feat: add a retention script downstreams can schedule
The library only ever SELECTs/INSERTs into llm_calls (D15), so expiring rows has to live outside it — holding DELETE would contradict the REVOKE UPDATE, DELETE the deployment template recommends. tools/telemetry_retention.py is dry-run by default and prints the row count, the created_at window and the tenant_id spread so an operator can tell whether the rows about to go are the intended ones. The Postgres branch refuses partitioned targets with exit code 3 (DETACH/DROP PARTITION is O(1); DELETE is not) and otherwise deletes in per-batch transactions. Missing asyncpg exits 2 rather than degrading quietly: this is an ops tool, and a silent "0 rows" reads as "already clean". Exit codes are the contract with the scheduler, so argparse errors were moved off 2 (now 1) to keep "bad flags" distinguishable from "cannot reach the database". The Postgres cases run against the real instance in throwaway schemas — never public.llm_calls — and the batch case asserts the shared table's row count is unchanged, so a search_path that failed to apply lands as a red test instead of a deletion.
This commit is contained in:
@@ -0,0 +1,273 @@
|
||||
"""`tools/telemetry_retention.py` 的 SQLite 分支测试(issue #12 Task 3)。
|
||||
|
||||
一律经 `subprocess` 跑真实脚本 + 真实临时 SQLite 库文件: 脚本是独立运维工具、
|
||||
不被库 import,用 monkeypatch 或直接 import 私有函数测出来的"通过"与运维实际
|
||||
执行的那条路径不是同一条(退出码、argparse 行为、stdout 全都测不到)。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sqlite3
|
||||
import subprocess
|
||||
import sys
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from pathlib import Path
|
||||
|
||||
from polygateway.telemetry.schema import SQLITE_DDL
|
||||
|
||||
_ROOT = Path(__file__).resolve().parents[2]
|
||||
_SCRIPT = _ROOT / "tools" / "telemetry_retention.py"
|
||||
_TIME_FORMAT = "%Y-%m-%d %H:%M:%S"
|
||||
|
||||
# 库写入 SQLite 的 created_at 是 UTC 的 'YYYY-MM-DD HH:MM:SS' 文本(schema 的
|
||||
# DEFAULT (datetime('now'))),测试数据必须同款,否则字符串比较的口径就假了
|
||||
_INSERT = (
|
||||
"INSERT INTO llm_calls (call_id, model, provider, source_name, messages, response, "
|
||||
"prompt_tokens, completion_tokens, usage_source, latency_ms, tenant_id, created_at) "
|
||||
"VALUES (?, 'm', 'p', 's1', '[]', 'ok', 1, 2, 'measured', 10, ?, ?)"
|
||||
)
|
||||
|
||||
|
||||
def _stamp(delta: timedelta) -> str:
|
||||
return (datetime.now(UTC) + delta).strftime(_TIME_FORMAT)
|
||||
|
||||
|
||||
def _make_db(tmp_path: Path, rows: list[tuple[str, str, str]]) -> Path:
|
||||
"""按库的真实 DDL 建临时库并灌入 (call_id, tenant_id, created_at) 三元组。"""
|
||||
path = tmp_path / "telemetry.db"
|
||||
conn = sqlite3.connect(path)
|
||||
try:
|
||||
conn.executescript(SQLITE_DDL)
|
||||
conn.executemany(_INSERT, rows)
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
return path
|
||||
|
||||
|
||||
def _run(*args: str) -> subprocess.CompletedProcess[str]:
|
||||
return subprocess.run(
|
||||
[sys.executable, str(_SCRIPT), *args],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=_ROOT,
|
||||
timeout=120,
|
||||
)
|
||||
|
||||
|
||||
def _rows(path: Path) -> list[str]:
|
||||
conn = sqlite3.connect(path)
|
||||
try:
|
||||
return [r[0] for r in conn.execute("SELECT call_id FROM llm_calls ORDER BY call_id")]
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
