fix: escape all LIKE specials in step-row cleanup

This commit is contained in:
2026-07-17 01:17:02 -04:00
parent 16993ed362
commit b3aba7c31d
2 changed files with 43 additions and 3 deletions
+20 -3
View File
@@ -602,6 +602,21 @@ def _write_skip_report(
)
def _escape_sql_like(text: str) -> str:
"""转义 SQL LIKE 模式中的全部特殊字符(`\\`、`%`、`_`)为字面匹配。
参数:
text: 待作为 LIKE 前缀字面使用的原始字符串。
返回:
可安全拼入 `LIKE ? ESCAPE '\\'` 模式的转义串。
关键实现细节:
反斜杠必须最先转义,否则会二次转义后续替换产生的转义符。
"""
return text.replace("\\", "\\\\").replace("%", r"\%").replace("_", r"\_")
def _clear_step_rows(db_path: str, *, baseline_run_id: str, epoch: int, step: int) -> None:
"""清空一个 step 的全部旧行(rollout + gate 派生),保证崩溃重跑幂等。
@@ -621,13 +636,15 @@ def _clear_step_rows(db_path: str, *, baseline_run_id: str, epoch: int, step: in
无。
关键实现细节:
predictions/traces 的 gate 行按 LIKE 前缀删除,'_' 通配显式转义
(ESCAPE)钉死字面匹配,避免 `..._s1` 误匹配 `..._s10` 类前缀陷阱。
predictions/traces 的 gate 行按 LIKE 前缀删除,`\\`/`%`/`_` 三个 LIKE
特殊字符全部显式转义(ESCAPE)钉死字面匹配,避免 `..._s1` 误匹配
`..._s10` 类前缀陷阱,也防 run_id 含 `%`/`\\` 时通配误删他 run 行。
"""
from app.harness.inference import PREDICTIONS_SCHEMA, TRACES_SCHEMA
from app.harness.log import HarnessLog
step_run_id = f"{baseline_run_id}_e{epoch}_s{step}"
escaped = _escape_sql_like(step_run_id)
with HarnessLog(db_path, step_run_id, register_run=False) as log:
log.create_table("predictions", PREDICTIONS_SCHEMA)
log.create_table("traces", TRACES_SCHEMA)
@@ -635,7 +652,7 @@ def _clear_step_rows(db_path: str, *, baseline_run_id: str, epoch: int, step: in
log.execute(f"DELETE FROM {table} WHERE run_id=?", (step_run_id,))
log.execute(
f"DELETE FROM {table} WHERE run_id LIKE ? ESCAPE '\\'",
(step_run_id.replace("_", r"\_") + r"\_gate\_%",),
(escaped + r"\_gate\_%",),
)
for table in ("gate_evidence", "quadrant_pair"):
exists = log.query(
+23
View File
@@ -67,3 +67,26 @@ def test_clear_step_rows_missing_tables_is_noop(tmp_path) -> None:
conn.commit()
conn.close()
_clear_step_rows(str(db), baseline_run_id="infer_adhoc", epoch=1, step=0)
def test_clear_step_rows_like_specials_in_run_id(tmp_path) -> None:
"""run_id 含 % 与反斜杠时不通配误删他 run 行(LIKE 全特殊字符转义回归锁)。"""
db = tmp_path / "harness.db"
conn = sqlite3.connect(db)
conn.execute("CREATE TABLE predictions (run_id TEXT, question_id TEXT)")
conn.execute("CREATE TABLE traces (run_id TEXT, question_id TEXT)")
rows = [
(r"we%ird\run_e1_s0", "q1"), # 本 step rollout
(r"we%ird\run_e1_s0_gate_x_base", "q2"), # 本 step gate 行
(r"weXird\run_e1_s0_gate_x_base", "q3"), # % 若未转义会误匹配此行
(r"we%irdXrun_e1_s0_gate_x_base", "q4"), # \ 若未转义会误匹配此行
]
conn.executemany("INSERT INTO predictions VALUES (?, ?)", rows)
conn.executemany("INSERT INTO traces VALUES (?, ?)", rows)
conn.commit()
conn.close()
_clear_step_rows(str(db), baseline_run_id=r"we%ird\run", epoch=1, step=0)
conn = sqlite3.connect(db)
left = {r[0] for r in conn.execute("SELECT run_id FROM predictions")}
conn.close()
assert left == {r"weXird\run_e1_s0_gate_x_base", r"we%irdXrun_e1_s0_gate_x_base"}