup=cleanup)
assert "The database takes 3.0 GiB on disk." in page
assert page.index(">plugin_metrics<") < page.index(">docker_logs<")
assert "41,000,000" in page and "512.0 MiB" in page
assert "took 12s" in page and "86,400" in page
assert page.index("Steward itself") < page.index("Storage") < page.index("Last cleanup")
async def test_a_quiet_cleanup_and_one_not_yet_run_each_say_so(app, previews):
previews()
got = await health.process_health(None)
for r in got["rows"]:
r["spark"] = ""
quiet = await _page(app, got, cleanup={"at": AT, "secs": 1.0, "passes": 14, "removed": []})
assert "Nothing was past its window (14 passes)." in quiet
assert "None has finished since this version started" in await _page(app, got)
async def test_the_last_cleanup_keeps_only_what_went(monkeypatch):
stored = {"at": "2026-10-09T12:00:00+00:00", "secs": 3.2,
"removed": [["audit_events: older than 365 days", 0], ["docker_logs: past the age window", 7]]}
async def fake(db, key):
assert key == "cleanup.last_run"
return stored
monkeypatch.setattr("steward.core.settings.get_setting", fake)
got = await health.last_cleanup(None)
assert got["at"] == AT and got["passes"] == 2
assert got["removed"] == [("docker_logs: past the age window", 7)]
stored = {}
assert await health.last_cleanup(None) is None
+27 -4
View File
@@ -22,7 +22,7 @@ def app():
def test_the_audit_window_comes_from_settings(app):
from sqlalchemy import text
from steward.core.cleanup import run_cleanup
from steward.core.settings import set_setting
from steward.core.settings import get_setting, set_setting
from steward.models.audit import AuditEvent
now = datetime.now(timezone.utc)
@@ -35,16 +35,23 @@ def test_the_audit_window_comes_from_settings(app):
s.add(AuditEvent(action=tag, entity_id="old", timestamp=now - timedelta(days=40)))
s.add(AuditEvent(action=tag, entity_id="new", timestamp=now - timedelta(days=20)))
try:
await run_cleanup(app)
done = await run_cleanup(app)
finally:
async with app.db_sessionmaker() as s:
async with s.begin():
await set_setting(s, "audit.retention_days", 365)
async with app.db_sessionmaker() as s:
return [r[0] for r in (await s.execute(text(
kept = [r[0] for r in (await s.execute(text(
"SELECT entity_id FROM audit_events WHERE action = :a"), {"a": tag})).all()]
return kept, done, await get_setting(s, "cleanup.last_run")
assert asyncio.run(_go()) == ["new"]
kept, done, stored = asyncio.run(_go())
assert kept == ["new"]
# What it did is kept for Settings → System (#5469), each pass by name.
counts = dict(done["removed"])
assert counts["audit_events: older than 30 days"] >= 1
assert "plugin_metrics: raw samples rolled into hourly" in counts and done["secs"] >= 0
assert stored == done
def test_the_chart_seam_follows_the_raw_metrics_setting(app):
@@ -77,3 +84,19 @@ def test_the_chart_seam_follows_the_raw_metrics_setting(app):
await set_setting(s, "metrics.retention.raw_days", 7)
assert [v for _, v in asyncio.run(_go())] == [10.0]
def test_table_sizes_come_from_the_catalog_largest_first(app):
"""Settings → System's storage figures (#5469), read against real Postgres."""
from steward.core.health import TABLES_SHOWN, table_sizes
async def _go():
async with app.db_sessionmaker() as s:
return await table_sizes(s)
got = asyncio.run(_go())
sizes = [t["bytes"] for t in got["tables"]]
assert sizes == sorted(sizes, reverse=True) and len(sizes) <= TABLES_SHOWN
names = {t["name"] for t in got["tables"]}
assert got["rest"]["count"] or "audit_events" in names # the schema's own tables
assert got["total"] >= sum(sizes) + got["rest"]["bytes"] > 0