|
||||
def _aged_db(tmp_path: Path) -> Path:
|
||||
return _make_db(
|
||||
tmp_path,
|
||||
[
|
||||
("old-1", "", _stamp(timedelta(days=-30))),
|
||||
("old-2", "acme", _stamp(timedelta(days=-20))),
|
||||
("old-3", "acme", _stamp(timedelta(days=-10))),
|
||||
("fresh-1", "acme", _stamp(timedelta(days=-1))),
|
||||
("fresh-2", "", _stamp(timedelta(hours=-1))),
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
class TestSqliteDryRun:
|
||||
def test_dry_run_deletes_nothing_and_reports_counts_range_and_tenants(self, tmp_path):
|
||||
"""缺省(不带 --apply)是 dry-run: 一行不删,且报出足以判断"删的是不是我想删的"的三样。"""
|
||||
path = _aged_db(tmp_path)
|
||||
|
||||
result = _run("--backend", "sqlite", "--path", str(path), "--older-than-days", "7")
|
||||
|
||||
assert result.returncode == 0, result.stderr
|
||||
assert _rows(path) == ["fresh-1", "fresh-2", "old-1", "old-2", "old-3"]
|
||||
assert "将删除行数: 3" in result.stdout
|
||||
assert "created_at 范围:" in result.stdout
|
||||
assert "按 tenant_id 分布" in result.stdout
|
||||
# 空串是"未归属"的哨兵而非 NULL,repr 让它在输出里不被误读成缺失
|
||||
assert "'acme': 2" in result.stdout
|
||||
assert "'': 1" in result.stdout
|
||||
assert "dry-run" in result.stdout
|
||||
|
||||
def test_dry_run_reports_the_actual_created_at_window(self, tmp_path):
|
||||
"""时间范围报的必须是**命中行**的窗口,不是全表的。"""
|
||||
path = _aged_db(tmp_path)
|
||||
|
||||
result = _run("--backend", "sqlite", "--path", str(path), "--older-than-days", "7")
|
||||
|
||||
conn = sqlite3.connect(path)
|
||||
try:
|
||||
low, high = conn.execute(
|
||||
"SELECT MIN(created_at), MAX(created_at) FROM llm_calls WHERE call_id LIKE 'old-%'"
|
||||
).fetchone()
|
||||
finally:
|
||||
conn.close()
|
||||
assert f"{low} ~ {high}" in result.stdout
|
||||
|
||||
|
||||
class TestSqliteApply:
|
||||
def test_apply_removes_only_expired_rows(self, tmp_path):
|
||||
path = _aged_db(tmp_path)
|
||||
|
||||
result = _run(
|
||||
"--backend", "sqlite", "--path", str(path), "--older-than-days", "7", "--apply"
|
||||
)
|
||||
|
||||
assert result.returncode == 0, result.stderr
|
||||
assert _rows(path) == ["fresh-1", "fresh-2"]
|
||||
assert "已删除 3 行" in result.stdout
|
||||
|
||||
def test_older_than_days_zero_deletes_everything_before_now(self, tmp_path):
|
||||
"""N=0 的边界: 截止时刻即"此刻",此刻之前的全删、之后的(未来戳)留下。"""
|
||||
path = _make_db(
|
||||
tmp_path,
|
||||
[
|
||||
("past", "", _stamp(timedelta(seconds=-5))),
|
||||
("future", "", _stamp(timedelta(hours=1))),
|
||||
],
|
||||
)
|
||||
|
||||
result = _run(
|
||||
"--backend", "sqlite", "--path", str(path), "--older-than-days", "0", "--apply"
|
||||
)
|
||||
|
||||
assert result.returncode == 0, result.stderr
|
||||
assert _rows(path) == ["future"]
|
||||
|
||||
def test_vacuum_with_apply_rewrites_the_file(self, tmp_path):
|
||||
path = _aged_db(tmp_path)
|
||||
|
||||
result = _run(
|
||||
"--backend",
|
||||
"sqlite",
|
||||
"--path",
|
||||
str(path),
|
||||
"--older-than-days",
|
||||
"7",
|
||||
"--apply",
|
||||
"--vacuum",
|
||||
)
|
||||
|
||||
assert result.returncode == 0, result.stderr
|
||||
assert "VACUUM" in result.stdout
|
||||
assert _rows(path) == ["fresh-1", "fresh-2"]
|
||||
|
||||
def test_deleting_from_a_db_without_the_table_is_a_backend_failure(self, tmp_path):
|
||||
"""连得上但没有 llm_calls: 属"目标不可用",退出码 2 且**不**静默当成 0 行。"""
|
||||
