feat(executors): add postgres retention executor

Deletes rows past a retention window from a table on the shared Postgres
server. Written for sysmon's check_history, which grows with every
monitoring check and had no retention at all despite the docs promising
a 30-day rolling window.

Connects with the Scheduler's own credentials and overrides only the
database name, so no second set of secrets enters the stack. The target
database grants scheduler_user just SELECT and DELETE on the table, so a
bug here can drop old rows but cannot corrupt or forge history.

Table and column names cannot be bound as query parameters, so both are
validated against a strict identifier pattern before interpolation, and
a retention window below 1 day is refused rather than silently emptying
the table.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
2026-08-08 11:00:42 +02:00
co-authored by Claude
parent ae4f9e6a20
commit 788c03514a
2 changed files with 260 additions and 0 deletions
@@ -0,0 +1,109 @@
"""
Postgres Retention Executor
Deletes rows older than a retention window from a table on the shared Postgres
server. Written for sysmon's `check_history`, which grows with every monitoring
check and had no retention at all, but the executor is table-agnostic.
Connects with the Scheduler's own Postgres credentials and only overrides the
database name. That keeps a second set of credentials out of the stack; the
target database grants `scheduler_user` exactly SELECT and DELETE on the table,
so a bug here can drop old rows but cannot corrupt or forge history.
Config schema:
{
"database": "sysmon", # defaults to the Scheduler's own database
"table": "check_history", # required
"timestamp_column": "ts", # required
"retention_days": 30, # required, must be >= 1
"dry_run": false # count what would go, delete nothing
}
Table and column names cannot be passed as query parameters, so both are
validated against a strict identifier pattern before being interpolated.
Autovacuum reclaims the space afterwards; this deliberately does not VACUUM,
which would need table ownership the Scheduler intentionally does not have.
"""
import asyncio
import logging
import re
from typing import Any, Dict
import psycopg2
from src.config import Settings
logger = logging.getLogger(__name__)
# Deliberately strict: unquoted lowercase identifiers only. Anything needing
# quoting is out of scope and would be a hole in the interpolation below.
IDENTIFIER_RE = re.compile(r"^[a-z_][a-z0-9_]*$")
MAX_RETENTION_DAYS = 3650
def _validate_identifier(value: str, label: str) -> str:
if not isinstance(value, str) or not IDENTIFIER_RE.match(value):
raise ValueError(
f"invalid {label}: {value!r} (expected an unquoted lowercase identifier)"
)
return value
def _prune(config: Dict[str, Any], settings: Settings) -> str:
table = _validate_identifier(config.get("table", ""), "table")
column = _validate_identifier(config.get("timestamp_column", ""), "timestamp_column")
database = config.get("database") or settings.postgres_db
_validate_identifier(database, "database")
retention_days = config.get("retention_days")
if not isinstance(retention_days, int) or isinstance(retention_days, bool):
raise ValueError(f"retention_days must be an integer, got {retention_days!r}")
# A zero or negative window would delete everything, including the row the
# check just wrote. Refuse rather than quietly wipe the table.
if retention_days < 1 or retention_days > MAX_RETENTION_DAYS:
raise ValueError(
f"retention_days must be between 1 and {MAX_RETENTION_DAYS}, got {retention_days}"
)
dry_run = bool(config.get("dry_run", False))
cutoff_sql = f"{column} < now() - make_interval(days => %s)"
conn = psycopg2.connect(
host=settings.postgres_host,
port=settings.postgres_port,
database=database,
user=settings.postgres_user,
password=settings.postgres_password,
connect_timeout=10,
)
try:
with conn:
with conn.cursor() as cur:
cur.execute(f"SELECT count(*) FROM {table} WHERE {cutoff_sql}", (retention_days,))
stale = cur.fetchone()[0]
if dry_run:
logger.info("dry run: %s rows in %s.%s exceed %sd", stale, database, table, retention_days)
return f"dry run: {stale} rows older than {retention_days}d in {database}.{table}"
if stale == 0:
return f"nothing to prune in {database}.{table} (retention {retention_days}d)"
cur.execute(f"DELETE FROM {table} WHERE {cutoff_sql}", (retention_days,))
deleted = cur.rowcount
cur.execute(f"SELECT count(*) FROM {table}")
remaining = cur.fetchone()[0]
finally:
conn.close()
logger.info("pruned %s rows from %s.%s, %s remain", deleted, database, table, remaining)
return f"pruned {deleted} rows older than {retention_days}d from {database}.{table}, {remaining} remain"
async def execute(config: dict, settings: Settings) -> str:
"""Delete rows past the retention window. Returns a one-line summary."""
