test: close two always-green holes in the dimension tests

The cache-key test only asserted a hit, so a key degraded to a constant
would still pass it. Adding a namespace control group that must miss
proves the key still distinguishes inputs; verified by degrading
build_cache_key to a constant and watching the case go red.

The allow_nan=False branch had no test at all. A ChatRequest built with
a nan meta value (bypassing the entry validation, i.e. a future entry
point that forgets to validate) must drop the row and not raise;
verified red by removing allow_nan=False.

Also restore the read-only file permissions in a finally block, so a
failing assertion does not get masked by a PermissionError from tmp_path
cleanup; rename the warnings fixture to captured_warnings so it stops
shadowing the stdlib module; and drop a downstream business term from a
fixture value (zero-business-assumption rule).
This commit is contained in:
2026-08-17 12:28:47 -04:00
parent 9bdd312928
commit b6165ff438
3 changed files with 51 additions and 14 deletions
+10 -6
View File
@@ -424,7 +424,7 @@ CREATE TABLE {schema}.llm_calls (
_PRE_TENANT_INSERT = (
"INSERT INTO {schema}.llm_calls (call_id, model, provider, source_name, messages, response, "
"prompt_tokens, completion_tokens, usage_source, latency_ms) "
"VALUES ($1, 'm', 'p', 's1', '[]', 'contract text', 1, 2, 'measured', 10)"
"VALUES ($1, 'm', 'p', 's1', '[]', 'old body', 1, 2, 'measured', 10)"
)
@@ -434,8 +434,12 @@ def _search_path_dsn(dsn: str, schema: str) -> str:
@pytest.fixture
async def warnings():
"""捕获库发出的 WARNING;loguru 不经标准 logging,pytest 的 caplog 抓不到。"""
async def captured_warnings():
"""捕获库发出的 WARNING;loguru 不经标准 logging,pytest 的 caplog 抓不到。
名字避开裸 `warnings`: 那会遮蔽标准库模块名,本文件将来任何一次
`import warnings` 都会与它静默互相顶掉,而报错点离真因很远。
"""
from loguru import logger
messages: list[str] = []
@@ -608,7 +612,7 @@ class TestCallerDimensionsAcceptance:
await conn.close()
async def test_backfill_failure_degrades_per_row_not_wholesale(
self, least_privilege_pre_tenant_dsn, warnings
self, least_privilege_pre_tenant_dsn, captured_warnings
):
"""补列失败的降级方向: 记 warning、不置 `_failed`、后续 INSERT 仍照发。
@@ -619,8 +623,8 @@ class TestCallerDimensionsAcceptance:
try:
await _record_minimal(recorder, call_id=_cid("lpp1")) # 不得抛
assert recorder._failed is False
assert any("补列失败" in m for m in warnings)
assert any("补列失败" in m for m in captured_warnings)
# 缺列的表上 INSERT 必然失败;逐行 warning 正是"INSERT 照发了"的证据
assert any("写入失败" in m for m in warnings)
assert any("写入失败" in m for m in captured_warnings)
finally:
await recorder.aclose()
+12 -2
View File
@@ -232,13 +232,23 @@ class TestCallerDimensions:
assert recorder.rows == []
async def test_meta_does_not_enter_cache_key(self):
"""仅 meta 不同必须仍命中缓存(F1): 进 key 会让存量缓存全量冷启动且不报错。"""
client = _client(cache=InMemoryCache(), cache_namespace="proj", cache_ttl_s=3600)
"""仅 meta 不同必须仍命中缓存(F1): 进 key 会让存量缓存全量冷启动且不报错。
带对照组: 只断言"命中"的话,缓存 key 退化成常量(忽略一切输入)时本用例
照样绿——那是恒真断言。故再改一个**确实进 key** 的维度(namespace)断言
miss,证明 key 仍在区分输入,"meta 不进 key"才是被测出来的结论。
"""
cache = InMemoryCache() # 两个 client 共用一份存储,否则对照组的 miss 是白来的
client = _client(cache=cache, cache_namespace="proj", cache_ttl_s=3600)
async with client:
first = await client.chat(self._MSG, meta={"batch": "b-1"})
second = await client.chat(self._MSG, meta={"batch": "b-2"})
assert first.cache_hit is False and second.cache_hit is True
other_ns = _client(cache=cache, cache_namespace="other", cache_ttl_s=3600)
async with other_ns:
assert (await other_ns.chat(self._MSG, meta={"batch": "b-1"})).cache_hit is False
class TestModelFingerprint:
"""配置级采样参数须进缓存身份,否则改 temperature 后仍读旧缓存(决策 C)。"""
+25 -2
View File
@@ -318,7 +318,7 @@ CREATE TABLE llm_calls (
_PRE_TENANT_INSERT = (
"INSERT INTO llm_calls (call_id, model, provider, source_name, messages, response, "
"prompt_tokens, completion_tokens, usage_source, latency_ms) "
"VALUES ('old-row', 'm', 'p', 's1', '[]', 'contract text', 1, 2, 'measured', 10)"
"VALUES ('old-row', 'm', 'p', 's1', '[]', 'old body', 1, 2, 'measured', 10)"
)
@@ -399,12 +399,16 @@ class TestSQLiteCallerDimensionsAcceptance:
conn.close()
db.chmod(0o444)
# finally 还原权限位: 任一断言先失败时,不还原会让 tmp_path 清理连带报错,
# 把"某条断言失败"的真因盖成一个无关的 PermissionError
try:
recorder = SQLiteRecorder(db) # 不得抛
assert recorder._conn is not None # 补列失败 ≠ recorder 失能
await _record_minimal(recorder, call_id="doomed") # 只读库写不进,但不得抛
recorder.close()
finally:
db.chmod(0o644)
db.chmod(0o644) # 还原,让 tmp_path 清理不受阻
stale = sqlite3.connect(db)
assert [r[1] for r in stale.execute("PRAGMA table_info(llm_calls)")] == (
_EXPECTED_COLUMNS[:-2]
@@ -875,6 +879,25 @@ class TestEmitterCallerDimensions:
)
assert "研发" in rec.rows[0]["meta"]
async def test_non_finite_meta_value_drops_the_row_instead_of_poisoning_it(self):
"""入口失守时 `allow_nan=False` 的真实结果: 整行降级丢弃,且不抛给调用方。
直接构造带 `nan` 的 `ChatRequest`(绕过 `validate_caller_dimensions` 这道
主防线,模拟将来某个新入口忘记校验)。没有 `allow_nan=False` 时,
`json.dumps` 会写出裸 `NaN` 字面量——PG 的 JSONB 会拒收,但 **SQLite 的
`meta` 是 TEXT 列不做校验**,那串非法 JSON 会被静默存进去,污染此后一切
按 JSON 解析 meta 的分析。宁可丢一行遥测,也不要一行毒数据。
同时断言不抛: 遥测的降级方向是"静默降级"(铁律),把调用方的一次正常
业务调用因为一个维度值炸掉,方向反了。
"""
rec = _MemoryRecorder()
req = ChatRequest(messages=[{"role": "user", "content": "hi"}], meta={"k": float("nan")})
await TelemetryEmitter(rec).emit_terminal_failure(
request=req, call_id="c", latency_ms=1, error="dead"
)
assert rec.rows == []
class TestCostWithCachedTier:
"""issue #3: 命中部分按缓存单价计费,避免 cost 系统性高估。"""