path = tmp_path / "empty.db"
|
||||
sqlite3.connect(path).close()
|
||||
|
||||
result = _run("--backend", "sqlite", "--path", str(path), "--older-than-days", "7")
|
||||
|
||||
assert result.returncode == 2
|
||||
assert "llm_calls" in result.stderr
|
||||
|
||||
def test_missing_db_file_exits_two(self, tmp_path):
|
||||
result = _run(
|
||||
"--backend", "sqlite", "--path", str(tmp_path / "nope.db"), "--older-than-days", "7"
|
||||
)
|
||||
|
||||
assert result.returncode == 2
|
||||
assert "nope.db" in result.stderr
|
||||
|
||||
|
||||
class TestUsageErrors:
|
||||
"""参数层的一切错误都是退出码 1(argparse 默认的 2 已被本脚本改写,2 留给连接失败)。"""
|
||||
|
||||
def test_sqlite_with_dsn_exits_one(self, tmp_path):
|
||||
result = _run(
|
||||
"--backend",
|
||||
"sqlite",
|
||||
"--path",
|
||||
str(tmp_path / "x.db"),
|
||||
"--dsn",
|
||||
"postgresql://x/y",
|
||||
"--older-than-days",
|
||||
"7",
|
||||
)
|
||||
|
||||
assert result.returncode == 1
|
||||
assert "--dsn" in result.stderr
|
||||
|
||||
def test_sqlite_without_path_exits_one(self):
|
||||
result = _run("--backend", "sqlite", "--older-than-days", "7")
|
||||
|
||||
assert result.returncode == 1
|
||||
assert "--path" in result.stderr
|
||||
|
||||
def test_sqlite_with_batch_size_exits_one(self, tmp_path):
|
||||
result = _run(
|
||||
"--backend",
|
||||
"sqlite",
|
||||
"--path",
|
||||
str(tmp_path / "x.db"),
|
||||
"--older-than-days",
|
||||
"7",
|
||||
"--batch-size",
|
||||
"10",
|
||||
)
|
||||
|
||||
assert result.returncode == 1
|
||||
assert "--batch-size" in result.stderr
|
||||
|
||||
def test_postgres_with_vacuum_exits_one(self):
|
||||
result = _run(
|
||||
"--backend",
|
||||
"postgres",
|
||||
"--dsn",
|
||||
"postgresql://x/y",
|
||||
"--older-than-days",
|
||||
"7",
|
||||
"--apply",
|
||||
"--vacuum",
|
||||
)
|
||||
|
||||
assert result.returncode == 1
|
||||
assert "--vacuum" in result.stderr
|
||||
|
||||
def test_vacuum_without_apply_exits_one(self, tmp_path):
|
||||
result = _run(
|
||||
"--backend",
|
||||
"sqlite",
|
||||
"--path",
|
||||
str(tmp_path / "x.db"),
|
||||
"--older-than-days",
|
||||
"7",
|
||||
"--vacuum",
|
||||
)
|
||||
|
||||
assert result.returncode == 1
|
||||
assert "--apply" in result.stderr
|
||||
|
||||
def test_missing_older_than_days_exits_one(self, tmp_path):
|
||||
result = _run("--backend", "sqlite", "--path", str(tmp_path / "x.db"))
|
||||
|
||||
assert result.returncode == 1
|
||||
|
||||
def test_negative_older_than_days_exits_one(self, tmp_path):
|
||||
result = _run(
|
||||
"--backend", "sqlite", "--path", str(tmp_path / "x.db"), "--older-than-days", "-1"
|
||||
)
|
||||
|
||||
assert result.returncode == 1
|
||||
assert "--older-than-days" in result.stderr
|
||||
|
||||
def test_unknown_backend_exits_one(self, tmp_path):
|
||||
result = _run("--backend", "mysql", "--path", str(tmp_path / "x.db"))
|
||||
|
||||
assert result.returncode == 1
|
||||
|
||||
|
||||
class TestHelp:
|
||||
def test_help_names_the_maintenance_role_and_the_recommended_path(self):
|
||||
"""帮助文本是运维唯一会读的文档,权限口径与"推荐不是 DELETE"必须在里面。"""
|
||||
result = _run("--help")
|
||||
|
||||
assert result.returncode == 0
|
||||
assert "维护角色" in result.stdout
|
||||
assert "REVOKE" in result.stdout
|
||||
assert "PARTITION" in result.stdout
|
||||
Reference in New Issue
Block a user