# psycopg2 is synchronous; keep it off the scheduler's event loop.
return await asyncio.to_thread(_prune, config, settings)
+151
View File
@@ -0,0 +1,151 @@
"""
Tests for the postgres retention executor.
Focus is on the guards. The executor interpolates a table and column name
straight into SQL (they cannot be bound as parameters), and it issues DELETEs
against a live table, so the validation in front of both is what keeps a
malformed config from becoming data loss.
"""
from unittest.mock import MagicMock, patch
import pytest
from src.config import Settings
from src.executors import postgres_retention_executor as retention
@pytest.mark.executor
@pytest.mark.unit
class TestIdentifierValidation:
"""Table/column/database names are interpolated, so they must be rejected early."""
@pytest.mark.parametrize(
"bad",
[
"check_history; DROP TABLE users",
'check_history"',
"check history",
"Check_History", # uppercase would need quoting to resolve
"1_history",
"",
"--comment",
],
)
def test_rejects_unsafe_identifiers(self, bad):
with pytest.raises(ValueError):
retention._validate_identifier(bad, "table")
@pytest.mark.parametrize("good", ["check_history", "ts", "_private", "a1"])
def test_accepts_plain_identifiers(self, good):
assert retention._validate_identifier(good, "table") == good
@pytest.mark.executor
@pytest.mark.unit
class TestRetentionGuards:
"""A bad retention window must never reach the database."""
def _config(self, **overrides):
config = {
"database": "sysmon",
"table": "check_history",
"timestamp_column": "ts",
"retention_days": 30,
}
config.update(overrides)
return config
@pytest.mark.parametrize("days", [0, -1, -30, 3651])
def test_rejects_out_of_range_retention(self, days, test_settings: Settings):
# 0 or negative would delete every row including the one just written.
with patch("psycopg2.connect") as connect:
with pytest.raises(ValueError):
retention._prune(self._config(retention_days=days), test_settings)
connect.assert_not_called()
@pytest.mark.parametrize("days", ["30", None, 1.5, True])
def test_rejects_non_integer_retention(self, days, test_settings: Settings):
with patch("psycopg2.connect") as connect:
with pytest.raises(ValueError):
retention._prune(self._config(retention_days=days), test_settings)
connect.assert_not_called()
def test_rejects_injection_in_table_before_connecting(self, test_settings: Settings):
with patch("psycopg2.connect") as connect:
with pytest.raises(ValueError):
retention._prune(
self._config(table="check_history; DELETE FROM check_history --"),
test_settings,
)
connect.assert_not_called()
@pytest.mark.executor
@pytest.mark.unit
class TestRetentionBehaviour:
"""Behaviour against a mocked cursor."""
def _mock_conn(self, counts):
cursor = MagicMock()
cursor.fetchone.side_effect = [(c,) for c in counts]
cursor.rowcount = counts[0] if counts else 0
conn = MagicMock()
conn.cursor.return_value.__enter__.return_value = cursor
conn.__enter__.return_value = conn
return conn, cursor
def _config(self, **overrides):
config = {
"database": "sysmon",
"table": "check_history",
"timestamp_column": "ts",
"retention_days": 30,
}
config.update(overrides)
return config
def test_dry_run_does_not_delete(self, test_settings: Settings):
conn, cursor = self._mock_conn([7])
with patch("psycopg2.connect", return_value=conn):
result = retention._prune(self._config(dry_run=True), test_settings)
assert "dry run" in result
assert "7" in result
executed = " ".join(str(c) for c in cursor.execute.call_args_list)
assert "DELETE" not in executed.upper()
def test_no_stale_rows_skips_delete(self, test_settings: Settings):
conn, cursor = self._mock_conn([0])
with patch("psycopg2.connect", return_value=conn):
result = retention._prune(self._config(), test_settings)
assert "nothing to prune" in result
executed = " ".join(str(c) for c in cursor.execute.call_args_list)
assert "DELETE" not in executed.upper()
def test_deletes_and_reports(self, test_settings: Settings):
# count(stale) -> 5, then count(remaining) -> 42
conn, cursor = self._mock_conn([5, 42])
cursor.rowcount = 5
with patch("psycopg2.connect", return_value=conn):
result = retention._prune(self._config(), test_settings)
assert "pruned 5 rows" in result
assert "42 remain" in result
executed = " ".join(str(c) for c in cursor.execute.call_args_list)
assert "DELETE" in executed.upper()
def test_defaults_to_scheduler_database(self, test_settings: Settings):
conn, _ = self._mock_conn([0])
config = self._config()
del config["database"]
with patch("psycopg2.connect", return_value=conn) as connect:
retention._prune(config, test_settings)
assert connect.call_args.kwargs["database"] == test_settings.postgres_db
@pytest.mark.asyncio
async def test_execute_wraps_prune(self, test_settings: Settings):
conn, _ = self._mock_conn([0])
with patch("psycopg2.connect", return_value=conn):
result = await retention.execute(self._config(), test_settings)
assert "nothing to prune" in result